WO2019174081A1 - 音频播放方法、装置和音响设备 - Google Patents

音频播放方法、装置和音响设备 Download PDF

Info

Publication number
WO2019174081A1
WO2019174081A1 PCT/CN2018/082035 CN2018082035W WO2019174081A1 WO 2019174081 A1 WO2019174081 A1 WO 2019174081A1 CN 2018082035 W CN2018082035 W CN 2018082035W WO 2019174081 A1 WO2019174081 A1 WO 2019174081A1
Authority
WO
WIPO (PCT)
Prior art keywords
age
user
stage
audio
volume
Prior art date
Application number
PCT/CN2018/082035
Other languages
English (en)
French (fr)
Inventor
王声平
周毕兴
Original Assignee
深圳市沃特沃德股份有限公司
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 深圳市沃特沃德股份有限公司 filed Critical 深圳市沃特沃德股份有限公司
Publication of WO2019174081A1 publication Critical patent/WO2019174081A1/zh

Links

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
    • H04R1/02—Casings; Cabinets ; Supports therefor; Mountings therein
    • H04R1/028—Casings; Cabinets ; Supports therefor; Mountings therein associated with devices performing functions other than acoustics, e.g. electric candles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04S—STEREOPHONIC SYSTEMS 
    • H04S7/00—Indicating arrangements; Control arrangements, e.g. balance control
    • H04S7/30—Control circuits for electronic adaptation of the sound field
    • H04S7/301—Automatic calibration of stereophonic sound system, e.g. with test microphone
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Definitions

  • the invention relates to the field of smart home technology, in particular to an audio playing method, device and audio device.
  • the existing audio equipment has functions such as voice recognition and Bluetooth transmission.
  • the user can perform voice remote control on the audio equipment, and can also use audio equipment to remotely control other home equipment, so that the audio equipment is more intelligent.
  • Audio playback is the most important function of audio equipment.
  • a family usually has a group of users of different ages, and the user groups of different ages prefer different audio playback styles, and the audio playback style of the existing audio equipment is fixed, requiring the user to I like the manual adjustment, so I can't meet the diversified needs of users.
  • the main object of the present invention is to provide an audio playing method, device and audio device, which aims to realize adaptive adjustment of the audio playing style for user groups of different age groups, and improve the intelligent level of the audio device.
  • an embodiment of the present invention provides an audio playing method, where the method includes the following steps:
  • the step of matching the corresponding audio play policy according to the age of the user includes:
  • the audio play policy includes at least one of a track recommendation, a volume adjustment, and a function switch.
  • the age group includes a child stage, a youth stage, and an old stage
  • the audio play strategy includes a track recommendation
  • the recommended tracks corresponding to the child stage, the youth stage, and the old stage are respectively children's tracks, popular tracks, and classics. Tracks.
  • the age group includes a child stage, a youth stage, and an old stage
  • the audio play strategy includes a volume adjustment
  • the target volume corresponding to the child stage, the youth stage, and the old stage is a first volume and a second volume, respectively.
  • the third volume, the first volume, the second volume, and the third volume are sequentially increased.
  • the age group includes a child stage, a youth stage, and an old stage.
  • the audio play strategy includes a function switch, and the function switch policies corresponding to the child stage, the youth stage, and the old stage are respectively turning off the first function and turning on All features and turn off the second feature.
  • the audio playing policy includes a track recommendation
  • the step of executing the audio playing strategy includes: displaying the recommended track top.
  • the step of detecting the age of the user comprises: detecting the age of the user by using a face recognition technology.
  • the step of detecting the age of the user by the face recognition technology comprises:
  • the extracted feature vector is matched with the feature vector of the face of different ages in the face feature database to obtain the target feature vector with the highest similarity with the extracted feature vector;
  • the age corresponding to the target feature vector is evaluated as the age of the user.
  • the step of detecting the age of the user by the face recognition technology comprises:
  • the extracted feature vectors are matched with the feature vectors of faces of different ages in the face feature database to obtain N target feature vectors whose similarity with the extracted feature vectors reaches a threshold, N ⁇ 2;
  • the age of the user is evaluated based on ages corresponding to the N target feature vectors.
  • the embodiment of the invention simultaneously provides an audio playback device, the device comprising:
  • An age detection module for detecting the age of the user
  • a policy matching module configured to match a corresponding audio play policy according to the age of the user
  • a policy execution module configured to execute the audio play policy.
  • the policy matching module includes:
  • a determining unit configured to determine an age group in which the user is located according to the age of the user
  • the query unit is configured to query the correspondence between the age group and the audio playing policy, and obtain an audio playing strategy that matches the age group in which the user is located.
  • the audio playing policy includes a track recommendation
  • the policy execution module is configured to: display the recommended track top.
  • the age detecting module is configured to: detect a user's age by using a face recognition technology.
  • the age detecting module includes:
  • An image acquisition unit configured to collect a face image of the user
  • a feature extraction unit configured to extract a feature vector in the face image
  • a first matching unit configured to perform similarity matching between the extracted feature vector and a feature vector of a face of a different age in the face feature database, to obtain a target feature vector with the highest similarity with the extracted feature vector;
  • a first evaluation unit configured to estimate an age corresponding to the target feature vector as the age of the user.
  • the age detecting module includes:
  • An image acquisition unit configured to collect a face image of the user
  • a feature extraction unit configured to extract a feature vector in the face image
  • a second matching unit is configured to perform similarity matching between the extracted feature vector and the feature vector of the face of different ages in the face feature database, and obtain N target feature vectors whose similarity with the extracted feature vector reaches a threshold, N ⁇ 2;
  • a second evaluation unit configured to evaluate an age of the user according to an age corresponding to the N target feature vectors.
  • Embodiments of the present invention also provide an audio device including a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application being configured to be used for Perform the audio playback method.
  • An audio playing method provided by an embodiment of the present invention implements an adaptive adjustment of an audio playing style for a user group of different age groups by detecting an age of the user and performing an audio playing strategy that matches the age of the user. It satisfies the diversified needs of user groups of all ages, improves the intelligence level of audio equipment, and enhances the user experience.
  • FIG. 1 is a flow chart of an embodiment of an audio playing method of the present invention
  • FIG. 2 is a schematic diagram of a correspondence relationship between an age segment and an audio playing strategy according to an embodiment of the present invention
  • FIG. 3 is a block diagram showing an embodiment of an audio playback device of the present invention.
  • Figure 4 is a block diagram of the age detecting module of Figure 3;
  • FIG. 5 is a block diagram showing another module of the age detecting module of Figure 3;
  • FIG. 6 is a block diagram of the policy matching module of FIG. 3.
  • terminal and terminal device used herein include both a wireless signal receiver device, a device having only a wireless signal receiver without a transmitting capability, and a receiving and transmitting hardware.
  • Such devices may include cellular or other communication devices having a single line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications) Service, personal communication system), which can combine voice, data processing, fax and/or data communication capabilities; PDA (Personal Digital Assistant), which can include radio frequency receiver, pager, Internet/Intranet access, network Browser, notepad, calendar and/or GPS (Global Positioning System) receiver; conventional laptop and/or palmtop computer or other device with and/or conventional lap including radio frequency receiver Type and / or palmtop or other device.
  • PCS Personal Communications
  • PDA Personal Digital Assistant
  • terminal may be portable, transportable, installed in a vehicle (aviation, sea and/or land), or adapted and/or configured to operate locally, and/or Run in any other location on the Earth and/or space in a distributed form.
  • the "terminal” and “terminal device” used herein may also be a communication terminal, an internet terminal, a music/video playing terminal, and may be, for example, a PDA, a MID (Mobile Internet Device), and/or have a music/video playback.
  • Functional mobile phones can also be smart TVs, set-top boxes and other devices.
  • the audio playing method and device of the embodiment of the present invention are mainly applied to an audio device, and may of course be applied to a terminal device such as a mobile phone, a tablet, a personal computer, etc., which is not limited by the present invention.
  • a terminal device such as a mobile phone, a tablet, a personal computer, etc.
  • the following is a detailed description of the application to the audio equipment.
  • the method includes the following steps:
  • step S11 when a user activates, operates, or approaches an audio device, the audio device detects the current user's age.
  • the audio equipment can use image recognition technology, voiceprint recognition technology and other technical means to detect the age of the user. The following is an example of image recognition technology.
  • the face feature database is first established by first importing face image data of a large number of people of different ages into the database, and then extracting the machine learning method in the field of pattern recognition.
  • the feature vectors of faces of different ages (such as each age range) are recorded, and a face feature database is generated.
  • the audio device collects the user's face image through the camera, and uses the face recognition technology to extract the feature vector in the face image, and then extracts the feature vector and the face of the different age face in the face feature database.
  • the feature vector performs similarity matching, obtains the target feature vector with the highest similarity with the extracted feature vector, and finally estimates the age corresponding to the target feature vector as the user's age.
  • the age here can be a specific age value, such as 25 years old, or a rough age range, such as 20-25 years old.
  • the face feature library is established by performing the following methods before performing age detection:
  • the face feature database containing 400 sets of face feature vector sequences has been established, and each set of feature vectors has been sorted according to the age range.
  • the audio device collects the face image of the user, and uses the face recognition technology to extract the feature vector in the face image, and then extracts the feature vector and the feature vector of the face of different ages in the face feature database.
  • the similarity matching is performed, and N (N ⁇ 2) target feature vectors whose similarity with the extracted feature vector reaches the threshold are obtained, and finally the age of the user is evaluated according to the age corresponding to the N target feature vectors.
  • the specific evaluation methods are as follows: applying the sorting learning algorithm, respectively extracting the extracted feature vectors in the sequence of N target feature vectors according to the age to find the insertion position, and obtaining N age evaluation results, and performing weighted average calculation on the N age evaluation results. The final evaluation result.
  • the acoustic device applies the face recognition algorithm to extract the feature vector of the user's face image, and similarly matches the extracted feature vector with the feature vector in the face feature database (calculating the input image and the feature vector in the feature library) Image similarity). It is assumed that the three feature vectors (A, B, C) whose query and the extracted feature vector similarity reach the threshold value. Applying the sorting learning algorithm, the extracted feature vectors are searched for the insertion position according to the age group in the feature sequences related to A, B and C respectively, and three age evaluation results are obtained, which are assumed to be 20.x, 24.y, 22 respectively. .z. For the obtained evaluation results, a weighted evaluation algorithm is applied to calculate the final evaluation result.
  • the advantage of this scheme is that it does not rely on the similarity of single eigenvalues, effectively reduces the error rate of age recognition, and solves the problem that the eigenvalues cannot be unified under the conditions of urban-rural differences, latitude regional differences, ethnic differences, and gender differences.
  • step S12 after detecting the age of the user, the audio device matches the corresponding audio playing strategy according to the age of the user.
  • an audio playing strategy is preset in the audio device, and a correspondence relationship between the age group and the audio playing strategy is preset.
  • the audio device first determines the age range in which the user is located according to the age of the user, and then queries the correspondence between the age group and the audio playing strategy to obtain an audio playing strategy that matches the age group in which the user is located.
  • the age group may include at least two of a child stage, a youth stage, and an old age stage. For example, when determining the age range in which the user is located, if the age of the user is between 0-12 years old, it is determined that the user is in the child stage; if the age of the user is between 13-40 years old, it is determined that the user is in the youth stage; If the user's age is over 41, it is determined that the user is in the old age.
  • the above age group may be further subdivided, for example, the child stage is further subdivided into the infant stage and the infant stage, and the youth stage is further subdivided into the juvenile stage and the adult stage, and the old stage is further refined. Divided into middle-aged and advanced stages.
  • the audio playing strategy may include at least one of a track recommendation, a volume adjustment, a function switch, and the like, and different audio playback strategies correspond to different audio playback styles.
  • children's tracks can be recommended for children in the child stage, such as children's songs, including children's songs, light music, etc.; young people's tracks can be recommended for young people, such as popular songs, including current pop songs, rock music Etc.; It is suitable for the elderly users to recommend tracks suitable for the elderly, such as classic songs, including old songs and classical music that have been popular in the past.
  • the target volume can be set to the first volume for the user of the child stage, the target volume is set to the second volume for the user of the youth stage, and the target volume is set to the third volume for the user of the old stage, and the first volume, the first volume
  • the second volume and the third volume increase in turn.
  • set a small volume for children to prevent hearing loss in children set a moderate volume for young users, and set a large volume for older users, because older users have poor hearing.
  • the first volume, the second volume, and the third volume described herein may be specific volume values or approximate volume ranges.
  • the function switch strategy can be set for the user in the child stage to turn off the first function
  • the function switch policy is set for the user in the youth stage to turn on all functions
  • the function switch strategy is set to turn off the second function for the user in the old stage.
  • the first function and the second function may be the same or different. For example, for children and the elderly, they do not need additional functions such as shopping, only basic functions such as audio playback and voice recognition, so that additional functions such as shopping can be turned off for children and elderly users, leaving only basic functions.
  • the corresponding relationship between the age group and the audio playing strategy is: the audio playing strategy corresponding to the child stage is recommending the child track, adjusting the volume to the first volume, turning off the first function, and youth.
  • the audio playback strategy corresponding to the stage is to recommend popular tracks, adjust the volume to the second volume, and turn on all functions.
  • the audio playback strategy corresponding to the old stage is to recommend classic tracks, adjust the volume to the third volume, and turn on all functions.
  • the first volume, the second volume, and the third volume are sequentially increased.
  • step S13 after matching the corresponding audio playing strategy, the audio device immediately executes the audio playing strategy.
  • the audio device recommends a corresponding track to the user, such as displaying the recommended track on the display screen.
  • the audio playback strategy includes volume adjustment
  • the audio device adjusts the volume to the target volume.
  • the audio playback strategy includes a function switch
  • the audio device turns the corresponding function on or off.
  • the audio device when the user is a child, the audio device will display the children's songs to the top, adjust the volume to the first volume, and turn off the first function (such as shopping and other additional functions); when the user is young, the audio equipment will be popular.
  • the top of the track is displayed, the volume is adjusted to the second volume, and all functions are turned on; when the user is an elderly user, the audio device displays the classic track, adjusts the volume to the third volume, and turns off the second function (such as shopping, etc.) Additional features).
  • the audio playing method of the embodiment of the present invention realizes the adaptive adjustment of the audio playing style for the user groups of different age groups by detecting the age of the user and performing an audio playing strategy that matches the age of the user, and satisfies each
  • the diverse needs of the user community of the age group enhance the user experience.
  • the device includes an age detection module 10, a policy matching module 20, and a policy execution module 30.
  • the age detection module 10 is configured to detect the age of the user;
  • the module 20 is configured to match a corresponding audio play policy according to the age of the user, and the policy execution module 30 is configured to execute an audio play policy.
  • the age detecting module 10 detects the age of the current user.
  • the age detecting module 10 can detect the age of the user by using technical means such as image recognition technology and voiceprint recognition technology.
  • image recognition technology and voiceprint recognition technology.
  • voiceprint recognition technology The following is an example of image recognition technology.
  • the age detecting module 10 includes an image collecting unit 11, a feature extracting unit 12, a first matching unit 13, and a first evaluating unit 14, wherein: the image collecting unit 11 is configured to collect users. a face image; a feature extraction unit 12, configured to extract a feature vector in the face image; the first matching unit 13 is configured to compare the extracted feature vector with a feature vector of a face of a different age in the face feature database The degree matching is performed to obtain the target feature vector with the highest similarity with the extracted feature vector.
  • the first evaluation unit 14 is configured to estimate the age corresponding to the target feature vector as the age of the user.
  • the age here can be a specific age value, such as 25 years old, or a rough age range, such as 20-25 years old.
  • the age detecting module 10 includes an image collecting unit 11, a feature extracting unit 12, a second matching unit 15, and a second evaluating unit 16, wherein: the image collecting unit 11 is configured to collect a face image of the user; the feature extraction unit 12 is configured to extract a feature vector in the face image; and the second matching unit 15 is configured to perform the extracted feature vector and the feature vector of the face of different ages in the face feature database.
  • the similarity matching is performed to obtain N (N ⁇ 2) target feature vectors whose similarity with the extracted feature vector reaches the threshold; and the second evaluation unit 16 is configured to estimate the age of the user according to the age corresponding to the N target feature vectors.
  • the second evaluation unit 16 may apply a sorting learning algorithm, respectively extract the extracted feature vectors in the sequence of N target feature vectors according to the age to find the insertion position, obtain N age evaluation results, and perform weighted average calculation on the N age evaluation results. The final evaluation results are obtained.
  • an audio playing strategy is preset in the audio device, and a correspondence relationship between the age group and the audio playing strategy is preset.
  • the policy matching module 20 includes a determining unit and a query unit, wherein: a determining unit, configured to determine an age group in which the user is located according to the age of the user; and a query unit configured to query the correspondence between the age group and the audio playing policy Relationship, get the audio playback strategy that matches the age range in which the user is located.
  • the age group may include at least two of a child stage, a youth stage, and an old age stage. For example, when determining the age range in which the user is located, if the age of the user is between 0-12 years old, the determining unit determines that the user is in the child stage; if the user's age is between 13-40 years old, the determining unit determines the user In the youth stage; if the user's age is over 41, the determination unit determines that the user is in the old age.
  • the above age group may be further subdivided, for example, the child stage is further subdivided into the infant stage and the infant stage, and the youth stage is further subdivided into the juvenile stage and the adult stage, and the old stage is further refined. Divided into middle-aged and advanced stages.
  • the audio playing strategy may include at least one of a track recommendation, a volume adjustment, a function switch, and the like, and different audio playback strategies correspond to different audio playback styles.
  • children's tracks can be recommended for children in the child stage, such as children's songs, including children's songs, light music, etc.; young people's tracks can be recommended for young people, such as popular songs, including current pop songs, rock music Etc.; It is suitable for the elderly users to recommend tracks suitable for the elderly, such as classic songs, including old songs and classical music that have been popular in the past.
  • the target volume can be set to the first volume for the user of the child stage, the target volume is set to the second volume for the user of the youth stage, and the target volume is set to the third volume for the user of the old stage, and the first volume, the first volume
  • the second volume and the third volume increase in turn.
  • set a small volume for children to prevent hearing loss in children set a moderate volume for young users, and set a large volume for older users, because older users have poor hearing.
  • the first volume, the second volume, and the third volume described herein may be specific volume values or approximate volume ranges.
  • the function switch strategy can be set for the user in the child stage to turn off the first function
  • the function switch policy is set for the user in the youth stage to turn on all functions
  • the function switch strategy is set to turn off the second function for the user in the old stage.
  • the first function and the second function may be the same or different. For example, for children and the elderly, they do not need additional functions such as shopping, only basic functions such as audio playback and voice recognition, so that additional functions such as shopping can be turned off for children and elderly users, leaving only basic functions.
  • the corresponding relationship between the age group and the audio playing strategy is: the audio playing strategy corresponding to the child stage is recommending the child track, adjusting the volume to the first volume, turning off the first function, and youth.
  • the audio playback strategy corresponding to the stage is to recommend popular tracks, adjust the volume to the second volume, and turn on all functions.
  • the audio playback strategy corresponding to the old stage is to recommend classic tracks, adjust the volume to the third volume, and turn on all functions.
  • the first volume, the second volume, and the third volume are sequentially increased.
  • the policy execution module 30 After the corresponding audio play policy is matched, the policy execution module 30 immediately executes the audio play policy.
  • the policy execution module 30 recommends the corresponding track to the user, such as displaying the recommended track on the display screen.
  • the policy execution module 30 adjusts the volume to the target volume.
  • the policy execution module 30 turns the corresponding function on or off.
  • the policy execution module 30 displays the child track top, adjusts the volume to the first volume, and turns off the first function (such as shopping and other additional functions); when the user is a young person, the policy execution module 30 will display the popular track top, adjust the volume to the second volume, and turn on all functions; when the user is an elderly user, the policy execution module 30 will display the classic track top, adjust the volume to the third volume, and turn off the first Two features (such as additional features such as shopping).
  • the audio playing device of the embodiment of the present invention realizes the adaptive adjustment of the audio playing style for the user groups of different age groups by detecting the age of the user and performing an audio playing strategy that matches the age of the user, and satisfies each
  • the diverse needs of the user community of the age group enhance the user experience.
  • the present invention also contemplates an audio device that includes a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application being configured to perform an audio playback method.
  • the audio playing method includes the following steps: detecting the age of the user; matching the corresponding audio playing strategy according to the age of the user; and executing the audio playing strategy.
  • the audio playing method described in this embodiment is the audio playing method in the foregoing embodiment of the present invention, and details are not described herein again.
  • the present invention includes apparatus that is directed to performing one or more of the operations described herein. These devices may be specially designed and manufactured for the required purposes, or may also include known devices in a general purpose computer. These devices have computer programs stored therein that are selectively activated or reconfigured.
  • Such computer programs may be stored in a device (eg, computer) readable medium or in any type of medium suitable for storing electronic instructions and coupled to a bus, respectively, including but not limited to any Types of disks (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable) Read-Only Memory, EEPROM (Electrically Erasable) Programmable Read-Only Memory, flash memory, magnetic card or light card.
  • a readable medium includes any medium that is stored or transmitted by a device (eg, a computer) in a readable form.
  • each block of the block diagrams and/or block diagrams and/or flow diagrams and combinations of blocks in the block diagrams and/or block diagrams and/or flow diagrams can be implemented by computer program instructions. .
  • these computer program instructions can be implemented by a general purpose computer, a professional computer, or a processor of other programmable data processing methods, such that the processor is executed by a computer or other programmable data processing method.
  • steps, measures, and solutions in the various operations, methods, and processes that have been discussed in the present invention may be alternated, changed, combined, or deleted. Further, other steps, measures, and schemes of the various operations, methods, and processes that have been discussed in the present invention may be alternated, modified, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and solutions in the prior art having various operations, methods, and processes disclosed in the present invention may also be alternated, changed, rearranged, decomposed, combined, or deleted.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明揭示了一种音频播放方法、装置和音响设备，所述方法包括以下步骤：检测用户的年龄，根据用户的年龄匹配出对应的音频播放策略，执行音频播放策略。本发明实施例所提供的一种音频播放方法，通过检测用户的年龄，并执行与用户的年龄相匹配的音频播放策略，从而实现了针对不同年龄段的用户群体进行音频播放风格的自适应调整，满足了各个年龄段的用户群体的多样化需求，提高了音响设备的智能化水平，提升了用户体验。

Description

音频播放方法、装置和音响设备 技术领域
本发明涉及智能家居技术领域，特别是涉及到一种音频播放方法、装置和音响设备。
 背景技术
随着人工智能技术的发展，家居设备的智能化程度越来越高。以音响设备为例，现有的音响设备已具有语音识别、蓝牙传输等功能，用户可以对音响设备进行语音遥控，还可以利用音响设备来遥控其它的家居设备，使得音响设备更加智能化。
音频播放是音响设备最主要的功能。一个家庭中通常有多个年龄段的用户群体，而不同年龄段的用户群体喜欢的音频播放风格各不相同，而现有的音响设备的音频播放风格是固定不变的，需要用户根据自己的喜好手动调整，因此无法满足用户的多样化需求。
 技术问题
本发明的主要目的为提供一种音频播放方法、装置和音响设备，旨在实现针对不同年龄段的用户群体进行音频播放风格的自适应调整，提高音响设备的智能化水平。
 技术解决方案
为达以上目的，本发明实施例提出一种音频播放方法，所述方法包括以下步骤：
检测用户的年龄；
根据所述用户的年龄匹配出对应的音频播放策略；
执行所述音频播放策略。
可选地，所述根据所述用户的年龄匹配出对应的音频播放策略的步骤包括：
根据所述用户的年龄确定用户所处的年龄段；
查询年龄段与音频播放策略的对应关系，获取与所述用户所处的年龄段相匹配的音频播放策略。
可选地，所述音频播放策略包括曲目推荐、音量调节和功能开关中的至少一种。
可选地，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括曲目推荐，所述儿童阶段、青年阶段和老年阶段对应的推荐曲目分别为儿童曲目、流行曲目和经典曲目。
可选地，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括音量调节，所述儿童阶段、青年阶段和老年阶段对应的目标音量分别为第一音量、第二音量和第三音量，所述第一音量、第二音量和第三音量依次增大。
可选地，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括功能开关，所述儿童阶段、青年阶段和老年阶段对应的功能开关策略分别为关闭第一功能、开启所有功能和关闭第二功能。
可选地，所述音频播放策略包括曲目推荐，所述执行所述音频播放策略的步骤包括：将推荐曲目置顶显示。
可选地，所述检测用户的年龄的步骤包括：通过人脸识别技术检测用户的年龄。
可选地，所述通过人脸识别技术检测用户的年龄的步骤包括：
采集用户的人脸图像；
提取所述人脸图像中的特征向量；
将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度最高的目标特征向量；
将所述目标特征向量对应的年龄评估为所述用户的年龄。
可选地，所述通过人脸识别技术检测用户的年龄的步骤包括：
采集用户的人脸图像；
提取所述人脸图像中的特征向量；
将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度达到阈值的N个目标特征向量，N≥2；
根据所述N个目标特征向量对应的年龄评估所述用户的年龄。
本发明实施例同时提出一种音频播放装置，所述装置包括：
年龄检测模块，用于检测用户的年龄；
策略匹配模块，用于根据所述用户的年龄匹配出对应的音频播放策略；
策略执行模块，用于执行所述音频播放策略。
可选地，所述策略匹配模块包括：
确定单元，用于根据所述用户的年龄确定用户所处的年龄段；
查询单元，用于查询年龄段与音频播放策略的对应关系，获取与所述用户所处的年龄段相匹配的音频播放策略。
可选地，所述音频播放策略包括曲目推荐，所述策略执行模块用于：将推荐曲目置顶显示。
可选地，所述年龄检测模块用于：通过人脸识别技术检测用户的年龄。
可选地，所述年龄检测模块包括：
图像采集单元，用于采集用户的人脸图像；
特征提取单元，用于提取所述人脸图像中的特征向量；
第一匹配单元，用于将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度最高的目标特征向量；
第一评估单元，用于将所述目标特征向量对应的年龄评估为所述用户的年龄。
可选地，所述年龄检测模块包括：
图像采集单元，用于采集用户的人脸图像；
特征提取单元，用于提取所述人脸图像中的特征向量；
第二匹配单元，用于将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度达到阈值的N个目标特征向量，N≥2；
第二评估单元，用于根据所述N个目标特征向量对应的年龄评估所述用户的年龄。
本发明实施例还提出一种音响设备，其包括存储器、处理器和至少一个被存储在所述存储器中并被配置为由所述处理器执行的应用程序，所述应用程序被配置为用于执行音频播放方法。
 有益效果
本发明实施例所提供的一种音频播放方法，通过检测用户的年龄，并执行与用户的年龄相匹配的音频播放策略，从而实现了针对不同年龄段的用户群体进行音频播放风格的自适应调整，满足了各个年龄段的用户群体的多样化需求，提高了音响设备的智能化水平，提升了用户体验。
 附图说明
图1是本发明的音频播放方法一实施例的流程图；
图2是本发明实施例中年龄段与音频播放策略的对应关系示意图；
图3是本发明的音频播放装置一实施例的模块示意图；
图4是图3中的年龄检测模块的模块示意图；
图5是图3中的年龄检测模块的又一模块示意图；
图6是图3中的策略匹配模块的模块示意图。
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的最佳实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本发明，而不能解释为对本发明的限制。
本技术领域技术人员可以理解，除非特意声明，这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。应该进一步理解的是，本发明的说明书中使用的措辞“包括”是指存在所述特征、整数、步骤、操作、元件和/或组件，但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元件、组件和/或它们的组。应该理解，当我们称元件被“连接”或“耦接”到另一元件时，它可以直接连接或耦接到其他元件，或者也可以存在中间元件。此外，这里使用的“连接”或“耦接”可以包括无线连接或无线耦接。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的全部或任一单元和全部组合。
本技术领域技术人员可以理解，除非另外定义，这里使用的所有术语（包括技术术语和科学术语），具有与本发明所属领域中的普通技术人员的一般理解相同的意义。还应该理解的是，诸如通用字典中定义的那些术语，应该被理解为具有与现有技术的上下文中的意义一致的意义，并且除非像这里一样被特定定义，否则不会用理想化或过于正式的含义来解释。
本技术领域技术人员可以理解，这里所使用的“终端”、“终端设备”既包括无线信号接收器的设备，其仅具备无发射能力的无线信号接收器的设备，又包括接收和发射硬件的设备，其具有能够在双向通信链路上，执行双向通信的接收和发射硬件的设备。这种设备可以包括：蜂窝或其他通信设备，其具有单线路显示器或多线路显示器或没有多线路显示器的蜂窝或其他通信设备；PCS（Personal Communications Service，个人通信系统），其可以组合语音、数据处理、传真和/或数据通信能力；PDA（Personal Digital Assistant，个人数字助理），其可以包括射频接收器、寻呼机、互联网/内联网访问、网络浏览器、记事本、日历和/或GPS（Global Positioning System，全球定位系统）接收器；常规膝上型和/或掌上型计算机或其他设备，其具有和/或包括射频接收器的常规膝上型和/或掌上型计算机或其他设备。这里所使用的“终端”、“终端设备”可以是便携式、可运输、安装在交通工具（航空、海运和/或陆地）中的，或者适合于和/或配置为在本地运行，和/或以分布形式，运行在地球和/或空间的任何其他位置运行。这里所使用的“终端”、“终端设备”还可以是通信终端、上网终端、音乐/视频播放终端，例如可以是PDA、MID（Mobile Internet Device，移动互联网设备）和/或具有音乐/视频播放功能的移动电话，也可以是智能电视、机顶盒等设备。
本发明实施例的音频播放方法和装置，主要应用于音响设备，当然也可以应用于手机、平板、个人电脑等终端设备，本发明对此不做限定。以下以应用于音响设备为例进行详细说明。
参照图1，提出本发明的音频播放方法一实施例，所述方法包括以下步骤：
S11、检测用户的年龄。
S12、根据用户的年龄匹配出对应的音频播放策略。
S13、执行音频播放策略。
步骤S11中，当有用户启动、操作或靠近音响设备时，音响设备则检测当前用户的年龄。音响设备可以采用图像识别技术、声纹识别技术等技术手段来检测用户的年龄，以下以图像识别技术为例进行说明。
在一实施例中，在进行年龄检测之前，先通过以下方式建立人脸特征库：先向数据库导入大量不同年龄段的人的人脸图像数据，然后运用模式识别领域里的机器学习方法，提取并记录不同年龄（如每个年龄范围）的人脸的特征向量，生成人脸特征库。
当进行年龄检测时，音响设备通过摄像头采集用户的人脸图像，并利用人脸识别技术提取人脸图像中的特征向量，然后将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度最高的目标特征向量，最后将目标特征向量对应的年龄评估为用户的年龄。这里的年龄，可以是具体的年龄值，如25岁，也可以是大致的年龄范围，如20-25岁。
在另一实施例中，在进行年龄检测之前，先通过以下方式建立人脸特征库：
A.收集亚洲、美洲、欧洲、非洲的男/女人脸图像各10000张的人脸图像数据库。所涉及人的年龄范围从2岁到90岁，每人有20个年龄范围，每个年龄范围5张照片；
B. 应用人脸检测技术，对所搜集的40000张图片进行人脸图像检测，剔除检测不到人脸的图片，这里假设所有图片均成功通过了人脸检测；
C. 将通过人脸检测的图片以人为单位进行分组，并将每个人的图片按照年龄范围从小到大排列。本步骤完成后，就得到400组人脸图片；
D. 顺序遍历每组人脸照片中的每张图片，应用人脸识别技术，提取包括人脸的眼睛、鼻子、嘴、下巴等的位置、大小和形状等信息组成的人脸图像特征向量，并将每个人每个年龄范围的5张照片的特征向量进行加权求平均值，作为该年龄段的特征向量；
E. 仍然以人为单位分组，存储人脸图像的特征向量，从而建立包含400组特征向量序列的人脸特征库；
F. 应用排序学习算法，对每组特征序列里的特征向量按照年龄段从小到大重新进行排序。
至此，包含400 组人脸特征向量序列的人脸特征库建立完毕，并且每组特征向量都按照年龄范围完成了排序。
当进行年龄检测时，音响设备采集用户的人脸图像，并利用人脸识别技术提取人脸图像中的特征向量，然后将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度达到阈值的N （N≥2）个目标特征向量，最后根据N个目标特征向量对应的年龄评估用户的年龄。具体评估方法如：应用排序学习算法，分别将提取的特征向量在N个目标特征向量的序列中按照年龄查找插入位置，得到N个年龄评估结果，对N个年龄评估结果进行加权平均计算，得出最终的评估结果。
举例而言，假设用户是一位年轻的亚洲男性。音响设备应用人脸识别算法，提取出用户的人脸图像的特征向量，并将提取的特征向量与人脸特征库中的特征向量进行相似度匹配( 计算输入图像与特征库里特征向量所代表图像的相似度)。假设查询与提取的特征向量相似度达到阈值的3个目标特征向量 (A、B、C)。应用排序学习算法，分别将提取的特征向量在A、B、C 三者相关的特征序列中按照年龄段查找插入位置，得到三个年龄评估结果，假设分别为20.x，24.y，22.z。对得出的评估结果，应用加权求值算法，计算得出最终的评估结果。
本方案的优点是不依赖单一特征值相似度，有效降低了年龄识别的误差率，并且解决了城乡差异、纬度地域差异、人种差异、男女差异条件下特征值无法统一的问题。
步骤S12中，当检测出用户的年龄后，音响设备则根据用户的年龄匹配出对应的音频播放策略。
本发明实施例中，音响设备中预置了音频播放策略，以及年龄段与音频播放策略的对应关系。音响设备先根据用户的年龄确定用户所处的年龄段，再查询年龄段与音频播放策略的对应关系，获取与用户所处的年龄段相匹配的音频播放策略。
年龄段可以包括儿童阶段、青年阶段、老年阶段等中的至少两个阶段。例如，在确定用户所处的年龄段时，如果用户的年龄在0-12岁之间，则确定用户处于儿童阶段；如果用户的年龄在13-40岁之间，则确定用户处于青年阶段；如果用户的年龄在41岁以上，则确定用户处于老年阶段。
在某些实施例中，还可以将上述年龄段进一步细分，如：将儿童阶段进一步细分为婴儿阶段和幼儿阶段，将青年阶段进一步细分为少年阶段和成年阶段，将老年阶段进一步细分为中年阶段和高龄阶段。
音频播放策略可以包括曲目推荐、音量调节、功能开关等策略中的至少一种，不同的音频播放策略对应不同的音频播放风格。
对于曲目推荐，可以为儿童阶段的用户推荐适合儿童的曲目，如儿童曲目，包括儿歌、轻音乐等；可以为青年阶段的用户推荐适合青年人的曲目，如流行曲目，包括当下的流行歌曲、摇滚乐等；可以为老年阶段的用户推荐适合老年人的曲目，如经典曲目，包括过去流行过的老歌曲、古典乐等。
对于音量调节，可以为儿童阶段的用户设置目标音量为第一音量，为青年阶段的用户设置目标音量为第二音量，为老年阶段的用户设置目标音量为第三音量，且第一音量、第二音量和第三音量依次增大。也就是说，为儿童用户设置较小的音量，以防止儿童听力受损，为青年用户设置适中的音量，为老年用户设置较大的音量，因老年用户听力较差。这里所述的第一音量、第二音量和第三音量，可以是具体的音量值，也可以是大致的音量范围。
对于功能开关，可以为儿童阶段的用户设置功能开关策略为关闭第一功能，为青年阶段的用户设置功能开关策略为开启所有功能，为老年阶段的用户设置功能开关策略为关闭第二功能。其中，第一功能和第二功能可以相同，也可以不同。例如，对于儿童和老人来说，他们不需要购物等附加功能，只需要音频播放、语音识别等基本功能，因此可以为儿童和老年用户关闭购物等附加功能，只保留基本功能。
如图2所示，在一可选实施例中，年龄段与音频播放策略的对应关系为：儿童阶段对应的音频播放策略为推荐儿童曲目、调节音量至第一音量、关闭第一功能，青年阶段对应的音频播放策略为推荐流行曲目、调节音量至第二音量、开启所有功能，老年阶段对应的音频播放策略为推荐经典曲目、调节音量至第三音量、开启所有功能。其中，第一音量、第二音量和第三音量依次增大。
步骤S13中，当匹配出对应的音频播放策略后，音响设备则立即执行该音频播放策略。
具体的，当音频播放策略包括曲目推荐时，音响设备则向用户推荐对应的曲目，如在显示屏上将推荐曲目置顶显示。当音频播放策略包括音量调节时，音响设备则将音量调节至目标音量。当音频播放策略包括功能开关时，音响设备则开启或关闭对应的功能。
例如：当用户为儿童时，音响设备则将儿童曲目置顶显示，将音量调节至第一音量，并关闭第一功能（如购物等附加功能）；当用户为青年人时，音响设备则将流行曲目置顶显示，将音量调节至第二音量，并开启所有功能；当用户为老年用户时，音响设备则将经典曲目置顶显示，将音量调节至第三音量，并关闭第二功能（如购物等附加功能）。
本发明实施例的音频播放方法，通过检测用户的年龄，并执行与用户的年龄相匹配的音频播放策略，从而实现了针对不同年龄段的用户群体进行音频播放风格的自适应调整，满足了各个年龄段的用户群体的多样化需求，提升了用户体验。
参照图3，提出本发明的音频播放装置一实施例，所述装置包括年龄检测模块10、策略匹配模块20和策略执行模块30，其中：年龄检测模块10，用于检测用户的年龄；策略匹配模块20，用于根据用户的年龄匹配出对应的音频播放策略；策略执行模块30，用于执行音频播放策略。
本发明实施例中，当有用户启动、操作或靠近音响设备时，年龄检测模块10则检测当前用户的年龄。年龄检测模块10可以采用图像识别技术、声纹识别技术等技术手段来检测用户的年龄，以下以图像识别技术为例进行说明。
在一实施例中，年龄检测模块10如图4所示，包括图像采集单元11、特征提取单元12、第一匹配单元13和第一评估单元14，其中：图像采集单元11，用于采集用户的人脸图像；特征提取单元12，用于提取人脸图像中的特征向量；第一匹配单元13，用于将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度最高的目标特征向量；第一评估单元14，用于将目标特征向量对应的年龄评估为用户的年龄。这里的年龄，可以是具体的年龄值，如25岁，也可以是大致的年龄范围，如20-25岁。
在另一实施例中，年龄检测模块10如图5所示，包括图像采集单元11、特征提取单元12、第二匹配单元15和第二评估单元16，其中：图像采集单元11，用于采集用户的人脸图像；特征提取单元12，用于提取人脸图像中的特征向量；第二匹配单元15，用于将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度达到阈值的N （N≥2）个目标特征向量；第二评估单元16，用于根据N个目标特征向量对应的年龄评估用户的年龄。
第二评估单元16可以应用排序学习算法，分别将提取的特征向量在N个目标特征向量的序列中按照年龄查找插入位置，得到N个年龄评估结果，对N个年龄评估结果进行加权平均计算，得出最终的评估结果。
本发明实施例中，音响设备中预置了音频播放策略，以及年龄段与音频播放策略的对应关系。策略匹配模块20如图6所示，包括确定单元和查询单元，其中：确定单元，用于根据用户的年龄确定用户所处的年龄段；查询单元，用于查询年龄段与音频播放策略的对应关系，获取与用户所处的年龄段相匹配的音频播放策略。
年龄段可以包括儿童阶段、青年阶段、老年阶段等中的至少两个阶段。例如，在确定用户所处的年龄段时，如果用户的年龄在0-12岁之间，确定单元则确定用户处于儿童阶段；如果用户的年龄在13-40岁之间，确定单元则确定用户处于青年阶段；如果用户的年龄在41岁以上，确定单元则确定用户处于老年阶段。
在某些实施例中，还可以将上述年龄段进一步细分，如：将儿童阶段进一步细分为婴儿阶段和幼儿阶段，将青年阶段进一步细分为少年阶段和成年阶段，将老年阶段进一步细分为中年阶段和高龄阶段。
音频播放策略可以包括曲目推荐、音量调节、功能开关等策略中的至少一种，不同的音频播放策略对应不同的音频播放风格。
对于曲目推荐，可以为儿童阶段的用户推荐适合儿童的曲目，如儿童曲目，包括儿歌、轻音乐等；可以为青年阶段的用户推荐适合青年人的曲目，如流行曲目，包括当下的流行歌曲、摇滚乐等；可以为老年阶段的用户推荐适合老年人的曲目，如经典曲目，包括过去流行过的老歌曲、古典乐等。
对于音量调节，可以为儿童阶段的用户设置目标音量为第一音量，为青年阶段的用户设置目标音量为第二音量，为老年阶段的用户设置目标音量为第三音量，且第一音量、第二音量和第三音量依次增大。也就是说，为儿童用户设置较小的音量，以防止儿童听力受损，为青年用户设置适中的音量，为老年用户设置较大的音量，因老年用户听力较差。这里所述的第一音量、第二音量和第三音量，可以是具体的音量值，也可以是大致的音量范围。
对于功能开关，可以为儿童阶段的用户设置功能开关策略为关闭第一功能，为青年阶段的用户设置功能开关策略为开启所有功能，为老年阶段的用户设置功能开关策略为关闭第二功能。其中，第一功能和第二功能可以相同，也可以不同。例如，对于儿童和老人来说，他们不需要购物等附加功能，只需要音频播放、语音识别等基本功能，因此可以为儿童和老年用户关闭购物等附加功能，只保留基本功能。
如图2所示，在一可选实施例中，年龄段与音频播放策略的对应关系为：儿童阶段对应的音频播放策略为推荐儿童曲目、调节音量至第一音量、关闭第一功能，青年阶段对应的音频播放策略为推荐流行曲目、调节音量至第二音量、开启所有功能，老年阶段对应的音频播放策略为推荐经典曲目、调节音量至第三音量、开启所有功能。其中，第一音量、第二音量和第三音量依次增大。
当匹配出对应的音频播放策略后，策略执行模块30则立即执行该音频播放策略。
具体的，当音频播放策略包括曲目推荐时，策略执行模块30则向用户推荐对应的曲目，如在显示屏上将推荐曲目置顶显示。当音频播放策略包括音量调节时，策略执行模块30则将音量调节至目标音量。当音频播放策略包括功能开关时，策略执行模块30则开启或关闭对应的功能。
例如：当用户为儿童时，策略执行模块30则将儿童曲目置顶显示，将音量调节至第一音量，并关闭第一功能（如购物等附加功能）；当用户为青年人时，策略执行模块30则将流行曲目置顶显示，将音量调节至第二音量，并开启所有功能；当用户为老年用户时，策略执行模块30则将经典曲目置顶显示，将音量调节至第三音量，并关闭第二功能（如购物等附加功能）。
本发明实施例的音频播放装置，通过检测用户的年龄，并执行与用户的年龄相匹配的音频播放策略，从而实现了针对不同年龄段的用户群体进行音频播放风格的自适应调整，满足了各个年龄段的用户群体的多样化需求，提升了用户体验。
本发明同时提出一种音响设备，其包括存储器、处理器和至少一个被存储在存储器中并被配置为由处理器执行的应用程序，所述应用程序被配置为用于执行音频播放方法。所述音频播放方法包括以下步骤：检测用户的年龄；根据用户的年龄匹配出对应的音频播放策略；执行音频播放策略。本实施例中所描述的音频播放方法为本发明中上述实施例所涉及的音频播放方法，在此不再赘述。
本领域技术人员可以理解，本发明包括涉及用于执行本申请中所述操作中的一项或多项的设备。这些设备可以为所需的目的而专门设计和制造，或者也可以包括通用计算机中的已知设备。这些设备具有存储在其内的计算机程序，这些计算机程序选择性地激活或重构。这样的计算机程序可以被存储在设备（例如，计算机）可读介质中或者存储在适于存储电子指令并分别耦联到总线的任何类型的介质中，所述计算机可读介质包括但不限于任何类型的盘（包括软盘、硬盘、光盘、CD-ROM、和磁光盘）、ROM（Read-Only Memory，只读存储器）、RAM（Random Access Memory，随机存储器）、EPROM（Erasable Programmable Read-Only Memory，可擦写可编程只读存储器）、EEPROM（Electrically Erasable Programmable Read-Only Memory，电可擦可编程只读存储器）、闪存、磁性卡片或光线卡片。也就是，可读介质包括由设备（例如，计算机）以能够读的形式存储或传输信息的任何介质。
本技术领域技术人员可以理解，可以用计算机程序指令来实现这些结构图和/或框图和/或流图中的每个框以及这些结构图和/或框图和/或流图中的框的组合。本技术领域技术人员可以理解，可以将这些计算机程序指令提供给通用计算机、专业计算机或其他可编程数据处理方法的处理器来实现，从而通过计算机或其他可编程数据处理方法的处理器来执行本发明公开的结构图和/或框图和/或流图的框或多个框中指定的方案。
本技术领域技术人员可以理解，本发明中已经讨论过的各种操作、方法、流程中的步骤、措施、方案可以被交替、更改、组合或删除。进一步地，具有本发明中已经讨论过的各种操作、方法、流程中的其他步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。进一步地，现有技术中的具有与本发明中公开的各种操作、方法、流程中的步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。
以上所述仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。

Claims (20)

  1. 一种音频播放方法，其特征在于，包括以下步骤：
    检测用户的年龄；
    根据所述用户的年龄匹配出对应的音频播放策略；
    执行所述音频播放策略。
  2. 根据权利要求1所述的音频播放方法，其特征在于，所述根据所述用户的年龄匹配出对应的音频播放策略的步骤包括：
    根据所述用户的年龄确定用户所处的年龄段；
    查询年龄段与音频播放策略的对应关系，获取与所述用户所处的年龄段相匹配的音频播放策略。
  3. 根据权利要求2所述的音频播放方法，其特征在于，所述音频播放策略包括曲目推荐、音量调节和功能开关中的至少一种。
  4. 根据权利要求3所述的音频播放方法，其特征在于，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括曲目推荐，所述儿童阶段、青年阶段和老年阶段对应的推荐曲目分别为儿童曲目、流行曲目和经典曲目。
  5. 根据权利要求3所述的音频播放方法，其特征在于，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括音量调节，所述儿童阶段、青年阶段和老年阶段对应的目标音量分别为第一音量、第二音量和第三音量，所述第一音量、第二音量和第三音量依次增大。
  6. 根据权利要求3所述的音频播放方法，其特征在于，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括功能开关，所述儿童阶段、青年阶段和老年阶段对应的功能开关策略分别为关闭第一功能、开启所有功能和关闭第二功能。
  7. 根据权利要求3所述的音频播放方法，其特征在于，所述音频播放策略包括曲目推荐，所述执行所述音频播放策略的步骤包括：将推荐曲目置顶显示。
  8. 根据权利要求1所述的音频播放方法，其特征在于，所述检测用户的年龄的步骤包括：通过人脸识别技术检测用户的年龄。
  9. 根据权利要求8所述的音频播放方法，其特征在于，所述通过人脸识别技术检测用户的年龄的步骤包括：
    采集用户的人脸图像；
    提取所述人脸图像中的特征向量；
    将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度最高的目标特征向量；
    将所述目标特征向量对应的年龄评估为所述用户的年龄。
  10. 根据权利要求8所述的音频播放方法，其特征在于，所述通过人脸识别技术检测用户的年龄的步骤包括：
    采集用户的人脸图像；
    提取所述人脸图像中的特征向量；
    将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度达到阈值的N个目标特征向量，N≥2；
    根据所述N个目标特征向量对应的年龄评估所述用户的年龄。
  11. 一种音频播放装置，其特征在于，包括：
    年龄检测模块，用于检测用户的年龄；
    策略匹配模块，用于根据所述用户的年龄匹配出对应的音频播放策略；
    策略执行模块，用于执行所述音频播放策略。
  12. 根据权利要求11所述的音频播放装置，其特征在于，所述策略匹配模块包括：
    确定单元，用于根据所述用户的年龄确定用户所处的年龄段；
    查询单元，用于查询年龄段与音频播放策略的对应关系，获取与所述用户所处的年龄段相匹配的音频播放策略。
  13. 根据权利要求12所述的音频播放装置，其特征在于，所述音频播放策略包括曲目推荐、音量调节和功能开关中的至少一种。
  14. 根据权利要求13所述的音频播放装置，其特征在于，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括曲目推荐，所述儿童阶段、青年阶段和老年阶段对应的推荐曲目分别为儿童曲目、流行曲目和经典曲目。
  15. 根据权利要求13所述的音频播放装置，其特征在于，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括音量调节，所述儿童阶段、青年阶段和老年阶段对应的目标音量分别为第一音量、第二音量和第三音量，所述第一音量、第二音量和第三音量依次增大。
  16. 根据权利要求13所述的音频播放装置，其特征在于，所述年龄段包括儿童阶段、青年阶段和老年阶段，所述音频播放策略包括功能开关，所述儿童阶段、青年阶段和老年阶段对应的功能开关策略分别为关闭第一功能、开启所有功能和关闭第二功能。
  17. 根据权利要求11所述的音频播放装置，其特征在于，所述年龄检测模块用于：通过人脸识别技术检测用户的年龄。
  18. 根据权利要求18所述的音频播放装置，其特征在于，所述年龄检测模块包括：
    图像采集单元，用于采集用户的人脸图像；
    特征提取单元，用于提取所述人脸图像中的特征向量；
    第一匹配单元，用于将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度最高的目标特征向量；
    第一评估单元，用于将所述目标特征向量对应的年龄评估为所述用户的年龄。
  19. 根据权利要求17所述的音频播放装置，其特征在于，所述年龄检测模块包括：
    图像采集单元，用于采集用户的人脸图像；
    特征提取单元，用于提取所述人脸图像中的特征向量；
    第二匹配单元，用于将提取的特征向量与人脸特征库中不同年龄的人脸的特征向量进行相似度匹配，获得与提取的特征向量相似度达到阈值的N个目标特征向量，N≥2；
    第二评估单元，用于根据所述N个目标特征向量对应的年龄评估所述用户的年龄。
  20. 一种音响设备，包括存储器、处理器和至少一个被存储在所述存储器中并被配置为由所述处理器执行的应用程序，其特征在于，所述应用程序被配置为用于执行权利要求1至10任一项所述的音频播放方法。
PCT/CN2018/082035 2018-03-13 2018-04-04 音频播放方法、装置和音响设备 WO2019174081A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810205396.1 2018-03-13
CN201810205396.1A CN108521618A (zh) 2018-03-13 2018-03-13 音频播放方法和装置

Publications (1)

Publication Number Publication Date
WO2019174081A1 true WO2019174081A1 (zh) 2019-09-19

Family

ID=63433647

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/082035 WO2019174081A1 (zh) 2018-03-13 2018-04-04 音频播放方法、装置和音响设备

Country Status (2)

Country Link
CN (1) CN108521618A (zh)
WO (1) WO2019174081A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113225532A (zh) * 2021-04-30 2021-08-06 重庆天智慧启科技有限公司 一种智能联动视频监控系统和方法

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109557951B (zh) * 2018-12-10 2022-07-29 深圳Tcl数字技术有限公司 电视机角度的调节方法、电视机以及计算机可读存储介质
CN110188234A (zh) * 2019-05-31 2019-08-30 Oppo广东移动通信有限公司 音频推送方法及相关产品
CN111802963B (zh) * 2020-07-10 2022-01-11 小狗电器互联网科技（北京）股份有限公司 一种清洁设备及感兴趣信息播放方法和装置
CN113377323A (zh) * 2021-04-30 2021-09-10 荣耀终端有限公司 一种音频控制方法及电子设备
CN114708872A (zh) * 2022-03-22 2022-07-05 青岛海尔科技有限公司 语音指令的响应方法及装置、存储介质及电子装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106407424A (zh) * 2016-09-26 2017-02-15 维沃移动通信有限公司 一种推荐音乐的方法及移动终端
CN106648524A (zh) * 2016-09-30 2017-05-10 四川九洲电器集团有限责任公司 一种音频播放方法及音频播放设备
US20170170796A1 (en) * 2015-12-11 2017-06-15 Unlimiter Mfa Co., Ltd. Electronic device for adjusting an equalizer setting according to a user age, sound playback device, and equalizer adjustment method
CN107632814A (zh) * 2017-09-25 2018-01-26 珠海格力电器股份有限公司 音频信息的播放方法、装置和系统、存储介质、处理器

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102508606A (zh) * 2011-11-10 2012-06-20 广东步步高电子工业有限公司 通过识别人脸细分用户所属群体并设置移动手持装置对应功能的方法及系统
CN103177750A (zh) * 2011-12-20 2013-06-26 富泰华工业（深圳）有限公司 音频播放装置及其控制方法
CN105306673A (zh) * 2015-09-07 2016-02-03 惠州Tcl移动通信有限公司 移动终端及其自动调整情景模式的方法
CN105721222A (zh) * 2016-03-23 2016-06-29 四川长虹电器股份有限公司 对音乐内容进行分类和提供特色音效的方法及系统
CN106594610A (zh) * 2016-12-15 2017-04-26 上海亚明照明有限公司 一种具有图像识别功能的智能灯以及一种路灯

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170170796A1 (en) * 2015-12-11 2017-06-15 Unlimiter Mfa Co., Ltd. Electronic device for adjusting an equalizer setting according to a user age, sound playback device, and equalizer adjustment method
CN106407424A (zh) * 2016-09-26 2017-02-15 维沃移动通信有限公司 一种推荐音乐的方法及移动终端
CN106648524A (zh) * 2016-09-30 2017-05-10 四川九洲电器集团有限责任公司 一种音频播放方法及音频播放设备
CN107632814A (zh) * 2017-09-25 2018-01-26 珠海格力电器股份有限公司 音频信息的播放方法、装置和系统、存储介质、处理器

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113225532A (zh) * 2021-04-30 2021-08-06 重庆天智慧启科技有限公司 一种智能联动视频监控系统和方法

Also Published As

Publication number Publication date
CN108521618A (zh) 2018-09-11

Similar Documents

Publication Publication Date Title
WO2019174081A1 (zh) 音频播放方法、装置和音响设备
CN102779509B (zh) 语音处理设备和语音处理方法
CN108847219B (zh) 一种唤醒词预设置信度阈值调节方法及系统
CN108899044B (zh) 语音信号处理方法及装置
CN109427333A (zh) 激活语音识别服务的方法和用于实现所述方法的电子装置
US11521638B2 (en) Audio event detection method and device, and computer-readable storage medium
WO2015131783A1 (zh) 一种车辆内部使用场景的设置方法、车载设备和网络设备
WO2021135685A1 (zh) 身份认证的方法以及装置
CN109871896A (zh) 数据分类方法、装置、电子设备及存储介质
JP2007249585A (ja) 認証装置およびその制御方法、認証装置を備えた電子機器、認証装置制御プログラム、ならびに該プログラムを記録した記録媒体
CN110807325B (zh) 谓词识别方法、装置及存储介质
RU2635238C1 (ru) Способ, устройство и терминал для воспроизведения музыки на основе фотоальбома с фотографиями лиц
CN109271533A (zh) 一种多媒体文件检索方法
US11232790B2 (en) Control method for human-computer interaction device, human-computer interaction device and human-computer interaction system
CN110070863A (zh) 一种语音控制方法及装置
CN112312215B (zh) 基于用户识别的开机内容推荐方法、智能电视及存储介质
CN107666536A (zh) 一种寻找终端的方法和装置、一种用于寻找终端的装置
CN105956534B (zh) 基于人脸识别的智能提醒系统、方法及可穿戴设备
CN111090477A (zh) 一种可自动切换模式的智能终端及其实现方法
KR20150090730A (ko) 디스플레이장치 및 그 제어방법
CN111144344B (zh) 人物年龄的确定方法、装置、设备及存储介质
CN109302528A (zh) 一种拍照方法、移动终端及计算机可读存储介质
CN114333774B (zh) 语音识别方法、装置、计算机设备及存储介质
WO2022022743A1 (zh) 一种公用设备上识别用户的方法及电子设备
US20220284738A1 (en) Target user locking method and electronic device

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: 18909339

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18909339

Country of ref document: EP

Kind code of ref document: A1