WO2017185342A1 - 一种语音输入异常的确定方法、装置、终端以及存储介质 - Google Patents

一种语音输入异常的确定方法、装置、终端以及存储介质 Download PDF

Info

Publication number
WO2017185342A1
WO2017185342A1 PCT/CN2016/080716 CN2016080716W WO2017185342A1 WO 2017185342 A1 WO2017185342 A1 WO 2017185342A1 CN 2016080716 W CN2016080716 W CN 2016080716W WO 2017185342 A1 WO2017185342 A1 WO 2017185342A1
Authority
WO
WIPO (PCT)
Prior art keywords
audio
audio signal
electronic device
preset
collection module
Prior art date
Application number
PCT/CN2016/080716
Other languages
English (en)
French (fr)
Inventor
杨霖
尹朝阳
杨敬文
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to BR112017021239-0A priority Critical patent/BR112017021239B1/pt
Priority to US15/574,405 priority patent/US10231070B2/en
Priority to EP16895743.9A priority patent/EP3301950B1/en
Priority to AU2016402256A priority patent/AU2016402256B2/en
Priority to CN201680025187.8A priority patent/CN107548564B/zh
Priority to PCT/CN2016/080716 priority patent/WO2017185342A1/zh
Priority to CA2981775A priority patent/CA2981775C/en
Priority to CN202110146671.9A priority patent/CN113038353B/zh
Publication of WO2017185342A1 publication Critical patent/WO2017185342A1/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
    • H04R29/00—Monitoring arrangements; Testing arrangements
    • H04R29/004—Monitoring arrangements; Testing arrangements for microphones
    • H04R29/005—Microphone arrays
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/21—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being power information
    • 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
    • H04R1/32—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only
    • H04R1/40—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers
    • H04R1/406—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers 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
    • H04R3/005—Circuits for transducers, loudspeakers or microphones for combining the signals of two or more microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2499/00—Aspects covered by H04R or H04S not otherwise provided for in their subgroups
    • H04R2499/10—General applications
    • H04R2499/11—Transducers incorporated or for use in hand-held devices, e.g. mobile phones, PDA's, camera's
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the present invention relates to the field of electronic technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for determining a voice input abnormality.
  • a small hole is generally arranged in the outer casing of the electronic device as a sound collecting hole of the audio collecting module, and the sound receiving hole is connected with the audio collecting module.
  • the environment in which the electronic device is located is complicated, there are many times when the sound hole is blocked and the audio collection module collects sound information.
  • There are some methods for detecting voice which can only detect whether the algorithm of the collected audio signal is normal.
  • the present invention provides a method, a device, a terminal, and a storage medium for determining a voice input abnormality.
  • the method and the device provided by the present invention solve the prior art, and there is no effective method for determining that the sound receiving hole of the electronic device is blocked due to blockage. It is also impossible to prompt the user for a radio abnormality or provide remedial measures to affect the user experience.
  • the first aspect provides a method for determining a voice input abnormality, which is applied to an electronic device having an audio collection module, including:
  • the voice input of the electronic device is abnormal.
  • the audio collecting module may not be able to collect the audio signal normally, and the collected audio signal may be abnormal in the time domain and the frequency domain.
  • the solution provided by the embodiment of the present invention is collected.
  • the time domain (amplitude of the audio) and the frequency domain (the energy value of the frequency point) of the audio signal are comprehensively judged, and it is determined whether the voice input is abnormal according to the judgment result.
  • the Mic input amplitude combined with the input frequency for comprehensive detection can effectively improve the detection accuracy of Mic input anomaly.
  • the invention also provides a possible design for determining whether the amplitude value of the audio signal is less than a preset amplitude threshold and/or whether the energy distribution of the audio signal satisfies a preset condition:
  • the amplitude and the energy are judged only when it is detected that the electronic device establishes the voice path, so that the problem of silent voice transmission and the power saving effect can be achieved.
  • Another possible design is to determine whether the energy distribution of the audio signal meets preset conditions, including:
  • the energy value of each frequency point in the audio signal is affected, so based on the characteristic of the sound hole blocking, in this possible design, the frequency signal is subjected to Fourier frequency domain conversion to obtain each frequency point.
  • the energy value can be used to determine whether the sound hole of the electronic device is blocked according to the energy value of each frequency point.
  • the method for determining the sound hole of the electronic device is determined by the foregoing manner, and the corresponding solution may be provided in the following manner. After determining that the voice input of the electronic device is abnormal, the method further includes:
  • the prompt information is output; wherein the prompt information is used to prompt the user that the electronic device voice input is abnormal.
  • the adjusting the audio collection module for acquiring the audio signals includes:
  • the solution of the embodiment of the present invention after determining the problem of the sound hole, the solution can be provided in a timely and effective manner by the above manner, and other audio collection modules can be enabled to receive the sound or notify the user. Allows users to resolve issues as quickly as possible.
  • the preset amplitude threshold is obtained by:
  • the collected audio signal collected multiple times obtains a preset amplitude threshold
  • a further implementation may be: obtaining a preset amplitude threshold by acquiring audio signals having different sonic characteristics; or
  • the amplitude value of the audio signal collected by the audio collecting module is calculated, and the average value of the amplitude values of the obtained audio signals is calculated to obtain a preset amplitude threshold.
  • the audio signals in various scenes are collected as the basis for calculating the preset amplitude threshold, so that the preset amplitude threshold can be more accurately adapted to different scenes, thereby reducing the abnormality of the voice input of the electronic device. Mistakes.
  • the acquisition of the audio signal by the second audio acquisition module is as follows:
  • a specific implementation manner of selecting a second audio collection module from multiple audio collection modules is provided, which can provide a specific fault-tolerant avoidance method after the voice input of the electronic device is abnormal, which can reduce the Mic input abnormality and cause the device to fail. Effectively capture the impact of voice input data.
  • an electronic device including:
  • An audio collection module for collecting audio signals
  • a memory for storing instructions
  • a processor configured to invoke an instruction stored in the memory to determine whether an amplitude value of an audio signal collected by the audio collection module is less than a preset amplitude threshold, and/or whether an energy distribution of the audio signal satisfies Setting a condition; if the amplitude value of the audio signal is less than a preset amplitude threshold and/or the energy distribution of the audio signal does not satisfy the preset condition, determining that the voice input of the electronic device is abnormal.
  • the processor invokes instructions stored in the memory to implement the solution in the method design of the first aspect above.
  • the implementation and benefits of the electronic device to solve the problem reference may be made to the first aspect and the first aspect.
  • the possible implementations and the beneficial effects, therefore, the implementation of the electronic device can refer to the implementation of the method, and the repeated description is not repeated.
  • a device being disposed in an electronic device, the electronic device comprising at least an audio collection module, the device comprising:
  • a comparison module configured to determine whether an amplitude value of the audio signal collected by the audio collection module is less than a preset amplitude threshold, and/or whether an energy distribution of the audio signal meets a preset condition
  • a determining module configured to determine that the voice input of the electronic device is abnormal if the amplitude value of the audio signal is less than a preset amplitude threshold and/or the energy distribution of the audio signal does not satisfy the preset condition.
  • the principle and the beneficial effects of the device can be referred to the first aspect and the possible implementation manners of the first aspect and the beneficial effects. Therefore, the implementation of the device can be referred to the implementation of the method. The repetitions are not repeated here.
  • a non-transitory computer readable storage medium storing one or more programs
  • the one or more programs comprising instructions that, when executed by an electronic device having an audio capture module
  • the electronic device performs the first aspect and the possible embodiments of the first aspect described above.
  • the principles and advantages of the problems solved by the program stored in the non-volatile computer readable storage medium when executed by the electronic device having the audio collection module can be referred to the above first aspect and the first aspect.
  • the implementation of the non-transitory computer readable storage medium can be referred to the implementation of the method, and the repeated description is not repeated here.
  • the method and device provided by the embodiments of the present invention comprehensively determine the time domain and frequency domain characteristics of the collected audio signal, and determine whether the voice input is abnormal according to the determination result.
  • the prior art solves the problem that the radio reception hole blocked by the electronic device is not normal, and there is no effective determination method, and the user is not prompted for the radio reception abnormality or provides remedial measures, which affects the user experience.
  • FIG. 1 is a schematic flowchart of a method for determining an abnormality of a voice input of an electronic device according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
  • FIG. 4 is a schematic structural diagram of a device according to an embodiment of the present invention.
  • the existing voice detection method can only detect whether the collected audio signal has a problem in the speech algorithm itself, there is no suitable judgment method for the validity and accuracy of the data collected by the audio collection module (for example, Mic).
  • a sound hole is opened on the outer casing of the electronic device, and the sound receiving hole is connected to the audio collecting module; since the sound receiving hole is usually arranged on the outer casing of the mobile phone, when the user holds the electronic device or an object around the electronic device, the sound receiving hole may be Will be blocked, which in turn affects the accuracy of the audio acquisition module to collect audio signals, such as: microphone pickup sound is small or There is no good improvement measure for similar problems. Therefore, the present invention provides a method for determining an abnormality of a voice input of an electronic device to improve the above problem.
  • the embodiments of the present invention are further described in detail below with reference to the accompanying drawings.
  • an embodiment of the present invention provides a method for determining a voice input abnormality, which is applied to an electronic device having an audio collection module, and the method specifically includes:
  • the method provided by the embodiment of the present invention can be applied to all electronic devices provided with an audio collection module (which may be a microphone), and the electronic device collects sound information through the audio collection module, and converts the sound information into an analog audio signal;
  • An audio hole is formed on the outer casing of the electronic device, and the sound collecting hole is connected to the audio collecting module.
  • the sound hole is generally set at the bottom of the mobile terminal, but in general, when the user holds the mobile terminal, the support effect is better and the finger is placed on the bottom of the mobile terminal, so in this way In the case of a situation, it is easy to cause a finger to block the sound hole, which causes a problem that the call is silent.
  • Step 101 Determine an amplitude of an audio signal collected by the audio collection module and an energy distribution of the audio signal.
  • determining whether the amplitude of the audio signal is less than a preset amplitude threshold, and/or whether the energy distribution of the audio signal satisfies a preset condition And detecting whether a voice path is established, and if it is detected that the voice path is established, determining whether the amplitude of the audio signal is less than a preset amplitude threshold, and/or whether the energy distribution of the audio signal satisfies a preset condition.
  • the amplitude value of the audio signal can be determined by sampling the audio signal in the unit period, obtaining the sampled value of the audio signal, calculating the absolute value of the amplitude of the sampled value of the audio signal, and calculating the average of the absolute values of the amplitudes of the plurality of sampled values.
  • the value gives the average of the amplitudes of the sampled values of the audio signal, which is the amplitude value of the audio signal.
  • the following steps 102 to 103 describe in detail the comprehensive determination of the time domain characteristic and the frequency domain characteristic of the collected audio signal to determine whether the voice input of the electronic device is abnormal.
  • Step 102 Determine whether the amplitude of the audio signal collected by the audio collection module is less than a preset amplitude threshold, and/or whether the energy distribution of the audio signal meets a preset condition;
  • the amplitude of the audio signal collected by the audio collection module is greatly reduced, which may be less than the preset amplitude threshold.
  • the duration can be dynamically set according to the design needs.
  • the preset amplitude threshold of the embodiment of the present invention can be obtained according to an experiment, that is, the sound hole is blocked, and the audio signal is collected when the sound hole is blocked, and the amplitude of the audio signal collected when the sound hole is blocked is the preset amplitude threshold.
  • the audio signal is collected multiple times, and the average value of the amplitudes of the multiple collected audio signals is obtained, and the obtained average value is used as the preset amplitude threshold.
  • a preset amplitude threshold may be obtained by collecting audio signals having different acoustic characteristics (for example, male voice, female voice, old man, child, etc.).
  • the sound receiving holes can be blocked by different blocking methods (for example, different blocking angles, using different objects to block the sound collecting holes, etc.), and the amplitudes of the audio signals collected by the audio collecting module in various blocking modes are respectively obtained. Calculating an average of the amplitudes of the acquired audio signals to obtain a preset amplitude threshold.
  • the audio signal of the user's voice call is collected by the audio collection module, and the amplitude value of the audio signal during the voice call of the user is calculated. By comparing the amplitude value of the audio signal and the preset amplitude threshold value during the voice call of the user, the voice call of the user is determined. Whether the amplitude value of the audio signal is less than the preset vibration The amplitude threshold is determined by determining whether the amplitude value of the audio signal collected by the audio collection module is less than a preset amplitude threshold.
  • the low-frequency signal energy is relatively strong, the high-frequency signal energy is relatively weak; when the sound-receiving hole is blocked, most of the low-frequency signal can be collected by the audio collection module through the sound hole through the gap or shell resonance mode; but most of the high-frequency signals cannot be The sound collecting hole is collected by the audio collecting module; therefore, when the sound collecting hole is blocked, the audio signal collected by the audio collecting module is mainly a low frequency signal.
  • a preset condition ie, an audio signal having a frequency higher than a preset frequency point
  • Step 103 If the amplitude value of the audio signal is less than the preset amplitude threshold and/or the energy distribution of the audio signal does not satisfy the preset condition, it is determined that the electronic device sound hole is blocked or the electronic device voice input is abnormal.
  • the prompt information is output, and is used to prompt the user that the electronic device voice input is abnormal.
  • the electronic device adjusts the audio collection module that collects the audio signal according to the number of audio collection modules that are set by itself;
  • the electronic device When it is determined that the electronic device includes at least two audio collection modules and is currently using the first audio collection module;
  • the second audio collection module is enabled to acquire an audio signal; wherein the second audio collection module is any audio acquisition module of the electronic device other than the first audio collection module.
  • the first audio collection module is turned off.
  • the second audio collection module when the second audio collection module is selected from the plurality of audio collection modules, the second audio collection module may be selected according to the priority of the plurality of audio collection modules preset in advance (the second The audio collection module is the highest priority among the plurality of audio collection modules except the first audio collection module.
  • the electronic device when the electronic device has multiple sound collecting holes (for example, the electronic device includes three sound collecting holes: the sound collecting hole a, the sound receiving hole b, and the sound collecting hole c), when the audio signal is collected through the sound collecting hole a and the sound receiving hole a is blocked, and The current electronic device collects an audio signal through an audio collection module corresponding to the sound receiving hole a.
  • the electronic device can enable the audio collection module corresponding to the sound receiving hole b or the sound receiving hole c to collect the audio signal, and close the corresponding sound hole a.
  • the audio acquisition module collects audio signals.
  • the mobile phone is provided with one Mic or multiple Mic
  • the electronic device adjusts the audio collection module for collecting the audio signal according to the number of the audio collection modules set by the electronic device.
  • the specific implementation is explained:
  • the Mic hole is the sound collecting hole of the embodiment of the present invention
  • the Mic is the audio collecting module of the embodiment of the present invention:
  • the Mic hole used in the current call is blocked and lasts for more than 3 seconds, and the mobile phone Mic array is detected to determine that the mobile phone has several Mic;
  • the Mic hole is blocked by the prompt tone, text or vibration;
  • the mobile phone has at least two Mic (for example, three Mic, respectively, the main Mic, the secondary Mic, and the third Mic), and the current call uses the main Mic, when the main Mic hole is detected to be blocked, according to the preset priority. Select the remaining Mic except the main Mic to make a call.
  • the priority can be based on each Mic.
  • the quality of the set audio signal is determined; for example, the main Mic priority > the secondary Mic > the third Mic, etc., when the main Mic hole is blocked, the secondary Mic with the highest priority except the main Mic is preferentially activated to acquire the audio signal.
  • the audio is The parameters are switched to audio parameters that are adapted to the secondary Mic.
  • the Mic hole is blocked by a prompt tone, a text, or a vibration.
  • the method provided by the embodiment of the present invention comprehensively judges the time domain and the frequency domain characteristic of the collected audio signal, and determines whether the voice input is abnormal according to the determination result.
  • the problem that the sound collecting hole of the audio collecting module in the prior art is blocked and the audio collecting is invalid is solved.
  • Mic input amplitude and input frequency combined for comprehensive detection method can effectively improve the detection accuracy of Mic input anomaly.
  • the method provided by the embodiment of the present invention after determining that the voice input of the electronic device is abnormal, notifying the user that the voice input of the electronic device is abnormal by using the prompt information, thereby reducing the trouble of abnormal voice input when the user uses the device, and improving the user. feeling of using;
  • the method provided by the embodiment of the present invention automatically restores the voice input of the electronic device after determining the voice input abnormality of the electronic device, and reduces the voice input of the electronic device by using the fault-tolerant avoidance method.
  • the abnormality caused the device to be unable to effectively capture the impact of voice input data.
  • an embodiment of the present invention provides an electronic device, where the electronic device specifically includes:
  • the audio collection module 201 is configured to collect an audio signal.
  • the audio collection module may be a specific structure having an audio collection function such as Mic.
  • a memory 202 configured to store an instruction
  • a processor 203 configured to invoke an instruction stored in the memory 202 to implement determining the tone Whether the amplitude value of the audio signal collected by the frequency acquisition module is less than a preset amplitude threshold, and/or whether the energy distribution of the audio signal satisfies a preset condition; if the amplitude value of the audio signal is less than a preset amplitude threshold and/or If the energy distribution of the audio signal does not satisfy the preset condition, it is determined that the voice input of the electronic device is abnormal.
  • the processor invokes the instructions stored in the memory to implement the implementation of the foregoing method embodiments. Therefore, the implementation of the electronic device may refer to the implementation of the method, and the repeated description is not repeated.
  • the embodiment of the present invention is applicable to the terminal device, and the specific implementation structure of the terminal (or terminal device) 300 may include:
  • Input and output modules including audio output module 318, audio input module 316 and display 320, etc.
  • user interface 302 processor 304, transceiver (which may be an independent module that integrates transceiver functions, or may be transmitter 306 and receiver 308) Combinedly formed), coupler 310, antenna 314, and memory 312.
  • transceiver which may be an independent module that integrates transceiver functions, or may be transmitter 306 and receiver 308 Combinedly formed
  • coupler 310 which may be an independent module that integrates transceiver functions, or may be transmitter 306 and receiver 308 Combinedly formed
  • coupler 310 antenna 314, and memory 312.
  • the antenna 314 is configured to convert electromagnetic energy in the transmission line into electromagnetic waves in free space, or convert electromagnetic waves in free space into electromagnetic energy in the transmission line;
  • the coupler 310 is configured to divide the mobile communication signal into multiple channels and distribute the signals to multiple Receiver 308.
  • the transmitter 306 is configured to perform a transmission process (eg, modulation) on the mobile communication signal generated by the processor 304
  • the receiver 308 is configured to perform a reception process (eg, demodulation) on the mobile communication signal received by the antenna 314, which may be regarded as one.
  • Wireless modem e.g., the number of transmitters 306 or receivers 308 may be one or more.
  • the input and output module is mainly used to implement the interaction between the user equipment 300 and the user/external environment.
  • the inter-function mainly includes an audio output module 318, an audio input module 316, and a display 320.
  • the input and output module may further include: a camera, a touch screen, a sensor, and the like.
  • the input and output modules communicate with the processor 304 through the user interface 302.
  • Memory 312 is coupled to processor 304 for storing one or more programs, the one or more programs including instructions.
  • memory 312 can include high speed random access memory, and can also include non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state storage devices.
  • the audio input module uses the audio input module 316 as an example to collect an audio signal in an environment where the electronic device is currently located;
  • the processor 304 is mainly used to call the instructions stored in the memory 312, and performs the following steps:
  • the voice input of the electronic device is abnormal.
  • the processor invokes the instructions stored in the memory to implement the implementation of the foregoing method embodiments. Therefore, the implementation of the terminal may refer to the implementation of the method, and the repeated description is omitted.
  • an embodiment of the present invention provides an apparatus.
  • the apparatus provided by the embodiment of the present invention may be integrated into a terminal or an electronic device, where the terminal or the electronic device includes at least an audio collection module.
  • the apparatus provided by the embodiment of the present invention may be an integral part of the processor illustrated in FIG. 2 or FIG. 3, and the apparatus includes:
  • the comparison module 401 is configured to compare whether the amplitude value of the audio signal collected by the audio collection module is less than a preset amplitude threshold, and/or compare the ratio of the high frequency energy value to the low frequency energy value of the audio signal collected by the audio collection module. Preset threshold
  • the determining module 402 is configured to determine that the voice input of the electronic device is abnormal if the amplitude value of the audio signal is less than a preset amplitude threshold and/or the energy distribution of the audio signal does not satisfy the preset condition.
  • the determining module 402 may specifically include:
  • a first determining submodule configured to determine an amplitude value of the audio signal collected by the audio collecting module
  • a second determining submodule configured to perform Fourier frequency domain conversion on the audio signal, determining a high frequency energy value and a low frequency energy value of the audio signal; and an energy value of the audio signal having a frequency higher than a preset frequency point As a high frequency energy value, the energy value of the audio signal having a frequency lower than the preset frequency point is summed as a low frequency energy value;
  • the comparison module compares whether the amplitude value of the audio signal collected by the audio collection module is less than a preset amplitude threshold, and/or compares the ratio of the high frequency energy value and the low frequency energy value of the audio signal collected by the audio collection module.
  • the device further includes a detection module before being less than a preset threshold; wherein:
  • the detecting module is configured to detect whether a voice path is established; if it is detected that the voice path is established, compare whether the amplitude value of the audio signal collected by the audio collecting module is less than a preset amplitude threshold, and/or the comparison audio collecting module collects Whether the ratio of the high frequency energy value to the low frequency energy value of the audio signal is less than a preset threshold.
  • the device further includes:
  • an output module configured to output prompt information, where the prompt information is used to prompt the user that the electronic device voice input is abnormal.
  • the adjustment module is specifically configured to determine a first audio collection module that is currently used; and enable the second audio collection module of the multiple audio collection modules to acquire An audio signal; wherein the second audio collection module is the plurality of Any audio acquisition module other than the first audio collection module in the audio collection module.
  • a computer readable storage medium storing program code for implementing the method for determining a voice input exception described in the first aspect, the program code comprising operating the first aspect An execution instruction for a method of determining a voice input exception.
  • an embodiment of the present invention further provides a non-volatile computer readable storage medium storing one or more programs, where the one or more programs include instructions, when the instructions are provided with an audio collection module.
  • the electronic device executes the determining method of the voice input abnormality described in Embodiment 1 when the electronic device is executed.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
  • the method and device provided by the embodiments of the present invention comprehensively determine the time domain and frequency domain characteristics of the collected audio signal, and determine whether the voice input is abnormal according to the determination result.
  • the problem that the sound collecting hole of the audio collecting module in the prior art is blocked and the audio collecting is invalid is solved.
  • Mic input amplitude and input frequency combined for comprehensive detection method can effectively improve the detection accuracy of Mic input anomaly.
  • the solution of the invention proposes a fault-tolerant avoidance method after detecting an abnormality of the Mic input, which can reduce the influence of the Mic input abnormality that the device cannot effectively collect the voice input data.
  • the solution of the present invention also proposes a user interaction mode after detecting an abnormal Mic input, which reduces the trouble of abnormal voice input when the user uses the device, and improves the user experience.
  • the computer program instructions can also be stored in a non-transitory computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the generation of instructions stored in the computer readable memory includes the manufacture of the instruction device.
  • the instruction means implements the functions specified in a block or blocks of a flow or a flow and/or a block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Otolaryngology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Telephone Function (AREA)

Abstract

一种语音输入异常的确定方法、装置、终端以及存储介质，该方法应用于具有音频采集模块的电子设备，包括：确定所述音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。本发明提供的方案解决现有技术对于电子设备收音孔被堵塞导致的收音不正常则没有有效的确定方法的问题。

Description

一种语音输入异常的确定方法、装置、终端以及存储介质 技术领域
本发明涉及电子技术领域，尤其涉及一种语音输入异常的确定方法、装置、终端以及存储介质。
背景技术
随着电子技术的发展和消费者需求的增多，越来越多的电子产品问世，例如智能手机，平板电脑。这些电子设备为用户的生活和工作带来了极大的便利。通常这些电子设备都提供音频采集功能，采集音频信号。
现有技术中，为了防止手机外壳对音频信号的阻隔，达到好的收音效果，一般会在电子设备的外壳设置一个小孔作为音频采集模块的收音孔，该收音孔与音频采集模块连接。但是因为电子设备所处的环境复杂，所以很多时候会出现收音孔堵塞影响音频采集模块采集声音信息。现有一些对语音进行检测的方法，只能检测采集到的音频信号的算法是否正常，对于电子设备收音孔被堵塞导致的收音不正常则没有有效的检测方法，也无法针对收音异常提示用户或提供补救措施，影响用户体验。
发明内容
本发明提供一种语音输入异常的确定方法、装置、终端以及存储介质，本发明所提供的方法和装置解决现有技术对于电子设备收音孔被堵塞导致的收音不正常则没有有效的确定方法，也无法针对收音异常提示用户或提供补救措施，影响用户体验的问题。
第一方面，提供一种语音输入异常的确定方法，应用于具有音频采集模块的电子设备，包括：
确定所述音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；
如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
针对收音孔被堵塞会导致音频采集模块不能正常采集到音频信号，从而会导致采集到的音频信号在时域和频域的特性都出现异常，本发明实施例所提供的方案，通过对采集到音频信号的时域(音频的振幅)和频域(频点的能量值)特性进行综合判断，根据判断结果确定语音输入是否异常。并且Mic输入幅值与输入频率结合进行综合检测的方法，能够有效提升Mic输入异常的检测精度.
在一般情况下用户在握持移动终端时为了支撑效果更好也会将手指托着移动终端的底部，所以在这种情况下很容易出现手指堵塞收音孔的情况，从而造成通话送话无声的问题。所针对这种情况：
本发明事实还提供一种可能的设计，确定所述音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件之前：
检测是否建立了语音通路，如果检测到建立了语音通路，则确定所述音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件。
在该种可能的设计中，只有在检测到电子设备建立了语音通路，才进行振幅以及能量的判断，从而能够达到解决通话送话无声的问题，并且达到省电的效果。
另外一种可能的设计，确定所述音频信号的能量分布是否满足预设条件包括：
对所述音频信号进行傅里叶频域转换，确定所述音频信号的能量值；
将频率高于预设频点的音频信号的能量值求和作为高频能量值，将频率低于所述预设频点的音频信号的能量值求和作为低频能量值；
判断所述高频能量值与所述低频能量值的比值是否小于预设阈值，如果所述高频能量值与所述低频能量值的比值小于预设阈值，则确定所述音频信号的能量分布不满足所述预设条件。
因为收音孔堵塞会导致音频信号中各频点的能量值受到影响，所以基于收音孔堵塞的该特性，所以在该可能的设计中，在对音频信号进行傅里叶频域转换得到各频点的能量值，从而可以根据各频点的能量值更有针对性的判断出电子设备的收音孔是否堵塞。
通过上述方式确定电子设备的收音孔出现问题，对应的可以通过以下方式提供对应的解决方式，确定所述电子设备语音输入异常之后，该方法进一步包括：
调整采集音频信号的音频采集模块；或者
输出提示信息；其中，所述提示信息用于提示用户所述电子设备语音输入异常。
另外一种可能的设计中，当所述电子设备包括多个音频采集模块时，当所述电子设备包括多个音频采集模块时，所述调整采集音频信号的音频采集模块，包括：
确定当前使用的第一音频采集模块；
启用所述多个音频采集模块中的第二音频采集模块采集音频信号；其中，所述第二音频采集模块是所述多个音频采集模块中除所述第一音频采集模块外的任意音频采集模块。
通过本发明实施例的方案，在确定收音孔出现问题后，可以通过上述方式及时有效的提供解决方案，启用其他音频采集模块进行收音或者通知用户， 使得用户能够尽快对问题进行解决。
另外一种可能的设计中，通过以下方式获取预设振幅阈值，包括：
根据收音孔堵塞时，多次采集到的采集音频信号得到预设振幅阈值；
进一步的实现可以是：通过采集具有不同声波特性的音频信号得到预设振幅阈值；或者
采集不同堵塞方式堵塞收音孔时，音频采集模块所采集到的音频信号的振幅值，计算所获取的音频信号的振幅值的平均值得到预设振幅阈值。
在该种可能的设计中，采集各种场景下的音频信号作为计算预设振幅阈值的基础，从而使得预设振幅阈值能更准确的适应不同的场景，从而减小对电子设备语音输入异常判断的失误。
另外一种可能的设计中，在启用第二音频采集模块采集音频信号包括：
确定电子设备中设置的多个音频采集模块的优先级，根据该优先级由高到低的原则从多个音频采集模块中作为所述第二音频采集模块。
在该种可能的设计中，提供从多个音频采集模块选择第二音频采集模块的具体实现方式，能够在电子设备的语音输入异常后提供具体的容错规避方法，可以降低Mic输入异常造成设备无法有效采集语音输入数据的影响。
第二方面，提供一种电子设备，包括：
音频采集模块，用于采集音频信号；
存储器，用于存储指令；
处理器，用于调用存储在所述存储器中的指令以实现确定所述音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
所述处理器调用存储在所述存储器中的指令以实现上述第一方面的方法设计中的方案，由于该电子设备解决问题的实施方式以及有益效果可以参见上述第一方面和第一方面的各可能的实施方式以及有益效果，因此该电子设备的实施可以参见方法的实施，重复之处不再赘述。
第三方面，提供了一种装置，该装置设置于电子设备中，该电子设备至少包括音频采集模块，该装置包括：
比较模块，用于确定所述音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；
确定模块，用于如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
基于同一发明构思，由于该装置解决问题的原理以及有益效果可以参见上述第一方面和第一方面的各可能的实施方式以及所带来的有益效果，因此该装置的实施可以参见方法的实施，重复之处不再赘述。
第四方面，提供了一种存储一个或多个程序的非易失性计算机可读存储介质，所述一个或多个程序包括指令，所述指令当被具有音频采集模块的电子设备执行时使所述电子设备执行上述第一方面和第一方面的个可能的实施方式。
基于同一发明构思，由于非易失性计算机可读存储介质所存储的程序当被具有音频采集模块的电子设备执行时所解决的问题的原理以及有益效果可以参见上述第一方面和第一方面的各可能的实施方式以及所带来的有益效果，因此该非易失性计算机可读存储介质的实施可以参见方法的实施，重复之处不再赘述。
上述技术方案中的一个多种可能方式的结合，至少具有如下技术效果：
本发明实施例提供的方法和装置，通过对采集到音频信号的时域和频域特性进行综合判断，根据判断结果确定语音输入是否异常。解决了现有技术对于电子设备收音孔被堵塞导致的收音不正常则没有有效的确定方法，也无法针对收音异常提示用户或提供补救措施，影响用户体验的问题。
附图说明
图1为本发明实施例提供的一种电子设备语音输入异常的确定方法的流程示意图；
图2为本发明实施例提供的一种电子设备的的结构示意图；
图3为本发明实施例提供的一种终端设备的结构示意图；
图4为本发明实施例提供的一种装置的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
因为现有语音检测的方法只能检测采集到的音频信号在语音算法本身是否存在问题，但是对于音频采集模块(例如：Mic)采集数据的有效性和准确性都没有合适的判断方法。为了方便麦克风采集音频信号，在电子设备外壳上开设收音孔，该收音孔连接音频采集模块；由于收音孔通常布置在手机外壳上，当用户手持电子设备或电子设备周边有物体时，收音孔可能会被堵塞，进而影响音频采集模块采集音频信号的准确性，例如：麦克风拾音声音小或 无声；针对类似问题，一直没有很好的改善措施，所以本发明提供一种电子设备语音输入异常的确定方法以改善上述问题，下面结合说明书附图对本发明实施例作进一步详细描述。
实施例一
如图1所示，本发明实施例提供一种语音输入异常的确定方法，应用于具有音频采集模块的电子设备，该方法具体包括：
在本发明实施例所提供的方法可以适用于所有设置有音频采集模块(具体实现可以是麦克风)的电子设备，电子设备通过音频采集模块采集声音信息，并将声音信息转换为模拟音频信号；在电子设备外壳上开设收音孔，该收音孔连接音频采集模块。为了达到更好的收音效果，一般会把收音孔设置在移动终端的底部，但是一般情况下用户在握持移动终端时为了支撑效果更好也会将手指托着移动终端的底部，所以在这种情况下很容易出现手指堵塞收音孔的情况，从而造成通话送话无声的问题。
步骤101：确定音频采集模块采集到的音频信号的振幅以及该音频信号的能量分布；
优选地，为了解决通话送话无声的问题，并且达到省电的效果，在确定所述音频信号的振幅是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件之前，检测是否建立了语音通路，如果检测到建立了语音通路，则确定所述音频信号的振幅是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件。
音频信号的振幅值可以通过以下方法确定：采样单位周期内的音频信号，得到音频信号的采样值，计算音频信号的采样值的振幅的绝对值，计算多个采样值的振幅的绝对值的平均值，得到音频信号的采样值的振幅的平均值，该平均值为音频信号的振幅值。
如下步骤102～步骤103详细介绍通过对采集到的音频信号的时域特性和频域特性进行综合判断，确定所述电子设备语音输入是否异常。
步骤102：确定音频采集模块采集到的音频信号的振幅是否小于预设振幅阈值，和/或该音频信号的能量分布是否满足预设条件；
一，对音频采集模块采集到的音频信号进行时域分析，确定音频采集模块采集到的音频信号的振幅是否小于预设振幅阈值：
如果收音孔被堵塞则会导致音频采集模块收集到的音频信号的振幅大幅降低，可能小于预设振幅阈值。
优选的，当确定音频采集模块采集到的音频信号的振幅小于预设振幅阈值时，确定音频采集模块采集到的音频信号的振幅小于预设振幅阈值时的持续时长是否大于预设时长，预设时长可以根据设计需要动态设置。
可以根据实验获取本发明实施例的预设振幅阈值，即：将收音孔堵塞，收音孔被堵塞时采集音频信号，收音孔被堵塞时采集到的音频信号的振幅即为预设振幅阈值。可选的，可以将收音孔堵塞后，多次采集音频信号，获取多次采集到的音频信号的振幅的平均值，将得到的平均值作为预设振幅阈值。作为一种实施方式，当通过多次采集音频信号得到预设振幅阈值时，可以通过采集具有不同声波特性的音频信号(例如男声，女声，老人，儿童等)得到预设振幅阈值。作为一种实施方式，可以通过不同堵塞方式堵塞收音孔(如，不同堵塞角度，利用不同物体堵塞收音孔等)，分别获取音频采集模块在各种不同堵塞方式下所采集到的音频信号的振幅，计算所获取的音频信号的振幅的平均值得到预设振幅阈值。
通过音频采集模块采集用户语音通话的音频信号，计算用户语音通话时的音频信号的振幅值，通过比较用户语音通话时的音频信号的振幅值与预设振幅阈值的大小，确定用户语音通话时的音频信号的振幅值是否小于预设振 幅阈值，即：确定音频采集模块采集到音频信号的振幅值是否小于预设振幅阈值。
二，对音频采集模块采集的音频信号进行频域分析，确定音频信号的能量分布是否满足预设条件：
因为低频信号能量相对强，高频信号能量相对弱；当收音孔被堵塞时，大部分低频信号可以通过缝隙或壳体共振方式通过收音孔被音频采集模块采集到；但大部分高频信号无法通过收音孔被音频采集模块采集到；因此当收音孔被堵塞时，音频采集模块所采集到的音频信号主要是低频信号。
对所采集到的音频信号进行傅里叶FFT转换后得到音频信号的能量分布，通过判断采集到的音频信号的能量分布是否满足预设条件(即：将频率高于预设频点的音频信号的能量值求和作为高频能量值，将频率低于所述预设频点的音频信号的能量值求和作为低频能量值；判断高频能量值与所述低频能量值的比值是否小于预设阈值，如果高频能量值与所述低频能量值的比值小于预设阈值，则确定音频信号的能量分布不满足预设条件)。
步骤103，如果该音频信号的振幅值小于预设振幅阈值和/或该音频信号的能量分布不满足预设条件，则确定电子设备收音孔被堵塞或电子设备语音输入异常。
当确定电子设备收音孔被堵塞之后，可以通过以下方式处理，具体包括：
作为一种处理方式，输出提示信息，用于提示用户电子设备语音输入异常。
作为另一种处理方式，电子设备根据自身设置的音频采集模块的数量对采集音频信号的音频采集模块进行调整；包括：
当确定电子设备包括至少两个音频采集模块且当前使用的是第一音频采集模块时；
启用第二音频采集模块采集音频信号；其中，第二音频采集模块是电子设备中除第一音频采集模块外的任意音频采集模块。
可选的，为了减少电子设备的功耗，在启用第二音频采集模块采集音频信号后，关闭第一音频采集模块。并且该实施例中，从多个音频采集模块中选择第二音频采集模块时，可以根据预先设置的多个音频采集模块的优先级由高到低的顺序选择第二音频采集模块(该第二音频采集模块是多个音频采集模块中除第一音频采集模块外优先级最高的)。
例如：当电子设备有多个收音孔(例如：电子设备包括三个收音孔：收音孔a、收音孔b、收音孔c)，当通过收音孔a采集音频信号且收音孔a被堵塞，而且当前电子设备是通过与收音孔a对应的音频采集模块采集音频信号的，电子设备可以启用与收音孔b或者收音孔c对应的音频采集模块进行音频信号的采集，并关闭与收音孔a对应的音频采集模块采集音频信号。
为了更清楚详细的说明本发明实施例的方法，下面以手机设置有一个Mic或多个Mic为例，对电子设备根据自身设置的音频采集模块的数量对采集音频信号的音频采集模块进行调整的具体实现进行说明：
以手机为例，Mic孔为本发明实施例的收音孔，Mic为本发明实施例的音频采集模块：
当手机通话过程中，确定当前通话所使用的Mic孔堵塞且持续时长超过3秒钟，检测手机Mic阵列，判断手机有几个Mic；
如果手机只有一个Mic，则通过提示音、文字或震动等方式提醒用户Mic孔被堵；
如果手机具有至少两个Mic(例如，三个Mic，分别为主Mic，副Mic，第三Mic)，且当前通话使用主Mic，当检测到主Mic孔堵塞时，则根据预设的优先级选择除主Mic外的其余Mic进行通话，该优先级可以根据各Mic采 集音频信号的质量确定；例如：主Mic优先级>副Mic>第三Mic等，可以当主Mic孔堵塞时，优先启动除主Mic外优先级最高的副Mic采集音频信号，优选的，将音频参数切换为与副Mic适配的音频参数。
作为一种可选实施方式，当手机具有至少两个Mic且检测到当前通话所使用的Mic孔堵塞时，通过提示音、文字或震动等方式提醒用户Mic孔被堵。
本发明实施例提供的方法，通过对采集到的音频信号的时域和频域特性进行综合判断，根据判断结果确定语音输入是否异常。解决了现有技术中音频采集模块的收音孔被堵塞从而造成音频采集无效的问题。并且Mic输入幅值与输入频率结合进行综合检测的方法，能够有效提升Mic输入异常的检测精度。
本发明实施例提供的方法，在确定所述电子设备的语音输入异常后，利用输出提示信息的方式通知用户电子设备语音输入异常，降低了用户使用设备时出现语音输入异常的困扰，提升了用户使用感受；
另外，本发明实施例提供的方法，在确定所述电子设备的语音输入异常后，自动调整采集音频信号的音频采集模块的方式恢复电子设备的语音输入；通过该容错规避方法，可以降低Mic输入异常造成设备无法有效采集语音输入数据的影响。
实施例二
如图2所示，本发明实施例提供一种电子设备，该电子设备具体包括：
音频采集模块201，用于采集音频信号；
在具体的应用环境中，该音频采集模块可以是Mic等具有音频采集功能的具体结构。
存储器202，用于存储指令；
处理器203，用于调用存储在所述存储器202中的指令以实现确定所述音 频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
所述处理器调用存储在所述存储器中的指令以实现上述方法实施例的实施方式，因此该电子设备的实施可以参见方法的实施，重复之处不再赘述。
实施例三
如图3所示，本发明是实施例所提供的音频采集检测方式可以应用到终端设备，则本发明实施例还提供一种终端(或称为终端设备)300的具体实现结构可包括：
输入输出模块(包括音频输出模块318、音频输入模块316以及显示器320等)、用户接口302、处理器304、收发器(可以是集成收发功能的独立模块，也可以是发射器306和接收器308组合形成)、耦合器310、天线314以及存储器312。在本发明的一些实施例中，这些部件可通过总线或者其它方式连接，其中，图3中以通过总线连接为例。
其中：
天线314用于将传输线中的电磁能转换成自由空间中的电磁波，或者将自由空间中的电磁波转换成传输线中的电磁能；耦合器310用于将移动通信号分成多路，分配给多个的接收器308。
发射器306用于对处理器304生成的移动通信信号进行发射处理(例如调制)，接收器308用于对天线314接收的移动通信信号进行接收处理(例如解调)，二者可看作一个无线调制解调器。具体实现中，发射器306或接收器308的数量可以是一个或多个。
所述输入输出模块主要用于实现用户设备300和用户/外部环境之间的交 互功能，主要包括音频输出模块318、音频输入模块316以及显示器320等。具体实现中，所述输入输出模块还可包括：摄像头、触摸屏以及传感器等等。其中，所述输入输出模块均通过用户接口302与处理器304进行通信。
存储器312与处理器304耦合，用于存储一个或多个程序，所述一个或多个程序包括指令。具体实现中，存储器312可包括高速随机存取的存储器，并且也可包括非易失性存储器，例如一个或多个磁盘存储设备、闪存设备或其他非易失性固态存储设备。
在本发明实施例中，音频采集模块以音频输入模块316为例，用于采集电子设备当前所处环境中的音频信号；
处理器304主要用于调用存储于存储器312中的指令，并执行如下步骤：
确定所述音频输入模块316采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；
如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
所述处理器调用存储在所述存储器中的指令以实现上述方法实施例的实施方式，因此该终端的实施可以参见方法的实施，重复之处不再赘述。
实施例四
如图4所示，本发明实施例提供一种装置，本发明实施例提供的装置可以集成在终端或电子设备中，其中，该终端或电子设备至少包括音频采集模块；作为一种实施方式，本发明实施例提供的装置可以是图2或图3示例的处理器的组成部分，该装置包括：
比较模块401，用于比较音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或比较音频采集模块采集到的音频信号的高频能量值与低频能量值的比值是否小于预设阈值；
确定模块402，用于如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
其中，该确定模块402具体可以包括：
第一确定子模块，用于确定所述音频采集模块采集到的音频信号的振幅值；
第二确定子模块，用于对所述音频信号进行傅里叶频域转换，确定所述音频信号的高频能量值和低频能量值；将频率高于预设频点的音频信号的能量值求和作为高频能量值，将频率低于所述预设频点的音频信号的能量值求和作为低频能量值；
可选的，在比较模块比较音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或比较音频采集模块采集到的音频信号的高频能量值与低频能量值的比值是否小于预设阈值之前，该装置还包括检测模块；其中：
该检测模块，用于检测是否建立了语音通路；如果检测到建立了语音通路，则比较音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或比较音频采集模块采集到的音频信号的高频能量值与低频能量值的比值是否小于预设阈值。
可选的，该装置还包括：
调整模块，用于调整采集音频信号的音频采集模块；
输出模块，用于输出提示信息；其中，所述提示信息用于提示用户所述电子设备语音输入异常。
可选的，当所述终端或电子设备包括多个音频采集模块，则调整模块具体用于确定当前使用的第一音频采集模块；启用所述多个音频采集模块中的第二音频采集模块采集音频信号；其中，所述第二音频采集模块是所述多个 音频采集模块中除所述第一音频采集模块外的任意音频采集模块。第四方面，提供了一种计算机可读存储介质，所述可读存储介质上存储有实现第一方面描述的用于语音输入异常的确定的方法的程序代码，该程序代码包含运行第一方面描述的用于语音输入异常的确定的方法的执行指令。
基于同一发明构思，由于该装置解决问题的原理可以参见本发明方法实施例的实施方式，重复之处不再赘述。
可选的，本发明实施例还提供一种存储一个或多个程序的非易失性计算机可读取存储介质，所述一个或多个程序包括指令，所述指令当被具有音频采集模块的电子设备执行时使所述电子设备执行实施例一所述的语音输入异常的确定方法。
基于同一发明构思，由于该非易失性计算机可读取存储介质解决问题的原理可以参见本发明方法实施例一的实施方式，重复之处不再赘述。
另外，本领域普通技术人员可以理解实现上述实施例方法中的部分或全部流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
本申请实施例中的上述一个或多个技术方案，至少具有如下的技术效果：
本发明实施例提供的方法和装置，通过对采集到音频信号的时域和频域特性进行综合判断，根据判断结果确定语音输入是否异常。解决了现有技术中音频采集模块的收音孔被堵塞从而造成音频采集无效的问题。并且Mic输入幅值与输入频率结合进行综合检测的方法，能够有效提升Mic输入异常的检测精度。
本发明方案提出了检测到Mic输入异常后的容错规避方法，可以降低Mic输入异常造成设备无法有效采集语音输入数据的影响。
另外，本发明方案还提出了检测到Mic输入异常后的用户交互方式，降低了用户使用设备时出现语音输入异常的困扰，提升了用户使用感受。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的非易失性计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。

Claims (12)

  1. 一种语音输入异常的确定方法，应用于具有音频采集模块的电子设备，其特征在于，包括：
    确定所述音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；
    如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
  2. 如权利要求1所述的方法，其特征在于，确定所述音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件之前：
    检测是否建立了语音通路，如果检测到建立了语音通路，则确定所述音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件。
  3. 如权利要求1或2所述的方法，其特征在于，确定所述音频信号的能量分布是否满足预设条件包括：
    对所述音频信号进行傅里叶频域转换，确定所述音频信号的能量值；
    将频率高于预设频点的音频信号的能量值求和作为高频能量值，将频率低于所述预设频点的音频信号的能量值求和作为低频能量值；
    判断所述高频能量值与所述低频能量值的比值是否小于预设阈值，如果所述高频能量值与所述低频能量值的比值小于预设阈值，则确定所述音频信号的能量分布不满足所述预设条件。
  4. 如权利要求1～3任一所述的方法，其特征在于，确定所述电子设备语音输入异常之后，该方法进一步包括：
    调整采集音频信号的音频采集模块；或者
    输出提示信息；其中，所述提示信息用于提示用户所述电子设备语音输入异常。
  5. 如权利要求4所述的方法，其特征在于，当所述电子设备包括多个音频采集模块时，所述调整采集音频信号的音频采集模块，包括：
    确定当前使用的第一音频采集模块；
    启用所述多个音频采集模块中的第二音频采集模块采集音频信号；其中，所述第二音频采集模块是所述多个音频采集模块中除所述第一音频采集模块外的任意音频采集模块。
  6. 一种电子设备，其特征在于，包括音频采集模块、存储器、处理器：
    音频采集模块，用于采集音频信号；
    存储器，用于存储指令；
    处理器，用于调用存储在所述存储器中的指令以实现确定所述音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件；如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
  7. 如权利要求6所述的电子设备，其特征在于，所述处理器还用于检测是否建立了语音通路，如果检测到建立了语音通路，则确定所述音频信号的振幅值是否小于预设振幅阈值，和/或所述音频信号的能量分布是否满足预设条件。
  8. 如权利要求6或7所述的电子设备，其特征在于，所述处理器判断所述音频信号中各频点所对应的能量是否满足预设条件包括：
    对所述音频信号进行傅里叶频域转换，确定所述音频信号的能量值；
    将频率高于预设频点的音频信号的能量值求和作为高频能量值，将频率 低于所述预设频点的音频信号的能量值求和作为低频能量值；
    判断所述高频能量值与所述低频能量值的比值是否小于预设阈值，如果所述高频能量值与所述低频能量值的比值小于预设阈值，则确定所述音频信号的能量分布不满足所述预设条件。
  9. 如权利要求6～8任一所述的电子设备，其特征在于，所述处理器还用于调整采集音频信号的音频采集模块；或者输出提示信息；其中，所述提示信息用于提示用户所述电子设备语音输入异常。
  10. 如权利要求9所述的电子设备，其特征在于，所述电子设备包括多个音频采集模块，则所述处理器根据电子设备所设置的音频采集模块的数量对采集音频信号的音频采集模块进行调整包括：
    确定当前使用的第一音频采集模块；
    启用所述多个音频采集模块中的第二音频采集模块采集音频信号；其中，所述第二音频采集模块是所述多个音频采集模块中除所述第一音频采集模块外的任意音频采集模块。
  11. 一种装置，其特征在于，该装置设置于电子设备中，该电子设备至少包括音频采集模块，该装置包括：
    比较模块，用于比较音频采集模块采集到的音频信号的振幅值是否小于预设振幅阈值，和/或比较音频采集模块采集到的音频信号的高频能量值与低频能量值的比值是否小于预设阈值；
    确定模块，用于如果所述音频信号的振幅值小于预设振幅阈值和/或所述音频信号的能量分布不满足所述预设条件，则确定所述电子设备的语音输入异常。
  12. 一种存储一个或多个程序的非易失性计算机可读取存储介质，其特征在于，所述一个或多个程序包括指令，所述指令当被具有音频采集模块的 电子设备执行时使所述电子设备执行权利要求1至权利要求5所述的语音输入异常的确定方法。
PCT/CN2016/080716 2016-04-29 2016-04-29 一种语音输入异常的确定方法、装置、终端以及存储介质 WO2017185342A1 (zh)

Priority Applications (8)

Application Number Priority Date Filing Date Title
BR112017021239-0A BR112017021239B1 (pt) 2016-04-29 2016-04-29 Método, aparelho, e meio legível por computador de determinação de exceção de entrada de voz
US15/574,405 US10231070B2 (en) 2016-04-29 2016-04-29 Voice input exception determining method, apparatus, terminal, and storage medium
EP16895743.9A EP3301950B1 (en) 2016-04-29 2016-04-29 Method and apparatus for determining voice input anomaly, terminal, and storage medium
AU2016402256A AU2016402256B2 (en) 2016-04-29 2016-04-29 Voice input exception determining method, apparatus, terminal, and storage medium
CN201680025187.8A CN107548564B (zh) 2016-04-29 2016-04-29 一种语音输入异常的确定方法、装置、终端以及存储介质
PCT/CN2016/080716 WO2017185342A1 (zh) 2016-04-29 2016-04-29 一种语音输入异常的确定方法、装置、终端以及存储介质
CA2981775A CA2981775C (en) 2016-04-29 2016-04-29 Voice input exception determining method, apparatus, terminal, and storage medium
CN202110146671.9A CN113038353B (zh) 2016-04-29 2016-04-29 一种语音输入异常的确定方法、装置、终端以及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/080716 WO2017185342A1 (zh) 2016-04-29 2016-04-29 一种语音输入异常的确定方法、装置、终端以及存储介质

Publications (1)

Publication Number Publication Date
WO2017185342A1 true WO2017185342A1 (zh) 2017-11-02

Family

ID=60160515

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/080716 WO2017185342A1 (zh) 2016-04-29 2016-04-29 一种语音输入异常的确定方法、装置、终端以及存储介质

Country Status (7)

Country Link
US (1) US10231070B2 (zh)
EP (1) EP3301950B1 (zh)
CN (2) CN113038353B (zh)
AU (1) AU2016402256B2 (zh)
BR (1) BR112017021239B1 (zh)
CA (1) CA2981775C (zh)
WO (1) WO2017185342A1 (zh)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108650595A (zh) * 2018-07-24 2018-10-12 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN108924331A (zh) * 2018-07-24 2018-11-30 Oppo（重庆）智能科技有限公司 语音拾取方法及相关产品
CN109040912A (zh) * 2018-07-24 2018-12-18 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109040937A (zh) * 2018-07-24 2018-12-18 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN109089191A (zh) * 2018-07-24 2018-12-25 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109104684A (zh) * 2018-07-26 2018-12-28 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN109121046A (zh) * 2018-07-24 2019-01-01 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109121060A (zh) * 2018-07-26 2019-01-01 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN109121042A (zh) * 2018-07-26 2019-01-01 Oppo广东移动通信有限公司 语音数据处理方法及相关产品
CN109121059A (zh) * 2018-07-26 2019-01-01 Oppo广东移动通信有限公司 扬声器堵孔检测方法及相关产品
CN109151177A (zh) * 2018-07-24 2019-01-04 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN109151701A (zh) * 2018-07-26 2019-01-04 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN111047923A (zh) * 2019-12-30 2020-04-21 深圳创维数字技术有限公司 故事机的控制方法、故事播放系统及存储介质
CN109120779B (zh) * 2018-07-24 2021-10-19 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN113543005A (zh) * 2021-07-01 2021-10-22 猫岐智能科技（上海）有限公司 音频设备检测方法及系统
CN113746976A (zh) * 2021-07-23 2021-12-03 荣耀终端有限公司 音频模块检测方法、电子设备及计算机存储介质

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2016402256B2 (en) * 2016-04-29 2019-04-18 Honor Device Co., Ltd. Voice input exception determining method, apparatus, terminal, and storage medium
GB201715824D0 (en) * 2017-07-06 2017-11-15 Cirrus Logic Int Semiconductor Ltd Blocked Microphone Detection
CN108958699B (zh) * 2018-07-24 2021-12-07 Oppo（重庆）智能科技有限公司 语音拾取方法及相关产品
CN109151696A (zh) * 2018-07-26 2019-01-04 Oppo广东移动通信有限公司 堵孔检测方法及相关产品
CN109121035B (zh) * 2018-08-30 2020-10-09 歌尔科技有限公司 耳机异常处理方法、耳机、系统及存储介质
KR102652553B1 (ko) 2019-02-08 2024-03-29 삼성전자 주식회사 전자 장치 및 전자 장치의 마이크로폰 블록 검출 방법
CN110046305A (zh) * 2019-04-23 2019-07-23 江西财经大学 一种人工智能深度学习的方法
CN111918196B (zh) * 2019-05-08 2022-04-19 腾讯科技（深圳）有限公司 一种音频采集器录音异常的诊断方法、装置、设备及存储介质
CN110677780B (zh) * 2019-09-26 2021-12-14 北京小米移动软件有限公司 音频输入模组的检测方法及装置、存储介质
CN111107296B (zh) * 2019-11-26 2022-12-23 视联动力信息技术股份有限公司 音频数据采集方法、装置、电子设备及可读存储介质
CN113362850B (zh) * 2020-03-03 2024-05-28 杭州海康威视数字技术股份有限公司 音频信号采集设备的检测方法、设备和存储介质
CN111683317B (zh) * 2020-05-28 2022-04-08 江苏紫米电子技术有限公司 一种应用于耳机的提示方法、装置、终端及存储介质
CN111863032A (zh) * 2020-06-12 2020-10-30 随锐科技集团股份有限公司 音频采集设备的优选方法及系统、计算机可读存储介质
CN113286244B (zh) * 2021-05-12 2022-08-26 展讯通信（上海）有限公司 一种麦克风异常检测方法及装置
CN113611330B (zh) * 2021-07-29 2024-05-03 杭州网易云音乐科技有限公司 一种音频检测方法、装置、电子设备及存储介质
CN114264365B (zh) * 2021-12-14 2024-04-30 歌尔科技有限公司 风噪检测方法、装置、终端设备及存储介质
CN114302309B (zh) * 2021-12-16 2024-06-25 合肥联宝信息技术有限公司 一种音频采集器的检测方法及装置
CN114827821B (zh) * 2022-04-25 2024-06-11 世邦通信股份有限公司 拾音器拾音控制方法及系统、拾音器设备与存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101419795A (zh) * 2008-12-03 2009-04-29 李伟 音频信号检测方法及装置、以及辅助口语考试系统
CN102324229A (zh) * 2011-09-08 2012-01-18 中国科学院自动化研究所 语音输入设备使用异常的检测方法及系统
CN103578470A (zh) * 2012-08-09 2014-02-12 安徽科大讯飞信息科技股份有限公司 一种电话录音数据的处理方法及系统
CN105338148A (zh) * 2014-07-18 2016-02-17 华为技术有限公司 一种根据频域能量对音频信号进行检测的方法和装置

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06332492A (ja) * 1993-05-19 1994-12-02 Matsushita Electric Ind Co Ltd 音声検出方法および検出装置
JP2000214052A (ja) * 1999-01-28 2000-08-04 Nichiha Corp 異常音検出システム及び記録媒体
US6665411B2 (en) * 2001-02-21 2003-12-16 Digisonix Llc DVE system with instability detection
ATE551826T1 (de) * 2002-01-18 2012-04-15 Polycom Inc Digitale verknüpfung von mehrmikrofonsystemen
US8374362B2 (en) 2008-01-31 2013-02-12 Qualcomm Incorporated Signaling microphone covering to the user
JP4572945B2 (ja) * 2008-03-28 2010-11-04 ソニー株式会社 ヘッドフォン装置、信号処理装置、信号処理方法
US8379876B2 (en) * 2008-05-27 2013-02-19 Fortemedia, Inc Audio device utilizing a defect detection method on a microphone array
US8724829B2 (en) * 2008-10-24 2014-05-13 Qualcomm Incorporated Systems, methods, apparatus, and computer-readable media for coherence detection
DE102009046544A1 (de) * 2009-11-09 2011-05-12 Robert Bosch Gmbh Netzwerksystem für Audioeinrichtung, Verfahren und Computerprogramm
US8942386B2 (en) * 2011-11-30 2015-01-27 Midas Technology, Inc. Real-time quality monitoring of speech and audio signals in noisy reverberant environments for teleconferencing systems
US9423485B2 (en) * 2011-12-16 2016-08-23 Qualcomm Incorporated Systems and methods for predicting an expected blockage of a signal path of an ultrasound signal
US9699581B2 (en) * 2012-09-10 2017-07-04 Nokia Technologies Oy Detection of a microphone
CN102967026B (zh) * 2012-12-07 2015-04-01 四川长虹电器股份有限公司 智能空调及其控制方法
CN103297909B (zh) * 2013-04-23 2016-04-13 加一联创电子科技有限公司 一种耳机测试方法及装置
CN105359499B (zh) * 2013-07-11 2019-04-30 哈曼国际工业有限公司 用于数字音频会议工作流管理的系统和方法
CN104916292B (zh) * 2014-03-12 2017-05-24 华为技术有限公司 检测音频信号的方法和装置
CN103929707B (zh) * 2014-04-08 2019-03-01 努比亚技术有限公司 一种检测麦克风音频通道状况的方法和移动终端
CN105323363B (zh) * 2014-06-30 2019-07-12 中兴通讯股份有限公司 选择主麦克风的方法及装置
CN104538041B (zh) * 2014-12-11 2018-07-03 深圳市智美达科技有限公司 异常声音检测方法及系统
CN105517037A (zh) * 2015-11-25 2016-04-20 努比亚技术有限公司 通话质量检测装置和方法
AU2016402256B2 (en) * 2016-04-29 2019-04-18 Honor Device Co., Ltd. Voice input exception determining method, apparatus, terminal, and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101419795A (zh) * 2008-12-03 2009-04-29 李伟 音频信号检测方法及装置、以及辅助口语考试系统
CN102324229A (zh) * 2011-09-08 2012-01-18 中国科学院自动化研究所 语音输入设备使用异常的检测方法及系统
CN103578470A (zh) * 2012-08-09 2014-02-12 安徽科大讯飞信息科技股份有限公司 一种电话录音数据的处理方法及系统
CN105338148A (zh) * 2014-07-18 2016-02-17 华为技术有限公司 一种根据频域能量对音频信号进行检测的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3301950A4 *

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109040937B (zh) * 2018-07-24 2020-08-28 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN108924331A (zh) * 2018-07-24 2018-11-30 Oppo（重庆）智能科技有限公司 语音拾取方法及相关产品
CN109040912A (zh) * 2018-07-24 2018-12-18 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109040937A (zh) * 2018-07-24 2018-12-18 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN109089191A (zh) * 2018-07-24 2018-12-25 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109089191B (zh) * 2018-07-24 2021-11-02 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109121046A (zh) * 2018-07-24 2019-01-01 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109120779B (zh) * 2018-07-24 2021-10-19 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN109040912B (zh) * 2018-07-24 2021-05-04 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN108650595A (zh) * 2018-07-24 2018-10-12 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN109151177A (zh) * 2018-07-24 2019-01-04 Oppo（重庆）智能科技有限公司 麦克风堵塞提醒方法及相关装置
CN109121046B (zh) * 2018-07-24 2020-09-01 Oppo（重庆）智能科技有限公司 堵孔处理方法及相关产品
CN112333608A (zh) * 2018-07-26 2021-02-05 Oppo广东移动通信有限公司 语音数据处理方法及相关产品
CN109121042A (zh) * 2018-07-26 2019-01-01 Oppo广东移动通信有限公司 语音数据处理方法及相关产品
CN109151701A (zh) * 2018-07-26 2019-01-04 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN109104684B (zh) * 2018-07-26 2020-10-30 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN109121060B (zh) * 2018-07-26 2020-12-01 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN109121042B (zh) * 2018-07-26 2020-12-08 Oppo广东移动通信有限公司 语音数据处理方法及相关产品
CN109121059A (zh) * 2018-07-26 2019-01-01 Oppo广东移动通信有限公司 扬声器堵孔检测方法及相关产品
CN112333608B (zh) * 2018-07-26 2022-03-22 Oppo广东移动通信有限公司 语音数据处理方法及相关产品
CN109121060A (zh) * 2018-07-26 2019-01-01 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
US11234089B2 (en) 2018-07-26 2022-01-25 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Microphone hole blockage detection method, microphone hole blockage detection device, and wireless earphone
CN109104684A (zh) * 2018-07-26 2018-12-28 Oppo广东移动通信有限公司 麦克风堵孔检测方法及相关产品
CN111047923A (zh) * 2019-12-30 2020-04-21 深圳创维数字技术有限公司 故事机的控制方法、故事播放系统及存储介质
CN113543005A (zh) * 2021-07-01 2021-10-22 猫岐智能科技（上海）有限公司 音频设备检测方法及系统
CN113543005B (zh) * 2021-07-01 2022-10-04 猫岐智能科技（上海）有限公司 音频设备检测方法及系统
CN113746976A (zh) * 2021-07-23 2021-12-03 荣耀终端有限公司 音频模块检测方法、电子设备及计算机存储介质

Also Published As

Publication number Publication date
US10231070B2 (en) 2019-03-12
CA2981775C (en) 2020-08-11
CN107548564B (zh) 2021-02-26
BR112017021239A2 (pt) 2018-06-26
CA2981775A1 (en) 2017-10-29
BR112017021239B1 (pt) 2023-10-03
AU2016402256B2 (en) 2019-04-18
AU2016402256A1 (en) 2017-11-16
US20180139554A1 (en) 2018-05-17
CN113038353A (zh) 2021-06-25
EP3301950A4 (en) 2018-08-01
EP3301950A1 (en) 2018-04-04
CN113038353B (zh) 2022-08-09
CN107548564A (zh) 2018-01-05
EP3301950B1 (en) 2020-11-04

Similar Documents

Publication Publication Date Title
WO2017185342A1 (zh) 一种语音输入异常的确定方法、装置、终端以及存储介质
CN102318325B (zh) 使音频设备的行为适配当前声学环境条件的控制
US9224395B2 (en) Voice detection for automatic volume controls and voice sensors
CN103905956B (zh) 音频控制方法、电子设备和音频输出设备
CN113630708B (zh) 耳机麦克风异常检测的方法、装置、耳机套件及存储介质
US20110003615A1 (en) Apparatus and method for detecting usage profiles of mobile devices
US20140341386A1 (en) Noise reduction
CN107452395B (zh) 一种语音信号回声消除装置及电视机
US20180174574A1 (en) Methods and systems for reducing false alarms in keyword detection
CN105721066A (zh) 基于声波的空间状态检测装置、系统与方法
CN113573226B (zh) 一种耳机及其耳机的出入耳检测方法、存储介质
US11297429B2 (en) Proximity detection for wireless in-ear listening devices
WO2023092754A1 (zh) 降噪参数设置方法、装置、耳机设备及存储介质
US8924206B2 (en) Electrical apparatus and voice signals receiving method thereof
CN108605191A (zh) 异音检测方法和装置
CN117440282A (zh) 耳机佩戴状态检测方法、装置、耳机及存储介质
WO2022041485A1 (zh) 音频信号的处理方法、电子设备及存储介质
CN103177731A (zh) 一种改进的模拟亚音ctcss尾音检测的方法与装置
CN112885323A (zh) 音频信息处理方法、装置及电子设备
CN105516493A (zh) 一种移动终端及其闹钟控制方法
CN115699173A (zh) 语音活动检测方法和装置
CN114286216B (zh) 一种腕戴设备及其气压调节方法、装置及系统
JP6282999B2 (ja) 補聴器の指向性を試験するための装置
CN117255282A (zh) 一种蓝牙音频采集方法和蓝牙耳机
CN108156307B (zh) 语音处理的方法以及语音通讯装置

Legal Events

Date Code Title Description
REEP Request for entry into the european phase

Ref document number: 2016895743

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2981775

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: 15574405

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2016402256

Country of ref document: AU

Date of ref document: 20160429

Kind code of ref document: A

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112017021239

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 112017021239

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20171003

NENP Non-entry into the national phase

Ref country code: DE