WO2019141102A1 - 一种基于场景识别的自适应音频控制装置和方法 - Google Patents

一种基于场景识别的自适应音频控制装置和方法 Download PDF

Info

Publication number
WO2019141102A1
WO2019141102A1 PCT/CN2019/070657 CN2019070657W WO2019141102A1 WO 2019141102 A1 WO2019141102 A1 WO 2019141102A1 CN 2019070657 W CN2019070657 W CN 2019070657W WO 2019141102 A1 WO2019141102 A1 WO 2019141102A1
Authority
WO
WIPO (PCT)
Prior art keywords
ambient sound
sound signal
signal
user
noise reduction
Prior art date
Application number
PCT/CN2019/070657
Other languages
English (en)
French (fr)
Inventor
赵剑
刘建丹
Original Assignee
北京小鸟听听科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小鸟听听科技有限公司 filed Critical 北京小鸟听听科技有限公司
Priority to EP19741628.2A priority Critical patent/EP3672274A4/en
Priority to US16/647,768 priority patent/US10979814B2/en
Publication of WO2019141102A1 publication Critical patent/WO2019141102A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • H04R1/1041—Mechanical or electronic switches, or control elements
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
    • G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
    • G10K11/1783—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase handling or detecting of non-standard events or conditions, e.g. changing operating modes under specific operating conditions
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
    • G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
    • G10K11/1783—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase handling or detecting of non-standard events or conditions, e.g. changing operating modes under specific operating conditions
    • G10K11/17837—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase handling or detecting of non-standard events or conditions, e.g. changing operating modes under specific operating conditions by retaining part of the ambient acoustic environment, e.g. speech or alarm signals that the user needs to hear
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
    • G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
    • G10K11/1787—General system configurations
    • G10K11/17879—General system configurations using both a reference signal and an error signal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
    • H04R1/22—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired frequency characteristic only 
    • H04R1/222—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired frequency characteristic only  for microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R3/00—Circuits for transducers, loudspeakers or microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R5/00—Stereophonic arrangements
    • H04R5/04—Circuit arrangements, e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • H04R1/1083—Reduction of ambient noise
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
    • H04R1/22—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired frequency characteristic only 
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2410/00—Microphones
    • H04R2410/05—Noise reduction with a separate noise microphone
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2430/00—Signal processing covered by H04R, not provided for in its groups
    • H04R2430/01—Aspects of volume control, not necessarily automatic, in sound systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2430/00—Signal processing covered by H04R, not provided for in its groups
    • H04R2430/03—Synergistic effects of band splitting and sub-band processing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2460/00—Details of hearing devices, i.e. of ear- or headphones covered by H04R1/10 or H04R5/033 but not provided for in any of their subgroups, or of hearing aids covered by H04R25/00 but not provided for in any of its subgroups
    • H04R2460/01—Hearing devices using active noise cancellation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2460/00—Details of hearing devices, i.e. of ear- or headphones covered by H04R1/10 or H04R5/033 but not provided for in any of their subgroups, or of hearing aids covered by H04R25/00 but not provided for in any of its subgroups
    • H04R2460/07—Use of position data from wide-area or local-area positioning systems in hearing devices, e.g. program or information selection

Definitions

  • the present application relates to electroacoustic conversion technology, and more particularly to an adaptive audio control apparatus and method based on scene recognition.
  • an audio playback device with passive/active noise reduction function such as a noise canceling earphone
  • a noise canceling earphone has appeared to eliminate the influence of noise on the user.
  • the inventor has found that only eliminating noise can no longer satisfy the user's demand for the playback effect, and the user wants the audio playback device to be more intelligent and can automatically adjust the playback effect to adapt to the current playback environment.
  • the equivalent continuous A sound level is usually used to evaluate the environmental noise.
  • the ambient noise is lower than 50dBA, people feel that the environment is relatively quiet.
  • the noise is greater than 80dBA, people will feel that the surrounding environment is noisy.
  • the noise reaches 120dBA, people will feel unbearable. In the noise environment above 90dBA for a long time, the possibility of hearing damage is obviously increased.
  • the purpose of the present application is to provide an adaptive audio control scheme based on scene recognition to automatically adjust the playback effect according to the user's usage scene.
  • the control module includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the following steps:
  • the ambient sound adjustment module includes any one or combination of the following sub-modules: a wind noise suppression sub-module, a voice enhancement sub-module, a dynamic range control sub-module, and an EQ equalization processing sub-module.
  • the analyzing the usage scenario of the user according to the acceleration data output by the acceleration sensor and the geographic location data output by the positioning module includes:
  • a user's exercise mode is determined based on the moving speed and the step frequency value.
  • the type of environment includes an indoor environment and a road environment;
  • the sport mode includes any of the following: a still mode, a road walking mode, and a boarding mode.
  • the user is in the still mode
  • the user is in the walking mode
  • the user is in the boarding mode.
  • the device further includes a bone conduction microphone or an infrared proximity sensor, and the usage scenario of the user further includes a speaking state of the user;
  • the computer program when executed by the processor, implements the following steps:
  • the ambient sound collection microphone is a plurality of microphones including a microphone for collecting the ambient sound of the user's real-time location and a microphone for collecting ambient sounds heard near the user's auricle.
  • the sound level intensity according to the usage scenario, the ambient sound signal, and the energy and spectrum of the ambient sound The distribution controls the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • the control wind noise suppression sub-module performs suppression filtering on the wind noise signal in the ambient sound signal
  • the control dynamic range control sub-module performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal
  • control dynamic range control sub-module performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal, include:
  • the ambient sound signal is amplified
  • the ambient sound signal is attenuated.
  • the performing EQ compensation processing on the ambient sound signal comprises performing EQ compensation processing on the voice signal frequency band and the whistle signal frequency band in the ambient sound signal.
  • the usage scenario is that the user is in a road environment and is in a walking mode
  • controlling according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound further includes:
  • the spectrum distribution controls the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • the operating parameters of the audio signal volume adjustment module are controlled according to the sound level intensity of the ambient sound signal arriving at the speaker such that the audio level at the speaker and the ambient sound signal arriving at the speaker maintain a predetermined ratio.
  • the spectrum distribution controls the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • Controlling the wind noise suppression sub-module is turned off; and/or,
  • the dynamic range control Monitoring whether the sound level intensity of the ambient sound signal is greater than a preset sound level intensity upper limit or less than a preset sound level intensity lower limit, and if the sound level intensity of the ambient sound signal is greater than a preset sound level intensity upper limit, triggering the dynamic range control
  • the module attenuates the ambient sound signal. If the sound level intensity of the ambient sound signal is less than the preset sound level intensity lower limit, the dynamic range control sub-module is triggered to amplify the ambient sound signal.
  • the sound level intensity according to the usage scenario, the ambient sound signal, and the ambient sound The energy and spectrum distribution control the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • Control the audio signal volume adjustment module to turn down the volume or pause the audio signal.
  • the sound level intensity according to the usage scenario, the ambient sound signal, and the ambient sound The energy and spectrum distribution control the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, and further includes:
  • control wind noise suppression sub-module and the dynamic range control sub-module are turned off.
  • the device is an earphone.
  • an adaptive audio control method based on scene recognition including the following steps:
  • the ambient sound adjustment module includes any one or combination of the following sub-modules: a wind noise suppression sub-module, a voice enhancement sub-module, a dynamic range control sub-module, and an EQ equalization processing sub-module.
  • the analyzing the usage scenario of the user according to the acceleration data and the geographic location data includes:
  • a user's exercise mode is determined based on the moving speed and the step frequency value.
  • the type of environment includes an indoor environment and a road environment;
  • the sport mode includes any of the following: a still mode, a road walking mode, and a boarding mode.
  • the user is in the still mode
  • the user is in the walking mode
  • the user is in the boarding mode.
  • the audio playback device further includes a bone conduction microphone or an infrared proximity sensor
  • the usage scenario of the user further includes a speaking state of the user
  • the method further includes the following steps:
  • the collecting an ambient sound signal of the environment in which the user is located includes collecting a real-time ambient sound signal of the user and collecting an ambient sound signal heard near the user's pinna.
  • the sound level intensity according to the usage scenario, the ambient sound signal, and the energy and spectrum of the ambient sound The distribution controls the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • the control wind noise suppression sub-module performs suppression filtering on the wind noise signal in the ambient sound signal
  • the control dynamic range control sub-module performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal
  • control dynamic range control sub-module performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal, include:
  • the ambient sound signal is amplified
  • the ambient sound signal is attenuated.
  • the performing EQ compensation processing on the ambient sound signal comprises performing EQ compensation processing on the voice signal frequency band and the whistle signal frequency band in the ambient sound signal.
  • the usage scenario is that the user is in a road environment and is in a walking mode
  • controlling according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound further includes:
  • the spectrum distribution controls the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • the spectrum distribution controls the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • Controlling the wind noise suppression sub-module is turned off; and/or,
  • the dynamic range control Monitoring whether the sound level intensity of the ambient sound signal is greater than a preset sound level intensity upper limit or less than a preset sound level intensity lower limit, and if the sound level intensity of the ambient sound signal is greater than a preset sound level intensity upper limit, triggering the dynamic range control
  • the module attenuates the ambient sound signal. If the sound level intensity of the ambient sound signal is less than the preset sound level intensity lower limit, the dynamic range control sub-module is triggered to amplify the ambient sound signal.
  • the sound level intensity according to the usage scenario, the ambient sound signal, and the ambient sound The energy and spectrum distribution control the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, including:
  • Control the audio signal volume adjustment module to turn down the volume or pause the audio signal.
  • the sound level intensity according to the usage scenario, the ambient sound signal, and the ambient sound The energy and spectrum distribution control the operation of the audio signal volume adjustment module, the active noise reduction module, and the ambient sound adjustment module, and further includes:
  • control wind noise suppression sub-module and the dynamic range control sub-module are turned off.
  • the audio playback device is an earphone.
  • a method for controlling an audio playback device comprising the steps of: acquiring acceleration data of a user, analyzing a usage scenario of the user according to the acceleration data; acquiring an environmental sound signal of the environment in which the user is located, and calculating the environment The sound level intensity of the sound signal, and analyze the energy and spectral distribution of the ambient sound signal; control the audio signal volume and active of the audio playback device according to the use scene, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound signal Noise reduction level and adjustment of the ambient sound signal.
  • the method further includes the following steps: acquiring geographic location data of the user; wherein the usage scenario of the user is analyzed according to the acceleration data and the geographic location data.
  • a system for controlling an audio playback device comprising: one or more processors; a memory coupled to at least one of the one or more processors; a computer stored in the memory
  • the program instructions when executed by the at least one processor, cause the system to perform a method of controlling the audio playback device, the method comprising: acquiring acceleration data of the user, analyzing a usage scenario of the user according to the acceleration data; and acquiring an environment in which the user is located Ambient sound signal, calculate the sound level intensity of the ambient sound signal, and analyze the energy and spectral distribution of the ambient sound signal; control audio playback according to the use scene, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound signal The audio signal volume of the device, the active noise reduction level, and the adjustment of the ambient sound signal.
  • a computer program product capable of implementing the method of controlling an audio playback device as described in the third aspect of the present application when the computer program product is executed by a processor.
  • the above scene recognition-based adaptive audio control apparatus and method provided by the present application can analyze a user's use scene and automatically adjust the play effect according to the use scene.
  • FIG. 1 is a block diagram of a scene recognition based adaptive audio control apparatus provided by an embodiment of the present application.
  • FIG. 2 is a block diagram of a scene recognition based adaptive audio control apparatus according to still another embodiment of the present application.
  • FIG. 3 is a block diagram of a scene recognition based adaptive audio control apparatus according to still another embodiment of the present application.
  • FIG. 4 is a flowchart of a scene recognition based adaptive audio control method provided by an embodiment of the present application.
  • the present application proposes an adaptive audio control device based on scene recognition.
  • the device can be a headset, a speaker, or other electronic device capable of playing an audio signal.
  • the device can perform wired communication or wireless communication with a terminal device such as a mobile phone or a computer to play an audio signal of the terminal device.
  • the device can also store an audio signal, such as music, which can play its own stored audio signal.
  • the device can also be set up inside the terminal device as part of the terminal device.
  • the scene recognition-based adaptive audio control apparatus includes an ambient sound collection microphone 13 , an acceleration sensor 11 , a positioning module 12 , a control module 21 , and an audio signal volume adjustment module 22 .
  • the acceleration sensor 11 is configured to collect acceleration data of the user, and output acceleration data to the control module 21.
  • the positioning module 12 is configured to collect geographic location data of the user, and output geographic location data to the control module 21.
  • the audio signal is adjusted by the audio signal volume adjustment module 22 and then input to the speaker 30 for playback.
  • the ambient sound collection microphone 13 is configured to pick up an ambient sound signal, and feed the picked ambient sound signal to the control module 21, the active noise reduction module 23, and the ambient sound adjustment module 24, respectively.
  • the outputs of the active noise reduction module 23 and the ambient sound adjustment module 24 are respectively connected to the horn 30.
  • the control module 21 is respectively connected to the audio signal volume adjustment module 22, the active noise reduction module 23 and the ambient sound adjustment module 24 to control the operation of the three, for example, the control module 21 turns on/off a certain module or sub-module, or adjusts a certain Parameters of modules or submodules, etc.
  • the active noise reduction module 23 is configured to generate a corresponding noise reduction signal for the ambient sound signal, and output the noise reduction signal to the horn 30.
  • the noise reduction signal and the ambient sound signal cancel each other out in the ear canal of the user to reduce the influence of the external environment sound on the user listening to the audio signal.
  • the active noise reduction module 24 can have a feedback noise reduction mode, a feedforward noise reduction mode, and a feedforward combined feedback noise reduction mode.
  • the active noise reduction module 23 is only turned on when the sound level of the ambient sound reaches 60dBA; the active noise reduction module 23 can be provided with various noise reduction levels, such as when the sound level of the ambient sound When the intensity reaches 60dBA, 70dBA, 80dBA, and 90dBA respectively, each corresponds to a noise reduction level, and the stronger the sound level intensity of the ambient sound, the higher the noise reduction level.
  • the ambient sound adjustment module 24 is configured to adjust the ambient sound signal and output the adjusted ambient sound signal to the speaker 30.
  • the ambient sound adjustment module 24 includes the following sub-modules: a wind noise suppression sub-module 241, a speech enhancement sub-module 242, a dynamic range control sub-module 243, and an EQ equalization processing sub-module 244.
  • the wind noise suppression sub-module 241 is mainly used to filter out wind noise in the ambient sound signal. Wind noise is mainly concentrated in a very low frequency range. Once a relatively large wind noise is detected, different filters can be set to cope with it to reduce the influence of wind noise on the user listening to the audio signal. In a specific example, when the user is in an outdoor environment, whether the wind noise suppression sub-module 241 needs to be turned on may be determined according to the energy and spectrum distribution of the wind noise; when the user is in the indoor environment, the wind noise suppression sub-module may be turned off. 241.
  • the voice enhancement sub-module 242 is mainly used to enhance the voice part in the ambient sound signal, suppress and reduce noise interference, and improve the signal-to-noise ratio of the voice part, so that the user can hear the external voice more clearly.
  • the speech enhancement sub-module 241 is turned on when the user is in a speech state.
  • the voice enhancement sub-module 241 is turned on when the user is in a state in which it is necessary to hear the external voice.
  • the speech enhancement sub-module 242 can perform enhancement processing on the speech signal in the ambient sound signal and suppress the environmental noise to implement the speech enhancement function.
  • the dynamic range control sub-module 243 is mainly used for dynamic range adjustment of the ambient sound signal. For example, some pulse sounds may be compressed and then fed to the earphone to avoid causing a large break in the earphone end. In a specific example, the dynamic range control sub-module 243 is in an open state in each case to avoid the frightening damage of the bursting sound to the user. In another specific example, when the user is in an outdoor environment, the dynamic range control sub-module 243 must be turned on. When the user is in the indoor environment, the dynamic range control sub-module 243 can be turned off because the bursting sound in the indoor environment is relatively small. .
  • the EQ equalization processing sub-module 244 is mainly used to enhance and attenuate ambient sounds for different frequency bands to optimize the listening sound of the ambient sound. In a specific example, if a portion of the ambient sound needs to be heard, the EQ equalization processing sub-module 244 is turned on to compensate for the ambient sound of the portion of the band.
  • FIG. 2 a scene recognition based adaptive audio control apparatus according to another embodiment of the present application is provided.
  • the embodiment of Figure 2 has all of the structure and functionality provided by the embodiment of Figure 1, with the main difference being that the apparatus of the embodiment of Figure 2 further includes a bone conduction microphone 14 to which the output of the bone conduction microphone 14 is coupled.
  • FIG. 3 a scene recognition-based adaptive audio control apparatus according to still another embodiment of the present application is provided.
  • the embodiment of FIG. 3 has all of the structures and functions provided by the embodiment of FIG. 1.
  • the main difference is that the apparatus of the embodiment of FIG. 3 further includes an infrared proximity sensor 15 facing the front of the user, and the output of the infrared proximity sensor 15 is connected to the control module 21.
  • the ambient sound adjustment module 24 includes the following sub-modules: a wind noise suppression sub-module 241, a speech enhancement sub-module 242, a dynamic range control sub-module 243, and an EQ equalization processing sub-module 244.
  • the ambient sound adjustment module 24 may also include any or a combination of the above sub-modules or other sub-modules.
  • the device may also be provided with a passive noise reduction structure composed of a sound insulating material, and the passive noise reduction is physical noise reduction, and the noise that is transmitted to the ear canal through the outer casing and the ear cover is isolated.
  • This passive noise reduction method has a good effect on noise above 1 kHz.
  • the device may also be provided with a manual volume adjustment device, a manual noise reduction mode switching device, a manual ambient sound adjustment device, etc. to provide the user with more options.
  • the ambient sound collection microphones 13 may be one or more.
  • the left and right earphones are respectively provided with an ambient sound collection microphone.
  • only the left earphone is provided with an ambient sound collection microphone.
  • only the right earphone is provided with an ambient sound collection microphone.
  • a microphone disposed in the earphone casing for collecting the ambient sound of the user.
  • a microphone disposed inside the earphone for collecting ambient sound heard at the user's auricle.
  • the ambient sound collection microphones 13 are a plurality of microphones including a microphone for collecting ambient sounds of the user's real-time location and a microphone for collecting ambient sounds heard near the user's auricle.
  • control module 21 includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the following steps are implemented. :
  • the user's usage scenario may be analyzed based on the acceleration data output by the acceleration sensor.
  • the geographic location data collected by the positioning module 12 may also be acquired at this step, and the acceleration usage data and the geographic location data of the user are used to jointly analyze the usage scenario of the user.
  • the composition of the ambient sound can be obtained by analyzing the energy and spectral distribution of the ambient sound signal, such as whether the ambient sound contains a voice component, a warning tone component such as a siren, a wind noise component, and the like, and the energy of these components.
  • the control module 21 can automatically adjust the noise reduction parameters of the active noise reduction module 24 according to the usage scenario to achieve different noise reduction levels or effects; or the active noise reduction module 23 presets multiple noise reduction modes, each of which is reduced in noise. The mode corresponds to different noise reduction parameters, and the control module 21 automatically adjusts the noise reduction mode of the active noise reduction module 23 according to the usage scenario to achieve different noise reduction levels or effects.
  • the control module 21 controls the audio signal volume adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24 according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound.
  • the operation that is, the control module 21 comprehensively considers the sound level intensity of the ambient sound signal, the composition of the ambient sound and the energy of each component, and controls the audio signal volume adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24
  • the work is such that the audio control is adapted to the user's usage scene, and the audio control is adaptively performed according to the user's usage scene, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound.
  • analyzing the usage scenario of the user in step 101 includes:
  • the motion mode may include any of the following: a still mode, a road walking mode, and a boarding mode.
  • the exercise mode may include a fitness mode, and the fitness mode covers a fitness mode such as running, riding, and the like.
  • the user's usage scenario may be analyzed based only on the acquired user acceleration data without acquiring geographic location data.
  • the user's exercise mode can be determined based only on the user's stride value.
  • the user's moving speed may be calculated using only the geographic location data without using the geographic location data to obtain the environmental type.
  • the usage scenario of the user may further include the speaking state of the user.
  • the control module 21 determines whether the user is based on the signal output by the bone conduction microphone 14 or the infrared proximity sensor 15. In speech mode.
  • the usage scenario referred to in the embodiment of the present application includes at least the current motion mode of the user, and further includes the type of the environment in which the user is currently located and/or the speaking state of the user, that is, whether the user is in the speaking mode.
  • the control module 21 can determine, according to the geographic location data, an environment type in which the user is located.
  • the types of environments include indoor environments and road environments.
  • the positioning module 12 can include, for example, a GPS module or a Beidou module.
  • the positioning module first obtains the specific real-time location information of the user, and then determines the real-time location information according to the specific real-time location information. The type of environment the user is in.
  • the environment type can also be more detailed to achieve a more flexible and intelligent audio control effect.
  • the outdoor environment type is divided into a road environment type and a non-road outdoor environment type, and the non-road outdoor environment type can be further divided into an open-air trade catering type, an outdoor park green type, and the like.
  • the environment type can be divided into the following types:
  • Environmental type P 1 main and secondary trunk roads, intercity, urban expressway trunk lines, inland waterways and both sides;
  • Environmental type P 3 industrial production, warehouse logistics area
  • the types of environments in the embodiments of the present application may be classified into “indoor” and “outdoor”, and may further be subdivided for “outdoor” environment types, for example, “outdoor sports field”, “outdoor park green space”, and “outdoor set”. City” and other environmental types.
  • the type of the environment in which the user is currently located may be determined according to the user's selection.
  • the specific motion mode of the user may also be determined according to the geographic location data and the energy and spectrum distribution of the ambient sound signal. For example, according to the energy and spectrum distribution of the ambient sound signal, the ambient sound signal is included. The strong wind noise signal, combined with the geographical location data, can accurately determine that the user is in an outdoor environment.
  • the control module 21 may calculate a moving speed of the user according to the geographic location data, and calculate a step frequency value of the user according to the acceleration data. A user's exercise mode is determined based on the moving speed and the step frequency value.
  • the first frequency threshold may be set to 0.5 steps/second
  • the first speed threshold may be set to 0.2 meters/second, that is, if the user's moving speed is less than 0.2 meters/second and the step is If the frequency is less than 0.5 steps/second, the user is in the still mode.
  • the speed range in which a person walks normally is 1 m/s to 1.7 m/s, and the interval value of a normal walking step is 1.0 steps/second to 2.5 steps/second.
  • the walking cadence value interval can be set to 1.0 steps/second to 2.5 steps/second.
  • the running speed of vehicles, ships, railways, etc. is greater than 30km/h.
  • the second speed threshold can be set to 30 km/h. For example, if it is detected that the user's moving speed is about 60 km/h, it can be judged that the user is in the boarding vehicle.
  • the interval between the moving speed and the step frequency value may also be divided in more detail to determine the motion state of the user in detail.
  • the user's motion mode can also be divided into more detailed, for example, can also be divided into a still mode, a walking mode, a fast walking mode, a running mode, a riding mode, and the like.
  • the user's pitch value is in the interval of 2.5 steps/second to 5 steps/second, it is determined that the user is in the running mode.
  • the motion modes in the embodiments of the present application can be divided into “sports” and “non-sports”, and the “sports” mode can be further subdivided, for example, subdivided into “running”, “swim”, “riding”, etc. Sports mode.
  • the specific motion mode of the user may be determined according to the user's selection or the output of the related sensor.
  • the user's motion pattern may be analyzed based only on the acquired user acceleration data without acquiring geographic location data.
  • the user's exercise mode can be determined based only on the user's stride value.
  • control module 21 can determine whether the user is in a speaking state according to the pickup condition of the voice signal by the bone conduction microphone 14 described above.
  • control module 21 can determine whether there is another person within a certain distance range in front of the user according to the signal output by the infrared proximity sensor 15, and if so, determine that the user is in a speaking state.
  • the judgment of the foregoing environment type and the sport mode may be further combined to comprehensively determine whether the user is in a speaking state, for example, the user is in open air dining.
  • the “use scenario” referred to in the embodiment of the present application refers to a composite scenario, where “usage scenario” includes at least an environment type of the user and a current motion mode of the user, and may further include a user.
  • the state of speaking For example, if the environment type of the user is “outdoor” and the exercise mode is “sports”, the “use scenario” of the user is “outdoor exercise”. For example, if the environment type of the user is “indoor” and the sport mode is “sports”, the “use scenario” of the user is “indoor sports”. For example, the environment type of the user is “indoor”, the sport mode is “stationary”, and the speaking state is “in speech mode”, and the “use scenario” of the user is “indoor still conversation”.
  • the user's usage scenario can be estimated based only on the acceleration data. For example, if the user's pitch value is in the interval of 2.5 steps/second to 5 steps/second, it is judged that the user is in the running mode and is in the road environment.
  • the audio signal volume adjustment module 22 and the active noise reduction module are controlled according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectrum distribution of the ambient sound. 23.
  • the sound level intensity of the ambient sound signal here can be, for example, an equivalent continuous A sound level.
  • the usage scenario includes the environment type in which the user is currently located and the current motion mode of the user.
  • a function Action(t) can be defined to describe the usage scenario in which the user may be at a certain moment, and the sound of the ambient sound signal. Level strength, and the energy and spectral distribution of the ambient sound:
  • P(t) represents the type of environment the user is in at the current time
  • M(t) represents the motion mode of the user at the current time
  • L(t) represents the sound level of the ambient sound signal or the sound level of the ambient sound.
  • the interval to which the intensity belongs, F(t) represents the energy spectrum distribution of the ambient sound signal.
  • the function F(t) is defined to describe the energy and spectral distribution of the 20-20 kHz ambient sound at the user's location.
  • F(t) further includes F 0 (t) and Q(t), where F 0 (t) is used to indicate the frequency point corresponding to the maximum noise peak at the current time, and Q(t) is used to represent the ambient sound of the current time. Quality factor.
  • the corresponding noise environment is relatively stable steady-state noise, such as the restaurant environment during a certain meal period, mostly Background noise of conversation or tableware flick, and F 0 is between 200Hz and 300Hz.
  • V(t) represents the interval to which the user's moving speed or moving speed belongs at the current time
  • f(t) represents the current frequency value of the user or the interval to which the step frequency value belongs.
  • the usage scenario includes the user's speaking state, so the function Action(t) is:
  • S(t) is used to indicate whether the user is currently in the speaking mode.
  • the control module 21 determines the user according to the threshold value according to the real-time value of each sensor module (not limited to the ambient sound collection microphone 13, the acceleration sensor 11, the positioning module 12, the bone conduction microphone 14 / the infrared proximity sensor 15, etc.). Using the scene and ambient sound levels, the energy spectrum distribution of the ambient sound is obtained, that is, P(t), M(t), L(t), F(t), and S(t) are obtained.
  • the control module 21 performs real-time query on the Action(t) function, automatically generates a control instruction according to each variable of the Action(t), and sends the corresponding instruction to the audio signal volume adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment.
  • the module 24 enables each module to make a response that matches the current scene and ambient sound signals, that is, to automatically adjust the playback effect to suit the current playback environment.
  • Action(t) (P(t), V(t), f(t), L(t), F(t), S(t)) - function 4.
  • the interval to which the sound level intensity of the ambient sound signal belongs may include the following intervals:
  • 0dBA to 40dBA is the first sound level intensity interval, indicating a very quiet environment.
  • (4) 80dBA ⁇ 120dBA is the fourth sound intensity interval, indicating an unbearable noise environment.
  • the interval to which the sound level intensity of the ambient sound signal belongs can also be subdivided according to the actual application, and is not completely limited to this definition.
  • (1) 0 to 0.2 m/sec is the first moving speed interval, indicating that it is stationary.
  • the interval of the user's moving speed can be divided into more detailed, and the auxiliary step frequency value and the environment type in which the user is located help the control module 21 to accurately determine the user's usage scenario.
  • the interval of the user's pitch value may include the following intervals:
  • the interval to which the stride value belongs can also be subdivided according to the actual application, and is not completely limited to this definition.
  • the user's sports mode (including the used vehicle) can be based on the user's location.
  • the specific environment type, the interval of the user's moving speed, and the interval of the step frequency value are comprehensively determined. If the energy and spectrum distribution of the ambient sound are further combined, it can be determined more accurately.
  • the above function also illustrates that the embodiment of the present application can comprehensively analyze the geographic location data, the moving speed, the stride value, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound, thereby realizing the use according to the use.
  • the scene automatically adjusts the playback effect.
  • the first usage scenario is that the user is in a road environment and is in a walking mode. It is easy to understand that in this usage scenario, the user's motion pattern can be estimated only by the acquired acceleration data, and then the user's usage scenario can be estimated. For example, if the acceleration data indicates that the current user's pitch frequency value is within the interval of 0.5 steps/second to 2.5 steps/second, it is determined that the user is in the walking mode in the road environment.
  • the ambient sound is mostly ambient noise such as road traffic noise and wind noise of different intensities.
  • the F 0 of the ambient sound signal is often around 100 Hz, and the Q value is relatively small, that is, the relative distribution of the low frequency band noise. More general.
  • the sound level intensity will vary depending on the traffic conditions at different times.
  • control module 21 controls the audio signal volume adjustment module 22 and the active noise reduction module 23 according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectrum distribution of the ambient sound.
  • the work of the ambient sound adjustment module 24 includes:
  • the control wind noise suppression sub-module 241 performs suppression filtering on the wind noise signal in the ambient sound signal.
  • the voice signal is monitored for whether the voice signal is included in the ambient sound signal. If the voice signal is included, the voice enhancement sub-module 242 is triggered to enhance the voice signal in the ambient sound signal. That is to say, in the first usage scenario, the voice enhancement sub-module 242 is in a standby state, and can be awakened by the voice signal detected by the control module 21 in real time.
  • the control dynamic range control sub-module 243 performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal.
  • the sound level intensity of the ambient sound signal is ⁇ 40 dBA
  • the user can ensure that he can enjoy music and maintain certain monitoring and sensing ability to the external environment.
  • the division of the sound level intensity of the ambient sound signal ( ⁇ 40dBA, 40dBA ⁇ 50dBA, 50dBA ⁇ 60dBA, >60dBA) is only an example; the division of the interval can be adjusted according to the actual situation.
  • the control EQ equalization processing sub-module 244 performs EQ compensation processing on the ambient sound signal, and outputs it to the speaker 30 for playback. For example, EQ compensation processing is performed on the voice signal band and the whistle signal band in the ambient sound signal.
  • the active noise reduction module 23 Determining whether to activate the active noise reduction module 23 according to the sound level intensity of the ambient sound signal, and if the active noise reduction module 23 is turned on, automatically adjusting the noise reduction level of the active noise reduction module 23 according to the sound level intensity of the ambient sound signal.
  • the effect of feedback noise reduction can be increased to appropriately reduce the effect of feedforward noise reduction in the low frequency band.
  • the noise reduction signal generated by the active noise reduction module 23 is output to the horn 30.
  • the control module 21 can analyze whether there is a certain alert sound in the ambient sound signal according to the energy and spectral distribution of the ambient sound. For example, ambient sound pickup microphone (13) at the time t 1 to t pick up ambient noise, frequency domain analysis, or intermittently over the time period between consecutive frequency 500Hz-1500Hz, much greater than a quality factor Q The pulse signal, and the energy average is 10 dB higher than the previous period, it is judged that there is some kind of warning tone in the ambient sound signal that requires the user's attention. If there is some kind of warning sound in the ambient sound signal, the control module 21 controls the active noise reduction module 23 to actively denoise the portion of the ambient sound signal other than the alarm sound, and controls the dynamic range control sub-module 243. The alarm sound of the ambient sound signal is amplified to ensure the safety and alertness of the user.
  • ambient sound pickup microphone (13) at the time t 1 to t pick up ambient noise, frequency domain analysis, or intermittently over the time period between consecutive frequency 500Hz-1500Hz, much greater than
  • the operating parameters of the audio signal volume adjustment module 22 are controlled based on the sound level intensity of the ambient sound signal arriving at the horn 30 such that the audio level at the horn 30 and the ambient sound signal at the horn 30 are maintained at a predetermined ratio. .
  • the volume of the audio signal can be automatically controlled to become larger, that is, when the outside is relatively noisy, the volume of the audio signal is increased.
  • the volume of the audio signal can be automatically controlled to be small, that is, when the external environment is relatively quiet, the volume of the audio signal is lowered to protect the user's hearing.
  • the second usage scenario is that the user is in the road environment and is in the boarding mode, and the control module 21 controls the volume of the audio signal according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound.
  • the operations of the adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24 include:
  • the voice enhancement sub-module 242 and the EQ equalization processing sub-module 244 are in a standby state, and can be awakened by the voice signal detected by the control module 21 in real time.
  • the active noise reduction module 23 controls the active noise reduction of the ambient sound signal according to the strongest noise reduction level. Alternatively, the control active noise reduction module 23 determines whether to activate the active noise reduction module 23 according to the sound level intensity of the ambient sound signal, and if the active noise reduction module 23 is turned on, adjusts the active noise reduction module 23 according to the sound level intensity of the ambient sound signal. The level of noise reduction.
  • the operating parameters of the audio signal volume adjustment module 22 are controlled based on the sound level intensity of the ambient sound signal arriving at the horn 30 such that the audio level at the horn 30 and the ambient sound signal at the horn 30 are maintained at a predetermined ratio. .
  • the volume of the audio signal can be automatically controlled to become larger, that is, when the outside is relatively noisy, the volume of the audio signal is increased.
  • the volume of the audio signal can be automatically controlled to be small, that is, when the external environment is relatively quiet, the volume of the audio signal is lowered to protect the user's hearing.
  • control wind noise suppression sub-module (241) is turned off when the user is in a road environment and is in a boarding mode.
  • the trigger dynamic range control sub-module (243) attenuates the ambient sound signal, and if the sound level intensity of the ambient sound signal is less than the preset sound level intensity lower limit, the triggering dynamic The range control sub-module (243) amplifies the ambient sound signal.
  • the upper limit of the sound level intensity is, for example, 60 dBA
  • the lower limit of the sound level intensity is, for example, 40 dBA.
  • the user when it is determined that the user is in the boarding mode, it may be further determined which vehicle the user is traveling on. For example, depending on the type of environment, the altitude data in the geographic location data, the moving speed, and the stride value, it can be determined that the user is in a mode of riding a bicycle, riding an airplane, riding a railway, or riding a car. For example, if the user's moving speed reaches 250 km/h and the user is on the railroad trunk, it can be determined that the user is in the high-speed rail mode.
  • the control module 21 can set the active noise reduction module 23 and the ambient sound adjustment module 24 according to the characteristics of the ambient sound corresponding to the subdivided vehicle, such as the horn horn sound when the vehicle is riding, and the relatively high speed of the high-speed rail compartment.
  • the specific regulation mode for example, the active noise reduction module 23 is set to a lower level when the user rides the high-speed rail.
  • the vehicle when it is determined that the user is in the boarding mode, the vehicle may be determined based on the sound level intensity of the ambient sound signal and the energy and spectral distribution characteristics of the ambient sound.
  • the control module 21 can set the specific control mode of the active noise reduction module 23 and the ambient sound adjustment module 24 according to the characteristics of the environmental sound corresponding to the subdivided vehicle.
  • the user may talk to the companion, or there may be external voice reminders, such as a dangerous voice reminder or a vehicle arrival reminder in the second usage scenario, therefore, in the two usage scenarios
  • the voice enhancement sub-module 242 can be triggered by the voice signal in the ambient sound signal detected in real time.
  • the third usage scenario is that the user is in an indoor environment (for example, an indoor area such as a residential education medical research administrative office or a catering trade business) and is in a static mode and a speech mode, and then the control module 21 is configured according to the usage scenario and the ambient sound signal.
  • the sound level intensity, and the energy and spectral distribution of the ambient sound control the operation of the audio signal volume adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24, including:
  • the control speech enhancement sub-module 242 performs enhancement processing on the speech signal in the ambient sound signal.
  • the control EQ equalization processing sub-module 244 performs an EQ compensation process on the voice signal band in the ambient sound signal, and outputs it to the speaker 30 for playback.
  • control wind noise suppression sub-module 241 and the dynamic range control sub-module 243 are turned off.
  • the active noise reduction module 23 is controlled to turn off or perform active noise reduction processing on the ambient sound signal.
  • the audio signal volume adjustment module 22 is controlled to turn down the volume or pause the audio signal.
  • the adaptive audio control device of the embodiment of the present application may have a plurality of ambient sound collection microphones 13, including a microphone disposed on the earphone casing for collecting ambient sounds of the user, and a microphone disposed inside the earphone for collecting the user's ears.
  • the multi-microphone setting method can more accurately collect the ambient sound and can reflect the situation of the ambient sound heard by the user's auricle. It can be used for the active noise reduction function, which is beneficial to the positioning of the ambient sound source and the adjustment of the voice and ambient sound. Proportion, better optimization of noise reduction, is more conducive to smarter adaptive audio control.
  • control module 21 can also analyze the ambient sound signal collected by the ambient sound collection microphone 13 to obtain the sound level intensity, energy, and spectrum distribution of the ambient sound signal, and combine the data acquired by the acceleration sensor, the positioning module, and other sensors.
  • a richer scene analysis is implemented to facilitate finer control of the volume adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24, thereby providing the user with a better experience.
  • the foregoing scene recognition-based adaptive audio control device can be implemented by hardware, software or a combination of software and hardware. Based on the same inventive concept, referring to FIG. 4, a method for adaptive audio control based on scene recognition provided by an embodiment of the present application is provided, which includes the following steps:
  • acceleration data of the user may be acquired, and the usage scenario of the user is analyzed according to the acceleration data. It is easy to understand, and can also obtain the user's geographic location data, and analyze the user's usage scenario based on the acceleration data and the geographic location data.
  • the audio playback device is an earphone.
  • the ambient sound adjustment module 24 includes any one or combination of the following sub-modules: a wind noise suppression sub-module 241, a speech enhancement sub-module 242, a dynamic range control sub-module 243, and an EQ equalization processing sub-module 244.
  • step 401 analyzing a usage scenario of the user, including: determining, according to the geographic location data, an environment type of the user; calculating a moving speed of the user according to the geographic location data; Calculating the user's pitch frequency value; determining the user's motion mode based on the moving speed and the step frequency value.
  • the type of environment includes an indoor environment and a road environment;
  • the sport mode includes any of the following: a still mode, a road walking mode, and a boarding mode.
  • the user if the moving speed is less than the first speed threshold and the step frequency value is less than the first frequency threshold, the user is in a stationary mode; if the moving speed is within the walking speed interval and If the step frequency value is within the walking step frequency value interval, the user is in the walking mode; if the moving speed is greater than the second speed threshold, the user is in the boarding mode.
  • the audio playback device further includes a bone conduction microphone or an infrared proximity sensor
  • the user's use scene further includes a speaking state of the user
  • the method includes the following steps: according to the bone conduction microphone or infrared proximity
  • the signal output by the sensor determines if the user is in talk mode.
  • the collecting an ambient sound signal of the environment in which the user is located includes collecting a real-time ambient sound signal of the user and collecting an ambient sound signal heard near the user's pinna.
  • the audio signal volume adjustment module is controlled according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound. 22.
  • the work of the active noise reduction module 23 and the ambient sound adjustment module 24 includes:
  • the control wind noise suppression sub-module 241 performs suppression filtering on the wind noise signal in the ambient sound signal
  • the voice enhancement sub-module 242 Monitoring whether the ambient sound signal contains a voice signal, and if the voice signal is included, triggering the voice enhancement sub-module 242 to perform enhancement processing on the voice signal in the ambient sound signal;
  • the control dynamic range control sub-module 243 performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal;
  • the control EQ equalization processing sub-module 244 performs EQ compensation processing on the ambient sound signal
  • control dynamic range control sub-module 243 performs dynamic range adjustment on the ambient sound signal according to the sound level intensity of the ambient sound signal, including: when 40dBA ⁇ the sound level intensity of the ambient sound signal is ⁇ At 50dBA, the ambient sound signal is amplified; when the sound level of the ambient sound signal is >60dBA, the ambient sound signal is attenuated.
  • the performing an EQ compensation process on the ambient sound signal includes performing an EQ compensation process on the voice signal band and the whistle signal band in the ambient sound signal.
  • the audio signal volume is controlled according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound.
  • the operations of the adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24 include:
  • control wind noise suppression sub-module 241 is turned off when the user is in the road environment and is in the boarding vehicle mode.
  • the trigger dynamic range control sub-module (243) when the user is in the road environment and is in the boarding mode, whether the sound level intensity of the ambient sound signal is greater than a preset upper limit of the sound level or less than a preset lower limit of the sound level, if the environment The sound level intensity of the sound signal is greater than the preset sound level intensity upper limit, and the trigger dynamic range control sub-module (243) attenuates the ambient sound signal. If the sound level intensity of the ambient sound signal is less than the preset sound level intensity lower limit, Then, the trigger dynamic range control sub-module (243) amplifies the ambient sound signal.
  • the audio signal is controlled according to the usage scenario, the sound level intensity of the ambient sound signal, and the energy and spectral distribution of the ambient sound.
  • the operations of the volume adjustment module 22, the active noise reduction module 23, and the ambient sound adjustment module 24 include:
  • the control speech enhancement sub-module 242 performs enhancement processing on the speech signal in the ambient sound signal
  • the control EQ equalization processing sub-module 244 performs an EQ compensation process on the voice signal band in the ambient sound signal
  • the audio signal volume adjustment module 22 is controlled to turn down the volume or pause the audio signal.
  • control wind noise suppression sub-module 241 and the dynamic range control sub-module 243 are closed.
  • each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the Executable instructions.
  • the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented with a dedicated hardware-based device that performs the specified function or action. Or it can be implemented by a combination of dedicated hardware and computer instructions.
  • the computer program product provided by the embodiment of the present application includes a computer readable storage medium storing the program code, and the program code includes instructions for executing the method described in the foregoing method embodiment.
  • the program code includes instructions for executing the method described in the foregoing method embodiment.
  • refer to the method embodiment. will not repeat them here.
  • the disclosed apparatus, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or It can be integrated into another device, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, and may be electrical, mechanical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product.
  • the technical solution of the present application which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
  • the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Abstract

本申请公开了一种基于场景识别的自适应音频控制方法和系统。该方法包括：获取用户的加速度数据，根据加速度数据分析用户的使用场景；获取用户所处环境的环境声音信号，计算环境声音信号的声级强度，并分析环境声音信号的能量和频谱分布；根据使用场景、环境声音信号的声级强度、以及环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节。该方法还能够获取用户的地理位置数据，并与加速度数据一起用于分析用户的使用场景。基于以上方案，能够实现更为灵活和方便的音频播放控制。

Description

一种基于场景识别的自适应音频控制装置和方法 技术领域
本申请涉及电声转换技术，更具体的，涉及一种基于场景识别的自适应音频控制装置和方法。
背景技术
现有技术中，用户有时会在噪声环境下使用音频播放设备，为解决噪声问题，出现了具有被动/主动降噪功能的音频播放设备，例如降噪耳机，目的是消除噪声对用户的影响。发明人发现，只消除噪声已经不能够满足用户对播放效果的需求，用户希望音频播放设备更加智能，能够自动调节播放效果以适应当前的播放环境。
在声学领域中，为能够很好的反映人耳对外界噪声响度的主观听觉感受，通常会使用等效连续A声级对环境噪声进行评价，当环境噪声低于50dBA时，人们觉得环境相对安静，当噪声大于80dBA，人们会就觉得周围环境比较吵闹，当噪声达到120dBA，则人们会觉得难以忍受，长期处在90dBA以上的噪声环境中，听力受损伤的可能性明显增大。
因此，有必要提供一种能够自适应的音频播放控制方案。
发明内容
本申请的目的在于提供一种基于场景识别的自适应音频控制方案，以根据用户的使用场景自动调节播放效果。
根据本申请的第一方面，提供了一种基于场景识别的自适应音频控制装置，包括环境声音采集麦克风、加速度传感器、定位模块、控制模块、音频信号音量调节模块、主动降噪模块、以及环境声音调节模块；其中，所述音频信号音量调节模块、主动降噪模块、以及环境声音调节模块的输出端分别与喇叭连接；
所述控制模块包括存储器和处理器，其中所述存储器存储有计算机程序，所述计算机程序被所述处理器执行时实现以下步骤：
根据所述加速度传感器输出的加速度数据和所述定位模块输出的地理位置数据分析用户的使用场景；
计算所述环境声音采集麦克风采集的环境声音信号的声级强度，并分析所述环境声音信号的能量和频谱分布；
根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作。
在一种实施方式中，所述环境声音调节模块包括下列子模块的任一或组合：风噪抑制子模块、语音增强子模块、动态范围控制子模块、EQ均衡处理子模块。
在一种实施方式中，所述根据所述加速度传感器输出的加速度数据和所述定位模块输出的地理位置数据分析用户的使用场景，包括：
根据所述地理位置数据确定用户所处的环境类型；
根据所述地理位置数据计算用户的移动速度；
根据所述加速度数据计算用户的步频值；
根据所述移动速度和步频值确定用户的运动模式。
在一种实施方式中，所述环境类型包括室内环境和道路环境；所述运动模式包括下列任一：静止模式、道路行走模式和搭乘交通工具模式。
在一种实施方式中，如果所述移动速度小于第一速度阈值并且所述步频值小于第一步频值阈值，则用户处于静止模式；
如果所述移动速度在行走速度区间内并且所述步频值在行走步频值区间内，则用户处于行走模式；
如果所述移动速度大于第二速度阈值，则用户处于搭乘交通工具模式。
在一种实施方式中，所述装置还包括骨传导麦克风或红外接近传感器，用户的使用场景还包括用户的说话状态；
所述计算机程序被所述处理器执行时实现以下步骤：
根据所述骨传导麦克风或红外接近传感器输出的信号确定用户是否处于讲话模式。
在一种实施方式中，所述环境声音采集麦克风为多个，包括用于采集用户实时位置外界环境声音的麦克风和用于采集用户耳廓附近所听到的环境声音的麦克风。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于行走模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
控制风噪抑制子模块对环境声音信号中的风噪信号进行抑制性滤波；
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块对环境声音信号中的语音信号进行增强处理；
控制动态范围控制子模块根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整；
控制EQ均衡处理子模块对环境声音信号进行EQ补偿处理；根据到达喇叭处的环境声音信号的声级强度控制所述音频信号音量调节模块的工作参数，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于行走模式，则所述控制动态范围控制子模块根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整，包括：
当40dBA＜所述环境声音信号的声级强度≤50dBA时，对环境声音信号进行放大处理；
当所述环境声音信号的声级强度＞60dBA时，对环境声音信号进行衰减处理。
在一种实施方式中，所述对环境声音信号进行EQ补偿处理，包括对环境声音信号中的语音信号频带和鸣笛信号频段进行EQ补偿处理。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于行走模式，则根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，还包括：
根据所述环境声音信号的声级强度确定是否开启所述主动降噪模块，以及如果开启所述主动降噪模块，根据所述环境声音信号的声级强度调整所述主动降噪模块的降噪等级。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块对环境声音信号中的语音信号进行增强处理以及触发EQ均衡处理子模块对环境声音信号中的语音信号频带进行EQ补偿处理；
控制主动降噪模块按照最强降噪等级进行主动降噪处理；或者，根据所述环境声音信号的声级强度确定是否开启所述主动降噪模块，以及如果开启所述主动降噪模块，根据所述环境声音信号的声级强度调整所述主动降噪模块的降噪等级；
根据到达喇叭处的环境声音信号的声级强度控制所述音频信号音量调节模块的工作参数，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
控制风噪抑制子模块关闭；和/或，
监测环境声音信号的声级强度是否大于预设的声级强度上限或者小于预设的声级强度下限，如果环境声音信号的声级强度大于预设的声级强度上限，则触发动态范围控制子模块对环境声音信号进行衰减处理，如果环境声音信号的声级强度小于预设的声级强度下限，则触发动态范围控制子模块对环境声音信号进行放大处理。
在一种实施方式中，如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则所述根据所述使用场景、所述环境声音信号的 声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
控制语音增强子模块对环境声音信号中的语音信号进行增强处理；
控制EQ均衡处理子模块对环境声音信号中的语音信号频带进行EQ补偿处理；
控制主动降噪模块关闭或者对环境声音信号进行主动降噪处理；
控制音频信号音量调节模块调低音量或者暂停播放音频信号。
在一种实施方式中，如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，还包括：
控制风噪抑制子模块和动态范围控制子模块关闭。
在一种实施方式中，所述装置为耳机。
根据本申请的第二方面，提供了一种基于场景识别的自适应音频控制方法，包括以下步骤：
采集用户的加速度数据和地理位置数据，根据所述加速度数据和地理位置数据分析用户的使用场景；
采集用户所处环境的环境声音信号，计算所述环境声音信号的声级强度，并分析所述环境声音信号的能量和频谱分布；
根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频播放装置的音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作。
在一种实施方式中，所述环境声音调节模块包括下列子模块的任一或组合：风噪抑制子模块、语音增强子模块、动态范围控制子模块、EQ均衡处理子模块。
在一种实施方式中，所述根据所述加速度数据和地理位置数据分析用户的使用场景，包括：
根据所述地理位置数据确定用户所处的环境类型；
根据所述地理位置数据计算用户的移动速度；
根据所述加速度数据计算用户的步频值；
根据所述移动速度和步频值确定用户的运动模式。
在一种实施方式中，所述环境类型包括室内环境和道路环境；所述运动模式包括下列任一：静止模式、道路行走模式和搭乘交通工具模式。
在一种实施方式中，如果所述移动速度小于第一速度阈值并且所述步频值小于第一步频值阈值，则用户处于静止模式；
如果所述移动速度在行走速度区间内并且所述步频值在行走步频值区间内，则用户处于行走模式；
如果所述移动速度大于第二速度阈值，则用户处于搭乘交通工具模式。
在一种实施方式中，所述音频播放装置还包括骨传导麦克风或红外接近传感器，用户的使用场景还包括用户的说话状态，所述方法还包括以下步骤：
根据所述骨传导麦克风或红外接近传感器输出的信号确定用户是否处于讲话模式。
在一种实施方式中，所述采集用户所处环境的环境声音信号包括采集用户实时位置外界环境声音信号和采集用户耳廓附近所听到的环境声音信号。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于行走模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
控制风噪抑制子模块对环境声音信号中的风噪信号进行抑制性滤波；
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块对环境声音信号中的语音信号进行增强处理；
控制动态范围控制子模块根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整；
控制EQ均衡处理子模块对环境声音信号进行EQ补偿处理；根据到达音频播放装置的喇叭处的环境声音信号的声级强度控制所述音频 信号音量调节模块的工作参数，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于行走模式，则所述控制动态范围控制子模块根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整，包括：
当40dBA＜所述环境声音信号的声级强度≤50dBA时，对环境声音信号进行放大处理；
当所述环境声音信号的声级强度＞60dBA时，对环境声音信号进行衰减处理。
在一种实施方式中，所述对环境声音信号进行EQ补偿处理，包括对环境声音信号中的语音信号频带和鸣笛信号频段进行EQ补偿处理。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于行走模式，则根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，还包括：
根据所述环境声音信号的声级强度确定是否开启所述主动降噪模块，以及如果开启所述主动降噪模块，根据所述环境声音信号的声级强度调整所述主动降噪模块的降噪等级。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块对环境声音信号中的语音信号进行增强处理以及触发EQ均衡处理子模块对环境声音信号中的语音信号频带进行EQ补偿处理；
控制主动降噪模块按照最强降噪等级进行主动降噪处理；或者，根据所述环境声音信号的声级强度确定是否开启所述主动降噪模块，以及如果开启所述主动降噪模块，根据所述环境声音信号的声级强度调整所述主动降噪模块的降噪等级；
根据到达音频播放装置的喇叭处的环境声音信号的声级强度控制所述音频信号音量调节模块的工作参数，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例。
在一种实施方式中，如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
控制风噪抑制子模块关闭；和/或，
监测环境声音信号的声级强度是否大于预设的声级强度上限或者小于预设的声级强度下限，如果环境声音信号的声级强度大于预设的声级强度上限，则触发动态范围控制子模块对环境声音信号进行衰减处理，如果环境声音信号的声级强度小于预设的声级强度下限，则触发动态范围控制子模块对环境声音信号进行放大处理。
在一种实施方式中，如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，包括：
控制语音增强子模块对环境声音信号中的语音信号进行增强处理；
控制EQ均衡处理子模块对环境声音信号中的语音信号频带进行EQ补偿处理；
控制主动降噪模块关闭或者对环境声音信号进行主动降噪处理；
控制音频信号音量调节模块调低音量或者暂停播放音频信号。
在一种实施方式中，如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块、主动降噪模块、环境声音调节模块的工作，还包括：
控制风噪抑制子模块和动态范围控制子模块关闭。
在一种实施方式中，所述音频播放装置为耳机。
根据本申请的第三方面，提出了一种控制音频播放装置的方法，包 括以下步骤：获取用户的加速度数据，根据加速度数据分析用户的使用场景；获取用户所处环境的环境声音信号，计算环境声音信号的声级强度，并分析环境声音信号的能量和频谱分布；根据使用场景、环境声音信号的声级强度、以及环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节。
在一种实施方式中，还包括以下步骤：获取用户的地理位置数据；其中根据所述加速度数据和所述地理位置数据来分析用户的使用场景。
根据本申请的第四方面，提出了一种控制音频播放装置的系统，包括：一个或者多个处理器；耦合至一个或者多个处理器中的至少一个处理器的存储器；存储器中存储有计算机程序指令，当由至少一个处理器执行计算机程序指令时，使得系统执行控制音频播放装置的方法，所述方法包括：获取用户的加速度数据，根据加速度数据分析用户的使用场景；获取用户所处环境的环境声音信号，计算环境声音信号的声级强度，并分析环境声音信号的能量和频谱分布；根据使用场景、环境声音信号的声级强度、以及环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节。
根据本申请的第五方面，提出了一种计算机程序产品，当计算机程序产品由处理器执行时，能够实现如本申请的第三方面所述的控制音频播放装置的方法。
本申请提供的以上基于场景识别的自适应音频控制装置和方法，能够分析用户的使用场景，根据使用场景自动调节播放效果。
为使本申请的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍。应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对范围的限定。对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的 附图。
图1示出了本申请实施例提供的基于场景识别的自适应音频控制装置的框图。
图2示出了本申请又一实施例提供的基于场景识别的自适应音频控制装置的框图。
图3示出了本申请再一实施例提供的基于场景识别的自适应音频控制装置的框图。
图4示出了本申请实施例提供的基于场景识别的自适应音频控制方法的流程图。
具体实施方式
现在将参照附图来详细描述本申请的各种示例性实施例。应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本申请的范围。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本申请及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为说明书的一部分。
在这里示出和讨论的所有例子中，任何具体值应被解释为仅仅是示例性的，而不是作为限制。因此，示例性实施例的其它例子可以具有不同的值。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
本申请提出了一种基于场景识别的自适应音频控制装置。该装置可以是耳机、音箱、或其它能够播放音频信号的电子设备。该装置可以和手机、电脑等终端设备进行有线通信或无线通信，以播放终端设备的音频信号。该装置中也可以存储有音频信号，例如音乐，该装置可以播放自身存 储的音频信号。该装置也可以设置终端设备的内部，作为终端设备的一部分。
参见图1所示，本申请第一实施例提供的基于场景识别的自适应音频控制装置，包括环境声音采集麦克风13、加速度传感器11、定位模块12、控制模块21、音频信号音量调节模块22、主动降噪模块23、以及环境声音调节模块24。
加速度传感器11，用于采集用户的加速度数据，输出加速度数据至控制模块21。
定位模块12，用于采集用户的地理位置数据，输出地理位置数据至控制模块21。
音频信号经音频信号音量调节模块22进行音量调节后输入至喇叭30进行播放。
环境声音采集麦克风13，用于拾取环境声音信号，将拾取到的环境声音信号分别馈给控制模块21、主动降噪模块23和环境声音调节模块24。主动降噪模块23和环境声音调节模块24的输出端分别与喇叭30连接。
控制模块21分别与音频信号音量调节模块22、主动降噪模块23和环境声音调节模块24连接，以控制三者的工作，例如，控制模块21开启/关闭某个模块或子模块，或调整某个模块或子模块的参数等。
主动降噪模块23，用于针对环境声音信号生成相应的降噪信号，并将降噪信号输出至喇叭30。降噪信号和环境声音信号在用户耳道内互相抵消，以降低外界环境声音对用户聆听音频信号的影响。主动降噪模块24可以有反馈降噪方式、前馈降噪方式、前馈结合反馈的降噪方式。在一个具体的例子中，主动降噪模块23只有在环境声音的声级强度达到60dBA时，才会被开启；主动降噪模块23可以设置有各种降噪等级，例如当环境声音的声级强度分别达到60dBA、70dBA、80dBA、90dBA时，各自对应一个降噪等级，环境声音的声级强度越强，则降噪等级越高。
环境声音调节模块24，用于对环境声音信号进行调节，将调节后的环境声音信号输出至喇叭30。其中，环境声音调节模块24包括下列子模 块：风噪抑制子模块241、语音增强子模块242、动态范围控制子模块243、EQ均衡处理子模块244。
风噪抑制子模块241主要用于滤除环境声音信号中的风噪。风噪主要集中在非常低的频率段，一旦检测到比较大的风噪可以设置不同的滤波器来应对，以降低风噪对用户聆听音频信号的影响。在一个具体的例子中，当用户处于室外环境时，可以根据风噪的能量和频谱分布情况，确定是否需要开启风噪抑制子模块241；当用户处于室内环境时，可以关闭风噪抑制子模块241。
语音增强子模块242主要用于对环境声音信号中的语音部分进行增强，抑制、降低噪声干扰，提升语音部分的信噪比，使得用户能够更清晰的听到外界的语音。在一个具体的例子中，当用户处于讲话状态时，语音增强子模块241会被开启。在一个具体的例子中，当用户处于有必要听到外界提示语音的状态，语音增强子模块241会被开启。语音增强子模块242可以对环境声音信号中的语音信号进行增强处理并且对环境噪声进行抑制处理，从而实现语音增强功能。
动态范围控制子模块243主要用于对环境声音信号进行动态范围调整，例如可以对一些脉冲声进行压缩后再馈给耳机，避免在耳机端造成很大的破音。在一个具体的例子中，动态范围控制子模块243在各种情况下均处于开启的状态，以避免猝发声音对用户的惊吓损伤。在另一个具体的例子中，当用户处于室外环境时，动态范围控制子模块243必须开启，当用户处于室内环境中时，由于室内环境中猝发声音相对比较少，动态范围控制子模块243可以关闭。
EQ均衡处理子模块244主要用于对环境声音进行针对不同频带的增强和衰减，以优化环境声音的听感。在一个具体的例子中，如果需要听到部分环境声音，则EQ均衡处理子模块244会被开启以对部分频段的环境声音进行补偿增强。
参见图2所示，为本申请又一实施例提供的基于场景识别的自适应音频控制装置。图2实施例具有图1实施例提供的全部结构和功能，主要 区别在于，图2实施例的装置还包括骨传导麦克风14，骨传导麦克风14的输出端与控制模块21连接。
参见图3所示，为本申请再一实施例提供的基于场景识别的自适应音频控制装置。图3实施例具有图1实施例提供的全部结构和功能，主要区别在于，图3实施例的装置还包括朝向用户前方的红外接近传感器15，红外接近传感器15的输出端与控制模块21连接。
图1-3的实施例中，环境声音调节模块24包括下列子模块：风噪抑制子模块241、语音增强子模块242、动态范围控制子模块243、EQ均衡处理子模块244。在其它实施例中，环境声音调节模块24也可以包括上述子模块的任意或组合，或者含有其它子模块。
在一个实施例中，该装置还可能设有由隔声材料构成的被动降噪结构，被动降噪为物理降噪，通过外壳及耳套等对外界噪声传入到耳道内的噪声进行隔离，这种被动的降噪方法对中高频1kHz以上的噪声有比较好的作用。
在一个实施例中，该装置可能还设有手动音量调节装置、手动降噪模式切换装置、手动环境声音调节装置等结构，以提供给用户更多选择方式。
图1-3中的实施例中，环境声音采集麦克风13可以为一个或多个。例如左右耳机分别设置有环境声音采集麦克风。例如只有左耳耳机设置有环境声音采集麦克风。例如只有右耳耳机设置有环境声音采集麦克风。例如设置在耳机外壳的用于采集用户所处的外界环境声音的麦克风。例如设置在耳机内部的、用于采集用户耳廓处所听到环境声音的麦克风。在一个实施例中，环境声音采集麦克风13为多个，包括用于采集用户实时位置外界环境声音的麦克风和用于采集用户耳廓附近所听到的环境声音的麦克风。
在本申请实施例提供的基于场景识别的自适应音频控制装置中，控制模块21包括存储器和处理器，其中所述存储器存储有计算机程序，所 述计算机程序被所述处理器执行时实现以下步骤：
101、分析用户的使用场景。
根据本公开的一些实施例，可以根据加速度传感器输出的加速度数据来分析用户的使用场景。
根据本公开的另一些实施例，在该步骤还可以获取由定位模块12采集的地理位置数据，并利用加速度数据和用户的地理位置数据来共同分析用户的使用场景。
102、计算环境声音采集麦克风13采集的环境声音信号的声级强度，并分析环境声音信号的能量和频谱分布。通过分析环境声音信号的能量和频谱分布可以获得环境声音的组成成分，例如环境声音中是否含有语音成分、警笛等警示音成分、风噪成分等，以及这些成分的能量。
103、根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作。
其中，控制模块21可以根据使用场景自动调整主动降噪模块24的降噪参数以达到不同的降噪等级或效果；或者主动降噪模块23预先设定有多种降噪模式，每种降噪模式对应于不同的降噪参数，控制模块21根据使用场景自动调整主动降噪模块23的降噪模式以达到不同的降噪等级或效果。
控制模块21根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，也就是说，控制模块21综合考虑环境声音信号的声级强度，环境声音的组成成分和各成分的能量，控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，使得音频控制与用户的使用场景相适配，实现根据用户的使用场景、环境声音信号的声级强度、以及环境声音的能量和频谱分布自适应地进行音频控制。
根据本公开的一些实施例，在步骤101中分析用户的使用场景，包括：
1011、根据所述地理位置数据确定用户所处的环境类型。所述环境类型包括室内环境和道路环境。
1012、根据所述地理位置数据计算用户的移动速度，根据所述加速度数据计算用户的步频值。根据所述移动速度和步频值确定用户的运动模式。所述运动模式可以包括下列任一：静止模式、道路行走模式和搭乘交通工具模式。在另一个实施例中，所述运动模式可以包括健身模式，健身模式涵盖跑步、骑行等健身方式。
根据本公开的另一些实施例，可以不获取地理位置数据而仅根据所获取的用户加速度数据来分析用户的使用场景。例如，可以仅根据用户的步频值来确定用户的运动模式。
根据本公开的另一些实施例，可以仅利用地理位置数据计算用户的移动速度，而不利用地理位置数据来获取环境类型。
在上述图2的实施例和图3的实施例中，用户的使用场景还可以包括用户的说话状态，具体来说，控制模块21根据骨传导麦克风14或红外接近传感器15输出的信号确定用户是否处于讲话模式。
<关于使用场景>
本申请实施例中所指的使用场景至少包括用户当前的运动模式，进一步地，还可以包括用户当前所处的环境类型和/或用户的说话状态，即用户是否处于讲话模式。
<环境类型>
1011、控制模块21可以根据所述地理位置数据确定用户所处的环境类型。所述环境类型包括室内环境和道路环境。
定位模块12例如可以包括GPS模块或北斗模块，当用户开启并使用该装置的场景自适应调节播放功能时，定位模块会首先获取用户所处的具体实时位置信息，然后根据具体实时位置信息实时确定用户所处的环境类型。
在其它实施例中，环境类型还可以划分的更为细致，以达到更灵活智能的音频控制效果。例如将室外环境类型划分成道路环境类型和非道路 的室外环境类型，非道路的室外环境类型又可以划分为露天贸易餐饮集市区类型、户外公园绿地类型等等。
在一个具体的例子中，环境类型可以划分为以下类型：
环境类型P 1：市主、次干路交通干线，城际、城市高速公路交通干线，内河航道及两侧区域；
环境类型P 2：铁路交通干线；
环境类型P 3：工业生产，仓储物流区；
环境类型P 4：工商集市餐饮贸易混杂区；
环境类型P 5：住宅教育医疗科研行政办公区；
环境类型P 6：户外公园绿地；
环境类型P 7：康复疗养等区域。
本申请实施例中的环境类型可以划分为“室内”和“室外”，针对“室外”环境类型还可以做进一步细分，例如细分为“室外运动场”、“室外公园绿地”、“室外集市”等环境类型。在本申请实施例中，可以根据用户的选择确定用户当前所处的环境类型。在本申请实施例中，也可以根据上述地理位置数据，结合环境声音信号的能量和频谱分布确定用户的具体运动模式，例如，根据环境声音信号的能量和频谱分布判断出环境声音信号中含有很强的风噪信号，再结合地理位置数据，就可以准确判断出用户处于室外环境。
<运动模式>
1012、控制模块21可以根据所述地理位置数据计算用户的移动速度，根据所述加速度数据计算用户的步频值。根据所述移动速度和步频值确定用户的运动模式。
(a)、如果所述移动速度小于第一速度阈值并且所述步频值小于第一步频值阈值，则用户处于静止模式。
在一个实施例中，可以将第一步频值阈值设置为0.5步/秒，可以将第一速度阈值设置为0.2米/秒，也就是说，如果用户的移动速度小于0.2米/秒并且步频值小于为0.5步/秒，则该用户处于静止模式。
(b)、如果所述移动速度在行走速度区间内并且所述步频值在行走步 频值区间内，则用户处于行走模式。
人正常行走的速度区间为1米/秒-1.7米/秒，正常行走的步频值的区间为1.0步/秒-2.5步/秒。在一个实施例中，可以将行走步频值区间设置为1.0步/秒-2.5步/秒。
(c)、如果所述移动速度大于第二速度阈值，则用户处于搭乘交通工具模式。
通常汽车、轮船、铁路等交通工具的运行速度大于30km/h。在一个实施例中，可以将第二速度阈值设置为30km/h。例如，如果监测到用户的移动速度约为60km/h，则可以判断用户处于搭乘交通工具中。
在其它实施例中，还可以将移动速度和步频值的区间做更详细的划分，以详细判断用户的运动状态。
在其它实施例中，用户的运动模式还可以划分的更为细致，例如还可以划分为静止模式、散步模式、快速行走模式、跑步模式、骑行模式等等。
在一个实施例中，如果用户的步频值在2.5步/秒-5步/秒的区间内，则判断用户处于跑步模式。
本申请实施例中的运动模式可以划分为“运动”和“非运动”，针对“运功”模式还可以做进一步细分，例如细分为“跑步”、“游泳”、“骑行”等运动模式。在本申请实施例中，可以根据用户的选择或者相关传感器的输出来确定用户的具体运动模式。
容易理解，在一些实施例中，可以不获取地理位置数据而仅根据所获取的用户加速度数据来分析用户的运动模式。例如，可以仅根据用户的步频值来确定用户的运动模式。
<说话状态>
在一个实施例中，控制模块21可以根据前述骨传导麦克风14对语音信号的拾取情况来判断用户是否处于讲话状态。
在另一个实施例中，控制模块21可以根据前述红外接近传感器15输出的信号判断用户前方一定距离范围内是否有其他人，如果有人，则判定用户处于讲话状态。或者，如果有人，可以进一步结合前述环境类型和 运动模式的判断情况，综合判定用户是否处于讲话状态，例如，用户处于露天餐饮。
根据本公开的一个实施例，本申请实施例中所指的“使用场景”指的是复合场景，“使用场景”至少包括用户所处的环境类型和用户当前的运动模式，进一步还可以包括用户的说话状态。例如，用户所处的环境类型为“室外”，运动模式为“运动”，则用户的“使用场景”为“室外运动”。例如，用户所处的环境类型为“室内”，运动模式为“运动”，则用户的“使用场景”为“室内运动”。例如，用户所处的环境类型为“室内”，运动模式为“静止”，说话状态为“处于讲话模式”，则用户的“使用场景”为“室内静止交谈”。
根据本公开的另一个实施例，容易理解的是，可以仅根据加速度数据来估计用户的使用场景。例如，如果用户的步频值在2.5步/秒-5步/秒的区间内，则判断用户处于跑步模式，且处于道路环境。
<基于场景识别的自适应音频控制>
控制模块21确定用户的使用场景后，根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作。其中，这里的环境声音信号的声级强度例如可以使用等效连续A声级。
在一个实施例中，使用场景包括用户当前所处的环境类型和用户当前的运动模式，可通过定义一个函数Action(t)来描述某时刻用户可能所处的使用场景，以及环境声音信号的声级强度、以及所述环境声音的能量和频谱分布：
Action(t)＝(P(t),M(t),L(t),F(t))------函数1
其中，t为时间，P(t)表示当前时刻用户所处的环境类型，M(t)表示当前时刻用户的运动模式，L(t)表示环境声音信号的声级强度或者环境声音的声级强度所属的区间，F(t)表示环境声音信号的能量频谱分布情况。
通过定义函数F(t)来描述用户某时所在位置的20～20kHz环境声音的 能量和频谱分布情况。
F(t)又包含F 0(t)和Q(t)，其中，F 0(t)用于表示当前时刻的最大噪声峰值对应的频点，Q(t)用于表示当前时刻环境声音的品质因数。
一般来说，Q值越大，说明环境声音能量分布越集中且频率较为单一，此时对应为噪声环境中的非稳态噪声或突发的脉冲噪音，即响度较大的鸣笛声、敲击、碰撞等猝发声。Q值越小，环境声音在各频段分布相对较宽泛，且该频段内噪声能量分布较均匀，此时对应的噪声环境为相对稳定的稳态噪音，例如某一用餐时段的餐厅环境，多为交谈或餐具轻碰的背景噪声，且F 0多在200Hz～300Hz之间。
在另一个实施例中，上述函数1也可以调整为
Action(t)＝(P(t),V(t),f(t),L(t),F(t))------函数2
其中，V(t)表示当前时刻用户的移动速度或者移动速度所属的区间，f(t)表示当前时刻用户的步频值或者步频值所属的区间。
在另一实施例中，使用场景包括用户的说话状态，因此函数Action(t)为：
Action(t)＝(P(t),M(t),L(t),F(t),S(t))------函数3
其中，S(t)用于表示用户当前是否处于讲话模式。
控制模块21根据查询或接收到的各传感器模块(不限于环境声音采集麦克风13、加速度传感器11、定位模块12、骨传导麦克风14/红外接近传感器15等)的实时数值，依据阈值进行判定用户的使用场景和环境声级，获取环境声的能量频谱分布情况，也就是得到P(t)，M(t)，L(t)，F(t)和S(t)。
控制模块21会对Action(t)函数进行实时查询，根据Action(t)的各项变量自动生成控制指令，将对应指令分别发送到音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24，使得各模块做出与当下场景和环境声音信号相匹配的响应，即实现自动调节播放效果以适应当前的播放环境。
同理，在另一个实施例中，上述函数3也可以调整为
Action(t)＝(P(t),V(t),f(t),L(t),F(t),S(t))------函数4。
环境声音信号的声级强度所属的区间可以包括以下区间：
(1)0dBA～40dBA为第一声级强度区间，表示非常安静环境。
(2)40dBA～60dBA为第二声级强度区间，表示相对安静环境。
(3)60dBA～80dBA为第三声级强度区间，表示相对聒噪的环境。
(4)80dBA～120dBA为第四声级强度区间，表示难以忍受的噪声环境。
环境声音信号的声级强度所属的区间也可以根据实际应用加以细分，并不完全局限于此定义。
用户移动速度所属的区间，例如可以包括：
(1)0～0.2米/秒为第一移动速度区间，表示静止。
(2)0.2米/秒～1.7米/秒为第二移动速度区间，表示步行。
(3)500km/h以上为第三移动速度区间，表示飞行。
用户移动速度的区间可以划分的更为细致，辅助步频值、用户所处的环境类型帮助控制模块21精确判断用户的使用场景。
通常情况下人的步频最快不超过5步/秒，而最慢不低于0.5步/秒，因此用户步频值的区间可以包括以下区间：
(1)0步/秒～0.5步/秒为第一步频值区间，表示静止。
(2)0.5步/秒～2.5步/秒为第二步频值区间，表示行走。
(3)2.5步/秒～5步/秒为第三步频值区间，表示跑步。
步频值所属的区间也可以根据实际应用加以细分，不完全局限于此定义。
需要说明的是，虽然上述区间划分的时候考虑了“静止”、“步行”、“跑步”、“飞行”等情况，但是用户的运动模式(包括所使用的交通工具)可以根据用户所处的具体环境类型、用户的移动速度的区间和步频值的区间来综合确定，如果进一步结合环境声音的能量和频谱分布情况，还可以确定的更为精确。
另外，上述函数也说明，本申请实施例可以对用户的地理位置数据、 移动速度、步频值、环境声音信号的声级强度、以及环境声音的能量和频谱分布进行综合分析，从而实现根据使用场景自动调节播放效果。
下面用几个具体的例子说明本申请实施例的自适应音频装置在几种场景下的工作过程：
<第一使用场景>
第一使用场景为用户处于道路环境并且处于行走模式。容易理解，在该使用场景中，可以仅通过所获取的加速度数据来估计用户的运动模式，并进而估计用户的使用场景。例如，如果加速度数据显示当前用户的步频值位于0.5步/秒～2.5步/秒的区间之内，则判断用户处于道路环境下的行走模式。在第一使用场景下，环境声音多为道路的交通噪声和不同强度的风噪等环境低频噪声，环境声音信号的F 0常会在100Hz附近，且Q值相对较小，即低频段噪声相对分布较为宽泛。而声级强度会因不同时段的交通状况不同而不同。
在第一使用场景下，控制模块21根据该使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制所述音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，包括：
控制风噪抑制子模块241对环境声音信号中的风噪信号进行抑制性滤波。风噪抑制子模块241可以例如为截止频率f 0＝300Hz的二阶高通滤波器。
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块242对环境声音信号中的语音信号进行增强处理。也就是说，在第一使用场景下，语音增强子模块242处于待机状态，可被控制模块21实时检测到的语音信号唤醒。
控制动态范围控制子模块243根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整。在一个实施例中：当所述环境声音信号的声级强度≤40dBA时，判断外界环境为安静环境，环境声音基本不包含有用信息，对环境声音信号进行轻微放大处理；当40dBA＜所述环境声音信号的声级强度≤50dBA时，对环境声音信号进行选择性放大处理；当 50dBA＜所述环境声音信号的声级强度≤60dBA时，对环境声音信号做放大、缩小处理；当所述环境声音信号的声级强度＞60dBA时，判断为比较嘈杂的环境，对环境声音信号进行衰减处理。通过动态范围控制，使用户行进过程中既能保证可以随意欣赏音乐又能对外界环境保持一定的监控和感知能力。需要说明的是，这里对环境声音信号的声级强度的区间的划分(≤40dBA、40dBA～50dBA、50dBA～60dBA，＞60dBA)，只是一个示例；可以根据实际情况，调整区间的划分情况。
控制EQ均衡处理子模块244对环境声音信号进行EQ补偿处理，输出到喇叭30进行播放。例如，对环境声音信号中的语音信号频带和鸣笛信号频段进行EQ补偿处理。
根据所述环境声音信号的声级强度确定是否开启主动降噪模块23，以及如果开启主动降噪模块23，根据所述环境声音信号的声级强度自动调整主动降噪模块23的降噪等级。所述环境声音信号的声级强度越强，则主动降噪模块23的降噪等级越高，主动降噪的程度越大。此外，在风噪强度比较大的情况下，可以增加反馈降噪的作用而适当降低前馈降噪在低频段的作用。主动降噪模块23生成的降噪信号输出到喇叭30。
在一个实施例中，控制模块21可以根据环境声音的能量和频谱分布分析出环境声音信号中是否存在某种警音提示声。例如，环境声音采集麦克风(13)在t到t 1时刻拾取到的环境噪声，经频域分析，在此段时间内间断或连续出现了频率在500Hz-1500Hz之间、品质因数Q远大于1的脉冲信号，且能量平均高于前一时段10dB，则判断环境声音信号中存在需要用户注意的某种警示音。如果环境声音信号中存在某种警音提示声，则控制模块21控制主动降噪模块23对环境声音信号中除警音提示声以外的部分进行主动降噪，并且控制动态范围控制子模块243对环境声音信号的警音提示声进行放大处理，以保证用户的安全性和警觉性。
根据到达喇叭30处的环境声音信号的声级强度控制音频信号音量调节模块22的工作参数，使得到达喇叭30处的音频信号和到达喇叭30处的环境声音信号的声级强度保持预设的比例。当环境声音的声级强度变大时可以自动控制音频信号音量变大，即当外界比较嘈杂时，加大音频信号 的音量。反之，当环境声音的声级强度变小时可以自动控制音频信号音量变小，即当外界环境比较安静时，降低音频信号的音量以保护用户的听力。
<第二使用场景>
第二使用场景为用户处于道路环境并且处于搭乘交通工具模式，则控制模块21根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，包括：
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块242对环境声音信号中的语音信号进行增强处理以及触发EQ均衡处理子模块244对环境声音信号中的语音信号频带进行EQ补偿处理。也就是说，在第二使用场景下，语音增强子模块242和EQ均衡处理子模块244处于待机状态，可被控制模块21实时检测到的语音信号唤醒。
控制主动降噪模块23按照最强降噪等级对环境声音信号进行主动降噪处理。或者，控制主动降噪模块23根据所述环境声音信号的声级强度确定是否开启主动降噪模块23，以及如果开启主动降噪模块23，根据环境声音信号的声级强度调整主动降噪模块23的降噪等级。
根据到达喇叭30处的环境声音信号的声级强度控制音频信号音量调节模块22的工作参数，使得到达喇叭30处的音频信号和到达喇叭30处的环境声音信号的声级强度保持预设的比例。当环境声音的声级强度变大时可以自动控制音频信号音量变大，即当外界比较嘈杂时，加大音频信号的音量。反之，当环境声音的声级强度变小时可以自动控制音频信号音量变小，即当外界环境比较安静时，降低音频信号的音量以保护用户的听力。
在一个例子中，当用户处于道路环境并且处于搭乘交通工具模式时，控制风噪抑制子模块(241)关闭。
在一个例子中，当用户处于道路环境并且处于搭乘交通工具模式时，监测环境声音信号的声级强度是否大于预设的声级强度上限或者小于预设的声级强度下限，如果环境声音信号的声级强度大于预设的声级强度上 限，则触发动态范围控制子模块(243)对环境声音信号进行衰减处理，如果环境声音信号的声级强度小于预设的声级强度下限，则触发动态范围控制子模块(243)对环境声音信号进行放大处理。所述声级强度上限例如为60dBA，所述声级强度下限例如为40dBA。
在一个例子中，当确定用户处于搭乘交通工具模式时，可以进一步确定用户搭乘何种交通工具。例如根据环境类型、地理位置数据中的高度数据、移动速度、步频值，可以确定用户处于骑行自行车、搭乘飞机、搭乘铁路、或是搭乘汽车等模式。例如，用户的移动速度达到250km/h并且用户处于铁路干线上，则可确定用户处于搭乘高铁模式。
控制模块21可以根据细分的交通工具对应的环境声音的特点，比如搭乘汽车时喇叭鸣笛声会比较多，高铁车厢中相对比较安静等特点，设置主动降噪模块23、环境声音调节模块24的具体调控方式，例如设置主动降噪模块23在用户搭乘高铁时的降噪等级为较低等级。
在一个例子中，当确定用户处于搭乘交通工具模式时，也可以根据环境声音信号的声级强度和环境声音的能量和频谱分布特点确定用户搭乘何种交通工具。使得控制模块21可以根据细分的交通工具对应的环境声音的特点，设置主动降噪模块23、环境声音调节模块24的具体调控方式。
在第一使用场景和第二使用场景下，用户可能与同伴交谈，也可能会有外界语音提醒，例如危险语音提醒或者第二使用场景下的车辆到站提醒，因此，在这两种使用场景下，语音增强子模块242可以被实时检测到的环境声音信号中的语音信号触发工作。
<第三使用场景>
第三使用场景为用户处于室内环境(例如，住宅教育医疗科研行政办公或餐饮贸易商业等室内区域)并且处于静止模式和讲话模式，则控制模块21根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，包括：
控制语音增强子模块242对环境声音信号中的语音信号进行增强处理。
控制EQ均衡处理子模块244对环境声音信号中的语音信号频带进行EQ补偿处理，输出到喇叭30进行播放。
控制风噪抑制子模块241和动态范围控制子模块243关闭。
控制主动降噪模块23关闭或者对环境声音信号进行主动降噪处理。
控制音频信号音量调节模块22调低音量或者暂停播放音频信号。
本申请实施例的自适应音频控制装置，可以具有多个环境声音采集麦克风13，包括设置在耳机外壳的用于采集用户所处的外界环境声音的麦克风和设置在耳机内部的用于采集用户耳廓处所听到环境声音的麦克风。多麦克风设置方式，能够更加准确地采集环境声音，并且能够体现用户耳廓处所听到环境声音的情况，可以用于主动降噪功能，有利于对环境声源的定位和调节语音与环境声音的比例，对降噪量进行更好的优化，有利于更智能的自适应音频控制。
在其它实施例中，控制模块21还可以分析环境声音采集麦克风13采集的环境声音信号，得到环境声音信号的声级强度、能量和频谱分布情况，结合加速度传感器、定位模块、其他传感器获取的数据，实现更加丰富的场景分析，以便于对音量调节模块22、主动降噪模块23、环境声音调节模块24进行更细腻的控制，提供给用户更好的体验效果。
对于本领域技术人员来说，可以通过硬件方式、软件方式或软硬件结合的方式实现前述基于场景识别的自适应音频控制装置。基于同一发明构思，参见图4所示，说明本申请实施例提供的基于场景识别的自适应音频控制方法，包括以下步骤：
401、分析用户的使用场景；
具体而言，步骤401中，可以获取用户的加速度数据，根据所述加速度数据分析用户的使用场景。容易理解，还可以获取用户的地理位置数据，并根据加速度数据和地理位置数据来分析用户的使用场景。
402、采集用户所处环境的环境声音信号，计算所述环境声音信号的声级强度，并分析所述环境声音信号的能量和频谱分布；
403、根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频播放装置的音频信号音量调节模块、主动降噪模块、和环境声音调节模块的工作。
在一种实施方式中，所述音频播放装置为耳机。
在另一种实施方式中，环境声音调节模块24包括下列子模块的任一或组合：风噪抑制子模块241、语音增强子模块242、动态范围控制子模块243、EQ均衡处理子模块244。
在另一种实施方式中，步骤401、分析用户的使用场景，包括：根据所述地理位置数据确定用户所处的环境类型；根据所述地理位置数据计算用户的移动速度；根据所述加速度数据计算用户的步频值；根据所述移动速度和步频值确定用户的运动模式。
在另一种实施方式中，所述环境类型包括室内环境和道路环境；所述运动模式包括下列任一：静止模式、道路行走模式和搭乘交通工具模式。
在另一种实施方式中，如果所述移动速度小于第一速度阈值并且所述步频值小于第一步频值阈值，则用户处于静止模式；如果所述移动速度在行走速度区间内并且所述步频值在行走步频值区间内，则用户处于行走模式；如果所述移动速度大于第二速度阈值，则用户处于搭乘交通工具模式。
在另一种实施方式中，所述音频播放装置还包括骨传导麦克风或红外接近传感器，用户的使用场景还包括用户的说话状态，所述方法包括以下步骤：根据所述骨传导麦克风或红外接近传感器输出的信号确定用户是否处于讲话模式。
在另一种实施方式中，所述采集用户所处环境的环境声音信号包括采集用户实时位置外界环境声音信号和采集用户耳廓附近所听到的环境声音信号。
<第一使用场景>
如果所述使用场景为用户处于道路环境并且处于行走模式，则所述 根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，包括：
控制风噪抑制子模块241对环境声音信号中的风噪信号进行抑制性滤波；
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触发语音增强子模块242对环境声音信号中的语音信号进行增强处理；
控制动态范围控制子模块243根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整；
控制EQ均衡处理子模块244对环境声音信号进行EQ补偿处理；
根据到达音频播放装置的喇叭处的环境声音信号的声级强度控制音频信号音量调节模块22的工作参数，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例。
在一种实施方式中，所述控制动态范围控制子模块243根据所述环境声音信号的声级强度对环境声音信号进行动态范围调整，包括：当40dBA＜所述环境声音信号的声级强度≤50dBA时，对环境声音信号进行放大处理；当所述环境声音信号的声级强度＞60dBA时，对环境声音信号进行衰减处理。
在另一种实施方式中，所述对环境声音信号进行EQ补偿处理，包括对环境声音信号中的语音信号频带和鸣笛信号频段进行EQ补偿处理。
在另一种实施方式中，根据所述环境声音信号的声级强度确定是否开启所述主动降噪模块23，以及如果开启主动降噪模块23，根据所述环境声音信号的声级强度调整主动降噪模块23的降噪等级。
<第二使用场景>
如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，包括：
监测环境声音信号中是否含有语音信号，如果含有语音信号，则触 发语音增强子模块242对环境声音信号中的语音信号进行增强处理以及触发EQ均衡处理子模块244对环境声音信号中的语音信号频带进行EQ补偿处理；
控制主动降噪模块23按照最强降噪等级进行主动降噪处理；或者，根据所述环境声音信号的声级强度确定是否开启主动降噪模块23，以及如果开启主动降噪模块23，根据所述环境声音信号的声级强度调整主动降噪模块23的降噪等级；
根据到达音频播放装置的喇叭处的环境声音信号的声级强度控制音频信号音量调节模块22的工作参数，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例。
在一种实施方式中，当用户处于道路环境并且处于搭乘交通工具模式时，控制风噪抑制子模块241关闭。
在另一种实施方式中，当用户处于道路环境并且处于搭乘交通工具模式时，监测环境声音信号的声级强度是否大于预设的声级强度上限或者小于预设的声级强度下限，如果环境声音信号的声级强度大于预设的声级强度上限，则触发动态范围控制子模块(243)对环境声音信号进行衰减处理，如果环境声音信号的声级强度小于预设的声级强度下限，则触发动态范围控制子模块(243)对环境声音信号进行放大处理。
<第三使用场景>
如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音的能量和频谱分布控制音频信号音量调节模块22、主动降噪模块23、环境声音调节模块24的工作，包括：
控制语音增强子模块242对环境声音信号中的语音信号进行增强处理；
控制EQ均衡处理子模块244对环境声音信号中的语音信号频带进行EQ补偿处理；
控制主动降噪模块23关闭或者对环境声音信号进行主动降噪处理；
控制音频信号音量调节模块22调低音量或者暂停播放音频信号。
在一种实施方式中，控制风噪抑制子模块241和动态范围控制子模块243关闭。
需要说明的是，本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。但本领域技术人员应当清楚的是，上述各实施例可以根据需要单独使用或者相互结合使用。以上所描述的装置实施例仅仅是示意性的，其中作为分离部件说明的模块可以是或者也可是不是物理上分开的。
另外，附图中的流程图和框图显示了根据本申请的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的装置来实现，或者可以用专用硬件与计算机指令的组合来实现。
本申请实施例所提供的计算机程序产品，包括存储了程序代码的计算机可读存储介质，所述程序代码包括的指令可用于执行前面方法实施例中所述的方法，具体实现可参见方法实施例，在此不再赘述。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成 到另一个装置，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅为本申请的优选实施例而已，并不用于限制本申请，对 于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。
虽然已经通过例子对本申请的一些特定实施例进行了详细说明，但是本领域的技术人员应该理解，以上例子仅是为了进行说明，而不是为了限制本申请的范围。本领域的技术人员应该理解，可在不脱离本申请的范围的情况下，对以上实施例进行修改。本申请的范围由所附权利要求来限定。

Claims (21)

  1. 一种控制音频播放装置的方法，其特征在于，包括以下步骤：
    获取用户的加速度数据，根据所述加速度数据分析用户的使用场景；
    获取用户所处环境的环境声音信号，计算所述环境声音信号的声级强度，并分析所述环境声音信号的能量和频谱分布；
    根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节。
  2. 根据权利要求1所述的方法，还包括：
    获取用户的地理位置数据；其中
    根据所述加速度数据和所述地理位置数据来分析用户的使用场景。
  3. 根据权利要求2所述的方法，其特征在于，所述对所述环境声音信号的调节包括下列任一操作或其组合：风噪抑制、语音增强、动态范围调整、EQ均衡处理。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述加速度数据和地理位置数据分析用户的使用场景，包括：
    根据所述地理位置数据确定用户所处的环境类型；
    根据所述地理位置数据计算用户的移动速度；
    根据所述加速度数据计算用户的步频值；
    根据所述移动速度和步频值确定用户的运动模式。
  5. 根据权利要求4所述的方法，其特征在于，所述环境类型包括室内环境和道路环境；所述运动模式包括下列任一：静止模式、行走模式和搭乘交通工具模式。
  6. 根据权利要求5所述的方法，其特征在于，所述方法还包括：确定用户是否处于讲话模式。
  7. 根据权利要求1所述的方法，其特征在于，所述获取用户所处环境的环境声音信号包括获取用户实时位置外界环境声音信号和获取用户耳廓附近所听到的环境声音信号。
  8. 根据权利要求5所述的方法，其特征在于，如果所述使用场景为 用户处于道路环境并且处于行走模式，所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节，包括以下一项或多项：
    对所述环境声音信号中的风噪信号进行抑制性滤波；
    监测所述环境声音信号中是否含有语音信号，如果含有语音信号，则对所述环境声音信号中的语音信号进行增强处理；
    根据所述环境声音信号的声级强度对所述环境声音信号进行动态范围调整；
    对所述环境声音信号进行EQ补偿处理；
    根据到达所述音频播放装置的喇叭处的环境声音信号的声级强度来控制音频播放装置的音频信号音量，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例；以及
    根据所述环境声音信号的声级强度确定是否执行主动降噪，以及如果执行主动降噪，根据所述环境声音信号的声级强度调整主动降噪的降噪等级。
  9. 根据权利要求5所述的方法，其特征在于，如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节，包括以下一项或多项：
    监测所述环境声音信号中是否含有语音信号，如果含有语音信号，则对所述环境声音信号中的语音信号进行增强处理，以及对所述环境声音信号中的语音信号频带进行EQ补偿处理；
    设置主动降噪等级为最强降噪等级或者根据所述环境声音信号的声级强度确定是否执行主动降噪，以及如果执行主动降噪，根据所述环境声音信号的声级强度调整主动降噪的降噪等级；
    根据到达所述音频播放装置的喇叭处的环境声音信号的声级强度来控制音频播放装置的音频信号音量，使得到达喇叭处的音频信号和到达喇 叭处的环境声音信号的声级强度保持预设的比例；
    不执行风噪抑制；以及
    监测所述环境声音信号的声级强度是否大于预设的声级强度上限或者小于预设的声级强度下限，如果所述环境声音信号的声级强度大于预设的声级强度上限，则对所述环境声音信号进行衰减处理，如果所述环境声音信号的声级强度小于预设的声级强度下限，则对所述环境声音信号进行放大处理。
  10. 根据权利要求5所述的方法，其特征在于，如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节，包括以下一项或多项：
    对所述环境声音信号中的语音信号进行增强处理；
    对所述环境声音信号中的语音信号频带进行EQ补偿处理；
    不执行主动降噪或者对所述环境声音信号进行主动降噪处理；
    调低音频信号音量或者暂停播放音频信号；以及
    不执行风噪抑制和动态范围调整。
  11. 一种控制音频播放装置的系统，其特征在于，包括：
    一个或者多个处理器；
    耦合至所述一个或者多个处理器中的至少一个处理器的存储器；
    所述存储器中存储有计算机程序指令，当由所述至少一个处理器执行所述计算机程序指令时，使得所述系统执行控制音频播放装置的方法，所述方法包括：
    获取用户的加速度数据，根据所述加速度数据分析用户的使用场景；
    获取用户所处环境的环境声音信号，计算所述环境声音信号的声级强度，并分析所述环境声音信号的能量和频谱分布；
    根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节。
  12. 根据权利要求11所述的系统，其特征在于，所述当由所述至少一个处理器执行所述计算机程序指令时，使得所述系统执行控制音频播放装置的方法，还包括：
    获取用户的地理位置数据；其中
    根据所述加速度数据和所述地理位置数据来分析用户的使用场景。
  13. 根据权利要求12所述的系统，其特征在于，所述对所述环境声音信号的调节包括下列任一操作或其组合：风噪抑制、语音增强、动态范围调整、EQ均衡处理。
  14. 根据权利要求13所述的系统，其特征在于，所述至少一个处理器在执行所述根据所述加速度数据和地理位置数据分析用户的使用场景的指令时，执行以下操作：
    根据所述地理位置数据确定用户所处的环境类型；
    根据所述地理位置数据计算用户的移动速度；
    根据所述加速度数据计算用户的步频值；
    根据所述移动速度和步频值确定用户的运动模式。
  15. 根据权利要求14所述的系统，其特征在于，所述环境类型包括室内环境和道路环境；所述运动模式包括下列任一：静止模式、行走模式和搭乘交通工具模式。
  16. 根据权利要求15所述的系统，其特征在于，所述当由所述至少一个处理器执行所述计算机程序指令时，使得所述系统执行控制音频播放装置的方法，还包括：确定用户是否处于讲话模式。
  17. 根据权利要求11所述的系统，其特征在于，所述至少一个处理器在执行所述获取用户所处环境的环境声音信号的指令时，执行以下操作：
    获取用户实时位置外界环境声音信号和获取用户耳廓附近所听到的环境声音信号。
  18. 根据权利要求15所述的系统，其特征在于，如果所述使用场景为用户处于道路环境并且处于行走模式，所述至少一个处理器在执行所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级 和对所述环境声音信号的调节的指令时，执行以下一项或多项：
    对所述环境声音信号中的风噪信号进行抑制性滤波；
    监测所述环境声音信号中是否含有语音信号，如果含有语音信号，则对所述环境声音信号中的语音信号进行增强处理；
    根据所述环境声音信号的声级强度对所述环境声音信号进行动态范围调整；
    对所述环境声音信号进行EQ补偿处理；
    根据到达所述音频播放装置的喇叭处的环境声音信号的声级强度来控制音频播放装置的音频信号音量，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例；以及
    根据所述环境声音信号的声级强度确定是否执行主动降噪，以及如果执行主动降噪，根据所述环境声音信号的声级强度调整主动降噪的降噪等级。
  19. 根据权利要求15所述的系统，其特征在于，如果所述使用场景为用户处于道路环境并且处于搭乘交通工具模式，则所述至少一个处理器在执行所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节的指令时，执行以下一项或多项：
    监测所述环境声音信号中是否含有语音信号，如果含有语音信号，则对所述环境声音信号中的语音信号进行增强处理，以及对所述环境声音信号中的语音信号频带进行EQ补偿处理；
    设置主动降噪等级为最强降噪等级或者根据所述环境声音信号的声级强度确定是否执行主动降噪，以及如果执行主动降噪，根据所述环境声音信号的声级强度调整主动降噪的降噪等级；
    根据到达所述音频播放装置的喇叭处的环境声音信号的声级强度来控制音频播放装置的音频信号音量，使得到达喇叭处的音频信号和到达喇叭处的环境声音信号的声级强度保持预设的比例；
    不执行风噪抑制；以及
    监测所述环境声音信号的声级强度是否大于预设的声级强度上限或 者小于预设的声级强度下限，如果所述环境声音信号的声级强度大于预设的声级强度上限，则对所述环境声音信号进行衰减处理，如果所述环境声音信号的声级强度小于预设的声级强度下限，则对所述环境声音信号进行放大处理。
  20. 根据权利要求15所述的系统，其特征在于，如果所述使用场景为用户处于室内环境并且处于静止模式和讲话模式，则所述至少一个处理器在执行所述根据所述使用场景、所述环境声音信号的声级强度、以及所述环境声音信号的能量和频谱分布来控制音频播放装置的音频信号音量、主动降噪等级和对所述环境声音信号的调节的指令时，执行以下一项或多项：
    对所述环境声音信号中的语音信号进行增强处理；
    对所述环境声音信号中的语音信号频带进行EQ补偿处理；
    不执行主动降噪或者对所述环境声音信号进行主动降噪处理；
    调低音频信号音量或者暂停播放音频信号；以及
    不执行风噪抑制和动态范围调整。
  21. 一种计算机程序产品，当所述计算机程序产品由处理器执行时，能够实现如权利要求1-10中任一项所述的控制音频播放装置的方法。
PCT/CN2019/070657 2018-01-17 2019-01-07 一种基于场景识别的自适应音频控制装置和方法 WO2019141102A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP19741628.2A EP3672274A4 (en) 2018-01-17 2019-01-07 DEVICE AND METHOD FOR ADAPTIVE AUDIO CONTROL BASED ON SCENARIO IDENTIFICATION
US16/647,768 US10979814B2 (en) 2018-01-17 2019-01-07 Adaptive audio control device and method based on scenario identification

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810043127.XA CN110049403A (zh) 2018-01-17 2018-01-17 一种基于场景识别的自适应音频控制装置和方法
CN201810043127.X 2018-01-17

Publications (1)

Publication Number Publication Date
WO2019141102A1 true WO2019141102A1 (zh) 2019-07-25

Family

ID=67273101

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/070657 WO2019141102A1 (zh) 2018-01-17 2019-01-07 一种基于场景识别的自适应音频控制装置和方法

Country Status (3)

Country Link
EP (1) EP3672274A4 (zh)
CN (1) CN110049403A (zh)
WO (1) WO2019141102A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111698602A (zh) * 2020-06-19 2020-09-22 青岛歌尔智能传感器有限公司 耳机及其耳机控制方法、控制装置和可读存储介质
EP3869821A1 (en) * 2020-02-20 2021-08-25 Beijing Xiaoniao Tingting Technology Co., Ltd Signal processing method and device for earphone, and earphone
CN113505441A (zh) * 2021-07-29 2021-10-15 中国第一汽车股份有限公司 一种车辆风噪隔声性能评估方法、装置、设备及存储介质

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110830862A (zh) * 2019-10-10 2020-02-21 广东思派康电子科技有限公司 一种自适应降噪的降噪耳机
CN110996205A (zh) * 2019-11-28 2020-04-10 歌尔股份有限公司 耳机的控制方法、耳机及可读存储介质
CN111179984B (zh) * 2019-12-31 2022-02-08 Oppo广东移动通信有限公司 音频数据处理方法、装置及终端设备
CN111447523B (zh) * 2020-03-31 2022-02-18 歌尔科技有限公司 耳机及其降噪方法、计算机可读存储介质
CN111294691B (zh) * 2020-03-31 2021-10-26 歌尔股份有限公司 耳机及其降噪方法、计算机可读存储介质
CN111586522B (zh) * 2020-05-20 2022-04-15 歌尔科技有限公司 一种耳机降噪方法、耳机降噪装置、耳机及存储介质
CN113873379B (zh) * 2020-06-30 2023-05-02 华为技术有限公司 一种模式控制方法、装置及终端设备
WO2022022585A1 (zh) * 2020-07-31 2022-02-03 华为技术有限公司 电子设备及其音频降噪方法和介质
CN114079838B (zh) * 2020-08-21 2024-04-09 华为技术有限公司 一种音频控制方法、设备及系统
CN111935584A (zh) * 2020-08-26 2020-11-13 恒玄科技(上海)股份有限公司 用于无线耳机组件的风噪处理方法、装置以及耳机
CN112312257B (zh) * 2020-09-08 2022-11-29 深圳市逸音科技有限公司 一种主动数字降噪智能3d耳机
CN112185409A (zh) * 2020-10-15 2021-01-05 福建瑞恒信息科技股份有限公司 一种双麦克风降噪方法和存储设备
US11468875B2 (en) 2020-12-15 2022-10-11 Google Llc Ambient detector for dual mode ANC
CN112767908A (zh) * 2020-12-29 2021-05-07 安克创新科技股份有限公司 基于关键声音识别的主动降噪方法、电子设备及存储介质
CN112765395B (zh) * 2021-01-22 2023-09-19 咪咕音乐有限公司 音频播放方法、电子设备和存储介质
CN112954532A (zh) * 2021-03-06 2021-06-11 深圳市尊特数码有限公司 蓝牙耳机调节降噪等级的方法、系统、终端及存储介质
CN114121033B (zh) * 2022-01-27 2022-04-26 深圳市北海轨道交通技术有限公司 基于深度学习的列车广播语音增强方法和系统
CN114554346B (zh) * 2022-02-24 2022-11-22 潍坊歌尔电子有限公司 Anc参数的自适应调整方法、设备及存储介质
CN114280571B (zh) * 2022-03-04 2022-07-19 北京海兰信数据科技股份有限公司 一种雨杂波信号的处理方法、装置及设备
CN115778046B (zh) * 2023-02-09 2023-06-09 深圳豪成通讯科技有限公司 基于数据分析的智能安全帽调节控制方法和系统
CN117041803B (zh) * 2023-08-30 2024-03-22 江西瑞声电子有限公司 耳机播放的控制方法、电子设备及存储介质
CN116961806B (zh) * 2023-09-21 2024-02-09 广东保伦电子股份有限公司 一种基于卫星授时的花车音频同步广播系统，装置及方法
CN117238322B (zh) * 2023-11-10 2024-01-30 深圳市齐奥通信技术有限公司 一种基于智能感知的自适应语音调控方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140198929A1 (en) * 2012-02-22 2014-07-17 Snik Llc Magnetic earphones holder
CN103945062A (zh) * 2014-04-16 2014-07-23 华为技术有限公司 一种用户终端的音量调节方法、装置及终端
CN105554610A (zh) * 2014-12-29 2016-05-04 北京小鸟听听科技有限公司 耳机环境声音的调节方法和耳机
CN106792315A (zh) * 2017-01-05 2017-05-31 歌尔科技有限公司 一种抵消环境噪声的方法和装置及一种主动降噪耳机

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9113240B2 (en) * 2008-03-18 2015-08-18 Qualcomm Incorporated Speech enhancement using multiple microphones on multiple devices
CN101458931A (zh) * 2009-01-08 2009-06-17 无敌科技(西安)有限公司 一种消除语音信号中的环境噪声的方法
US8391524B2 (en) * 2009-06-02 2013-03-05 Panasonic Corporation Hearing aid, hearing aid system, walking detection method, and hearing aid method
US9025782B2 (en) * 2010-07-26 2015-05-05 Qualcomm Incorporated Systems, methods, apparatus, and computer-readable media for multi-microphone location-selective processing
US10218327B2 (en) * 2011-01-10 2019-02-26 Zhinian Jing Dynamic enhancement of audio (DAE) in headset systems
US9055367B2 (en) * 2011-04-08 2015-06-09 Qualcomm Incorporated Integrated psychoacoustic bass enhancement (PBE) for improved audio
JP2013102370A (ja) * 2011-11-09 2013-05-23 Sony Corp ヘッドホン装置、端末装置、情報送信方法、プログラム、ヘッドホンシステム
JP5949061B2 (ja) * 2012-03-30 2016-07-06 ソニー株式会社 情報処理装置、情報処理方法、及びプログラム
CN104158506A (zh) * 2014-07-29 2014-11-19 腾讯科技（深圳）有限公司 调节音量的方法、装置及终端
CN106285083B (zh) * 2015-05-12 2019-02-15 国网浙江省电力公司 一种变电站降噪方法
CN105530581A (zh) * 2015-12-10 2016-04-27 安徽海聚信息科技有限责任公司 一种基于声音识别的智能穿戴设备和控制方法
CN105611443B (zh) * 2015-12-29 2019-07-19 歌尔股份有限公司 一种耳机的控制方法、控制系统和耳机
CN106678552B (zh) * 2017-01-05 2019-03-26 北京埃德尔黛威新技术有限公司 一种新型渗漏预警方法
CN107105359B (zh) * 2017-06-02 2019-10-18 歌尔科技有限公司 一种切换耳机工作模式方法和一种耳机
CN107484058A (zh) * 2017-09-26 2017-12-15 联想(北京)有限公司 耳机装置和控制方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140198929A1 (en) * 2012-02-22 2014-07-17 Snik Llc Magnetic earphones holder
CN103945062A (zh) * 2014-04-16 2014-07-23 华为技术有限公司 一种用户终端的音量调节方法、装置及终端
CN105554610A (zh) * 2014-12-29 2016-05-04 北京小鸟听听科技有限公司 耳机环境声音的调节方法和耳机
CN106792315A (zh) * 2017-01-05 2017-05-31 歌尔科技有限公司 一种抵消环境噪声的方法和装置及一种主动降噪耳机

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3869821A1 (en) * 2020-02-20 2021-08-25 Beijing Xiaoniao Tingting Technology Co., Ltd Signal processing method and device for earphone, and earphone
US11302298B2 (en) 2020-02-20 2022-04-12 Beijing Xiaoniao Tingting Technology Co., LTD. Signal processing method and device for earphone, and earphone
CN111698602A (zh) * 2020-06-19 2020-09-22 青岛歌尔智能传感器有限公司 耳机及其耳机控制方法、控制装置和可读存储介质
CN113505441A (zh) * 2021-07-29 2021-10-15 中国第一汽车股份有限公司 一种车辆风噪隔声性能评估方法、装置、设备及存储介质
CN113505441B (zh) * 2021-07-29 2023-03-14 中国第一汽车股份有限公司 一种车辆风噪隔声性能评估方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN110049403A (zh) 2019-07-23
EP3672274A4 (en) 2021-05-05
EP3672274A1 (en) 2020-06-24

Similar Documents

Publication Publication Date Title
WO2019141102A1 (zh) 一种基于场景识别的自适应音频控制装置和方法
US10979814B2 (en) Adaptive audio control device and method based on scenario identification
US10535334B2 (en) Method and device for acute sound detection and reproduction
CN102124758B (zh) 助听器、助听系统、步行检测方法和助听方法
KR101542027B1 (ko) 강한 노이즈 환경 하에서의 헤드셋 통신 방법 및 헤드셋
US11276384B2 (en) Ambient sound enhancement and acoustic noise cancellation based on context
CN109348327B (zh) 一种主动降噪系统
JP2016051038A (ja) ノイズゲート装置
CN107533838A (zh) 使用多个麦克风的语音感测
CN106463107A (zh) 在耳机与源之间协作处理音频
WO2008103925A1 (en) Method and device for sound detection and audio control
US20180160211A1 (en) Sports headphone with situational awareness
CN104966521B (zh) 一种调整音乐播放模式的方法及装置
CN111683319A (zh) 一种通话拾音降噪方法及耳机、存储介质
JP2002051392A (ja) 車内会話補助装置
JP6548938B2 (ja) 音声処理装置及び音声処理方法
JP2010124435A (ja) 車内会話補助装置
JP3411648B2 (ja) 車載用オーディオ装置
CN115515040A (zh) 一种主动降噪听音设备风噪优化方法及系统
CN115866474A (zh) 无线耳机的透传降噪控制方法、系统及无线耳机
JP2010193213A (ja) 補聴器
US11812243B2 (en) Headset capable of compensating for wind noise
US20230169948A1 (en) Signal processing device, signal processing program, and signal processing method
WO2022230275A1 (ja) 情報処理装置、情報処理方法、及び、プログラム
JPWO2018105668A1 (ja) 音響装置及び音響処理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19741628

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019741628

Country of ref document: EP

Effective date: 20200317

NENP Non-entry into the national phase

Ref country code: DE