WO2020155490A1 - 基于语音分析的管理音乐的方法、装置和计算机设备 - Google Patents

基于语音分析的管理音乐的方法、装置和计算机设备 Download PDF

Info

Publication number
WO2020155490A1
WO2020155490A1 PCT/CN2019/089117 CN2019089117W WO2020155490A1 WO 2020155490 A1 WO2020155490 A1 WO 2020155490A1 CN 2019089117 W CN2019089117 W CN 2019089117W WO 2020155490 A1 WO2020155490 A1 WO 2020155490A1
Authority
WO
WIPO (PCT)
Prior art keywords
wearing
value
music file
similarity
preset
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2019/089117
Other languages
English (en)
French (fr)
Inventor
李影
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020155490A1 publication Critical patent/WO2020155490A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/18—Artificial neural networks; Connectionist approaches
    • 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
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones

Definitions

  • This application relates to the field of price prediction, and in particular to a method, device and computer equipment for managing music based on voice analysis.
  • the main purpose of this application is to provide a method, device and computer equipment for managing music based on voice analysis that automatically recognizes the validity of instructions and then recognizes music.
  • this application proposes a method for managing music based on voice analysis, including:
  • the smart headset After the smart headset receives an instruction to collect audio clips from the user, it acquires the wearing value collected by the wearing sensor set on the smart headset, the wearing sensor is used to detect whether the user is wearing the smart headset;
  • the present application also provides a device for managing music based on voice analysis, which is characterized in that it includes:
  • the acquiring and wearing module is used for the smart earphone to obtain the wearing value collected by the wearing sensor set on the smart earphone after receiving the instruction of the user to collect the audio clip, the wearing sensor is used to detect whether the user is wearing the smart earphone ;
  • the wearing judgment module is used to judge whether the wearing value is within a preset wearing value range
  • a sound collection module configured to determine that the user wears the smart headset if the wearing value is within a preset wearing value range, and control the microphone to collect sound to obtain audio information
  • An extraction module for extracting the frequency spectrum and voiceprint information in the audio information
  • the gender judgment module is used to input the voiceprint information into a preset gender judgment model to obtain the gender type of the voiceprint information;
  • a matching calculation module configured to respectively calculate the similarity between the music file with the gender type tag in the preset server and the frequency spectrum to obtain a plurality of first similarity values
  • a determining module configured to use the music file corresponding to the largest first similarity value as the target music file
  • the download module is used to download the target music file to the memory of the smart headset.
  • the present application also provides a computer device including a memory and a processor, the memory stores computer readable instructions, and the processor implements the steps of the above method when the computer readable instructions are executed.
  • the present application also provides a computer non-volatile readable storage medium, on which computer readable instructions are stored, and when the computer readable instructions are executed by a processor, the steps of the above method are implemented.
  • the method, device and computer equipment for managing music based on voice analysis of the present application automatically detect whether the smart earphone is in contact with the human body to determine whether the issued instruction is a misoperation, thereby reducing unnecessary music recognition.
  • the music file is automatically downloaded to the memory of the smart headset, which saves the user's download time; at the same time, it automatically recommends the same style as the music tag to the user according to the music tag, giving users a better experience.
  • recognizing music not only the music is recognized through the frequency spectrum, but also the lyrics of the music are reviewed to make the recognized music files more accurate. Send the downloaded music to the user's friends so that the user can share the music with their friends.
  • FIG. 1 is a schematic flowchart of a method for managing music based on voice analysis according to an embodiment of this application;
  • FIG. 2 is a schematic block diagram of the structure of an apparatus for managing music based on voice analysis according to an embodiment of the application;
  • FIG. 3 is a schematic block diagram of the structure of an apparatus for managing music based on voice analysis according to an embodiment of the application;
  • FIG. 4 is a schematic block diagram of the structure of an apparatus for managing music based on voice analysis according to an embodiment of the application;
  • FIG. 5 is a schematic block diagram of the structure of an apparatus for managing music based on voice analysis according to an embodiment of the application;
  • FIG. 6 is a schematic block diagram of the structure of an apparatus for managing music based on voice analysis according to an embodiment of the application;
  • FIG. 7 is a schematic block diagram of the structure of an apparatus for managing music based on voice analysis according to an embodiment of the application;
  • FIG. 8 is a schematic block diagram of the structure of a computer device according to an embodiment of the application.
  • an embodiment of the present application provides a method for managing music based on voice analysis, including the steps:
  • the smart earphone obtains the wearing value collected by the wearing sensor set on the smart earphone after receiving the instruction to collect the audio clip from the user, and the wearing sensor is used to detect whether the user is wearing the smart earphone;
  • the smart headset is based on a normal headset, and is also loaded with smart hardware such as a memory, a communication module, a processor, and a microphone.
  • the smart headset is equipped with input devices such as buttons and sensors.
  • the smart headset controls the wearing value collected by the wearing sensor on the smart headset.
  • the wearing sensor detects whether the smart headset is compatible with The sensor that the user touches and wears, because when the user wears the smart earphone and the user does not wear the smart earphone, the smart earphone is in a different position state. According to the different sensors set on the smart earphone, the value of the different position state can be detected. Determine whether the user wears the smart headset.
  • the wearing sensor collects the degree of contact with the user to obtain the wearing value, and then feeds the obtained wearing value back to the smart headset.
  • the smart headset After the smart headset receives the wearing value collected by the wearing sensor, it compares it with the preset wearing value range to determine whether the collected wearing value is within this range. If so, it is determined that the headset is worn by the user. Therefore, it is determined that the command to collect the audio clip received by the smart headset is issued by the user, and it is not a misoperation accidentally encountered.
  • the wearing value range is set by the user according to his physical fitness, the specific type of wearing sensor, and the specific position of the wearing sensor on the smart headset.
  • the smart headset confirms that the instruction to collect audio clips is not a misoperation but a user operation, and then controls the microphone Start to collect surrounding sounds, and form audio information from the sounds collected by the microphone.
  • the smart headset controls the microphone to continuously collect sound for 10 seconds to obtain audio information with a duration of 10 seconds.
  • the smart headset first preprocesses audio information, including windowing the audio information to obtain an audio fragment sequence, and then performs fast Fourier transform on each frame in the audio fragment sequence to obtain a time series spectrum set . Then, perform Christ extraction on the above-mentioned time series spectrum set to obtain a fundamental frequency sequence, which is actually a function of the pitch of the above-mentioned audio information changing at any time. Then the base frequency sequence is converted into sound names to obtain the sound name sequence. Finally, the note-name sequence is divided into notes, and finally the frequency spectrum of the audio information is obtained.
  • the frequency spectrum extraction methods described in other publications can also be used to extract the frequency spectrum of the audio information in this application.
  • Voiceprint is a sound wave spectrum that carries verbal information displayed by electroacoustic instruments. Modern scientific research shows that voiceprint is not only specific, but also relatively stable.
  • the audio information includes the sound made by people singing.
  • everybody's voice is different, and the corresponding voiceprint is also different.
  • the smart headset divides the audio signal into frames, extracts the acoustic features of the voice, and processes the acoustic features of the voice to calculate the voiceprint information.
  • the voiceprint information of the singer is included in the audio information.
  • the voiceprint information is input into the gender judgment model, and the gender judgment model outputs the gender type of the voiceprint information. Because of the obvious difference between male voice and female voice.
  • the gender type of the gender judgment model includes male, female, and neutral. Because the voice of some singing people is not good at distinguishing gender.
  • the music with the gender type label of the voiceprint information The files are filtered out, and the similarity calculation is performed only with the filtered music files, which reduces the calculation objects and improves the calculation speed.
  • the smart earphone obtains a first similarity value after calculating the similarity between the frequency spectrum in the audio information and a music file with the above gender tag, and calculates multiple times to obtain the first similarity value corresponding to multiple music files .
  • the preset server is a server preset by the staff for storing music files.
  • the music file corresponding to the highest first similarity value is determined as the target music file.
  • the smart earphone accesses the cloud through the communication module, and compares the frequency spectrum of the audio information with the frequency spectrum of the music file in the cloud server to see whether the frequency spectrum of the audio information is the same as the frequency spectrum of the above-mentioned music file or is part of the frequency spectrum of the music file. If yes, it is determined that the music file is the target music file, and the target music file information is obtained at the same time, and the target music file is played.
  • a dialog box whether to download the target music file is generated for the user to choose whether to download.
  • the smart headset downloads the target music file from the cloud and stores it in the smart headset's memory. It is convenient for users to collect this music.
  • the audio information includes the first lyrics
  • the target music file includes the second lyrics text
  • the method before the step of downloading the target music file to the memory of the smart headset, the method includes:
  • S801 Parse out the first lyrics text corresponding to the first lyrics in the audio information, and obtain the second lyrics text of the target music file;
  • the audio information contains the first lyrics, that is, in the audio information, a person is singing and uttering text.
  • the smart headset obtains the audio information, performs semantic analysis on the audio information, and recognizes the text therein, that is, the first lyrics text.
  • the music file includes various music-related information such as music audio, artist, album name, song title, and lyrics text.
  • the smart earphone reads the second lyric text in the target music file, and calculates the similarity between the first lyric text and the second lyric text
  • the matching calculation method is: Calculate the first lyric text and the second lyric text To obtain the second similarity value; the specific calculation method is to use the degree of coincidence between the characters in the first lyrics text and the characters in the second lyrics text, if all the characters in the first lyrics text and the second lyrics text If some characters or all characters are completely overlapped, the similarity between the two is 100%.
  • the similarity threshold is a critical value preset by the staff for determining whether the first lyric text belongs to the second lyric text.
  • the size of the set similarity threshold is based on the success rate of converting audio information into text in the semantic analysis technology. Determine whether the second similarity value is higher than the preset similarity threshold. If the second similarity value is higher than the similarity threshold, it means that the first lyrics text is exactly the same as the second lyrics text or the first lyrics text and the second lyrics text If most of the text is the same, it is determined that the first lyric text matches the second lyric text, and it is further determined that the frequency spectrum in the audio information is the music in the target music file. Thus, an instruction to download the target music file is generated.
  • the above-mentioned wearing sensor is a contact temperature sensor that is arranged on the smart earphone to contact a person's ear, the wearing value is a temperature value, and the wearing value range is a temperature value range;
  • the steps for whether the wearing value is within the preset wearing value range include:
  • the contact temperature sensor is used to detect the temperature of the object in direct contact with it. It is installed at the speaker of the smart headset. When the user wears the smart headset, the contact temperature sensor contacts the user's headset or head. , The temperature value of the head position that is in contact with the user is collected; when the user is not wearing the smart headset, the contact temperature sensor does not touch the human body, is in contact with the air or is in contact with other objects, and collects wrong signals or other The temperature value of the object.
  • the temperature value range is set by the user according to his physical fitness and the normal temperature value of the location in contact with the user. When the user does not set it, the smart headset automatically accesses the corresponding server through the above-mentioned communication module to obtain the normal human body temperature value range.
  • the wearing sensor may also be a pressure sensor, a distance sensor, etc., which are arranged at the smart earphone in contact with the human body.
  • the collection source that is, the specific type of the wearing sensor, can be obtained.
  • the wearing value is a temperature value
  • the collection source is a temperature sensor, that is, a contact temperature sensor set on the earphone in contact with the human earphone.
  • the temperature value range of the contact temperature sensor is called from the memory, and the temperature value range is used as the wearing value range.
  • compare the aforementioned wearing value with the wearing value range to see whether the wearing value is within the wearing value range, and if so, it is determined that the user is wearing the smart headset.
  • the method before the step of inputting the voiceprint information into a preset gender judgment model to obtain the gender type of the voiceprint information, the method includes:
  • S501 Input multiple sample voiceprint information and genders corresponding to the sample voiceprint information into a neural network model, and perform training to obtain the gender judgment model.
  • the neural network when the gender judgment model is trained, the neural network is used as the basic model, a plurality of pre-collected sample voiceprint information is input into the neural network, and the gender of the sample voiceprint information As the result of the output.
  • the sample voiceprint information of all men can be input into the neural network first, and the output result is all men.
  • the sample voiceprint information of all women into the neural network, and the output results are all women.
  • the neural network model is based on the sample voiceprint information of men and women, and obtains the parameters of men and women respectively, and correspondingly obtains the gender judgment model based on the neural network model.
  • the method includes:
  • the contact information is searched in the memory.
  • the contact information is the contact phone number or mailbox of the user's close friend.
  • the smart headset sends the download link to the aforementioned mailbox or mobile phone through the communication module. , So that users can share their favorite music with others.
  • the method includes:
  • the user likes a piece of music, and the corresponding user also wants to listen to other music associated with this piece of music.
  • each piece of music will be in an album, and the information in each music file also includes album information.
  • the smart headset reads the album information in the target music file, then accesses the cloud to find other music files with the album information, and then downloads other music files to the smart headset’s memory, directly downloads the music that the user likes, and gives the user more information. Good service experience.
  • the above step of playing the target music file includes:
  • the specific information of the target music file is obtained from the server, including pulse code modulation information (ie, PCM) of the target music file. Then process the PCM to get the decibel value of the target music file.
  • the specific calculation process is: first filter and amplify the PCM, then divide the frame, sample each frame, and then accumulate the value of each sampling point to obtain a total value, and then divide the total value by the number of samples Count to get the average energy value of the sound. Then the average energy value is quantized in a ratio between 100 and 32767 to obtain a quantized value of 1-100, which is the decibel value of the target music file output.
  • the decibel threshold preset by the user is called, and the decibel threshold is the most comfortable and most accustomed sound level of the music that the user sets according to his own preferences.
  • the smart headset obtains the rated power of the speaker of the smart headset at the same time, multiplying the decibel threshold by the rated power, and then dividing by the decibel value to obtain the output power of the speaker of the smart headset. That is, playing the target music file with the output power can make the loudspeaker output the target music file to be the decibel threshold. Then control the speaker to play the target music file with the output power. Because the decibel value of each music file is different, the sound played out is very different.
  • the decibel value of the second music file is twice the decibel value of the first music file, and the first music file switches to the first music file.
  • the power of the smart headset remains unchanged. This will cause the user to suddenly receive very high decibel music, which will damage the user’s ears. Therefore, before playing the target music file, calculate the target music first According to the decibel value of the file, the output power of the smart headset is adjusted according to the decibel value and the decibel threshold set by the user, so that the size of the sound played by the target music file meets the needs of the user and brings a good experience effect to the user.
  • the method for managing music based on voice analysis of the present application automatically detects whether the smart headset is in contact with the human body to determine whether the issued instruction is a misoperation, thereby reducing unnecessary music recognition.
  • the music file is automatically downloaded to the memory of the smart headset, which saves the user's download time; at the same time, it automatically recommends the same style as the music tag to the user according to the music tag, giving users a better experience.
  • recognizing music not only the music is recognized through the frequency spectrum, but also the lyrics of the music are reviewed to make the recognized music files more accurate. Send the downloaded music to the user's friends so that the user can share the music with their friends.
  • an embodiment of the present application also provides an apparatus for managing music based on voice analysis, including:
  • the acquiring and wearing module 1 is used for the smart earphone to obtain the wearing value collected by the wearing sensor set on the smart earphone after receiving the instruction of the user to collect the audio clip.
  • the wearing sensor is used to detect whether the user is wearing the smart earphone or not. headset;
  • the judgment wearing module 2 is used to judge whether the wearing value is within a preset wearing value range
  • the sound collection module 3 is configured to determine that the user wears the smart headset if the wearing value is within the preset wearing value range, and collect sound to obtain audio information;
  • the extraction module 4 is used to extract the frequency spectrum and voiceprint information in the audio information
  • the gender judgment module 5 is used to input the voiceprint information into a preset gender judgment model to obtain the gender type of the voiceprint information;
  • the matching calculation module 6 is configured to respectively calculate the similarity between the music file with the gender type tag in the preset server and the frequency spectrum to obtain multiple first similarity values;
  • the determining module 7 is configured to use the music file corresponding to the largest first similarity value as the target music file, and play the target music file;
  • the download module 8 is configured to receive a download instruction sent by the user to download the target music file.
  • the above-mentioned apparatus for managing music based on voice analysis further includes:
  • Lyrics parsing module 801 configured to parse the first lyric text corresponding to the first lyric in the audio information, and obtain the second lyric text of the target music file;
  • the similarity calculation module 802 is configured to calculate the similarity between the first lyric text and the second lyric text to obtain a second similarity value
  • the similarity determining module 803 is configured to determine whether the second similarity value is higher than a preset similarity threshold
  • the generating instruction module 804 is configured to generate an instruction to download the target music file if the second similarity value is higher than a preset similarity threshold.
  • the above-mentioned wearing sensor is a contact temperature sensor arranged on the smart earphone to contact a person's ear, the wearing value is a temperature value, and the wearing value range is a temperature value range;
  • Module 2 includes:
  • the first judging unit is used to judge the collection source of the wearing value
  • a determining unit configured to, if it is determined that the collection source is the contact temperature sensor, call a preset temperature value range from a memory, and use the temperature value range as the wearing value range;
  • the second judgment unit is used to judge whether the wearing value is within the temperature value range
  • the determining unit is configured to determine that the user wears the smart headset if the wearing value is within the temperature value range.
  • the aforementioned apparatus for managing music based on voice analysis further includes:
  • the training module 501 is configured to input multiple sample voiceprint information and the gender corresponding to the sample voiceprint information into the neural network model for training to obtain the gender judgment model.
  • the foregoing apparatus for managing music based on voice analysis further includes:
  • the sending module 9 is used to send the download link of the target music file to a designated contact person.
  • the above-mentioned apparatus for managing music based on voice analysis further includes:
  • the storage module 10 is configured to download other music files in the album where the target music file is located to the memory.
  • the above determination module 7 includes:
  • a calculation unit configured to calculate the pulse code modulation information to obtain the decibel value of the target music file
  • An adjustment unit configured to adjust the output power of the smart headset according to the decibel value and a preset decibel threshold
  • the playing unit is used to play the target music file with the output power.
  • the foregoing calculation unit includes:
  • the framing subunit is used for filtering and amplifying the pulse code modulation information, and then framing;
  • the sampling subunit is used to sample each frame and accumulate the values obtained from each sample to obtain the total value of the pulse code modulation information
  • a calculation subunit configured to divide the total value by the number of frames to obtain the average energy value of the sound corresponding to the pulse code modulation information
  • the quantization subunit is used to quantize the average energy value to obtain the decibel value output by the target music file.
  • the device for managing music based on voice analysis of the present application automatically detects whether the smart headset is in contact with the human body to determine whether the issued instruction is a misoperation, thereby reducing unnecessary music recognition.
  • the music file is automatically downloaded to the memory of the smart headset, which saves the user's download time; at the same time, it automatically recommends the same style as the music tag to the user according to the music tag, giving users a better experience.
  • recognizing music not only the music is recognized through the frequency spectrum, but also the lyrics of the music are reviewed to make the recognized music files more accurate. Send the downloaded music to the user's friends so that the user can share the music with their friends.
  • an embodiment of the present application also provides a computer device.
  • the computer device may be a server, and its internal structure may be as shown in FIG. 8.
  • the computer equipment includes a processor, a memory, a network interface and a database connected by a system bus. Among them, the computer designed processor is used to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system, a computer program, and a database.
  • the memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium.
  • the computer equipment database is used to store audio information, music files and other data.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer program is executed by the processor to realize a method of managing music based on voice analysis.
  • the above-mentioned processor executes the steps of the above-mentioned method for managing music based on voice analysis: after the smart earphone receives an instruction from the user to collect audio clips, it acquires the wearing value collected by the wearing sensor set on the smart earphone, and the wearing sensor Used to detect whether the user wears the smart headset; determine whether the wearing value is within the preset wearing value range; if so, determine whether the user wears the smart headset, and collect sound to obtain audio information; extract the audio information The frequency spectrum and voiceprint information in the file; input the voiceprint information into a preset gender judgment model to obtain the gender type of the voiceprint information; respectively calculate the music with the gender type tag in the preset server The similarity between the file and the frequency spectrum obtains multiple first similarity values; the music file corresponding to the largest first similarity value is used as the target music file, and the target music file is played; Download instruction to download the target music file.
  • the audio information includes the first lyrics
  • the target music file includes the second lyrics text
  • the method includes: The first lyric text corresponding to the first lyric in the audio information is parsed, and the second lyric text of the target music file is obtained; the similarity between the first lyric text and the second lyric text is calculated to obtain A second similarity value; it is determined whether the second similarity value is higher than a preset similarity threshold; if so, an instruction to download the target music file is generated.
  • the above-mentioned wearing sensor is a contact temperature sensor that is arranged on the smart earphone to contact a person's ear, the above-mentioned wearing value is a temperature value, and the above-mentioned wearing value range is a temperature value range;
  • the step of determining whether the value is within the preset wearing value range includes: judging the collection source of the wearing value; if it is determined that the collection source is the contact temperature sensor, calling the preset temperature value range from the memory to The temperature value range is used as the wearing value range; it is determined whether the wearing value is within the temperature value range; if the wearing value is within the temperature value range, it is determined that the user is wearing the smart headset.
  • the processor before the processor executes the step of inputting the voiceprint information into a preset gender judgment model to obtain the gender type of the voiceprint information, it includes: combining a plurality of sample voiceprint information and The gender corresponding to the sample voiceprint information is input into the neural network model for training to obtain the gender judgment model.
  • the above-mentioned processor executes the above-mentioned step of receiving the download instruction sent by the user to download the target music file, it includes: sending the download link of the target music file to a designated contact.
  • the above-mentioned processor executes the above-mentioned step of receiving the download instruction sent by the user to download the target music file, it includes: downloading other music files in the album where the target music file is located to all Mentioned in memory.
  • the above-mentioned processor executing the above-mentioned step of playing the target music file includes: obtaining pulse code modulation information of the target music file; calculating the pulse code modulation information to obtain the target music file Adjust the output power of the smart headset according to the decibel value and a preset decibel threshold; use the output power to play the target music file.
  • the computer device of the present application automatically detects whether the smart headset is in contact with the human body to determine whether the issued instruction is a misoperation, thereby reducing unnecessary music recognition.
  • the music file is automatically downloaded to the memory of the smart headset, which saves the user's download time; at the same time, it automatically recommends the same style as the music tag to the user according to the music tag, giving users a better experience.
  • recognizing music not only the music is recognized through the frequency spectrum, but also the lyrics of the music are reviewed to make the recognized music files more accurate. Send the downloaded music to the user's friends so that the user can share the music with their friends.
  • an embodiment of the present application also provides a computer device.
  • the computer device may be a server, and its internal structure may be as shown in FIG. 8.
  • the computer equipment includes a processor, a memory, a network interface and a database connected by a system bus. Among them, the computer designed processor is used to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system, computer readable instructions, and a database.
  • the memory provides an environment for the operation of the operating system and computer readable instructions in the non-volatile storage medium.
  • the database of the computer equipment is used to store data such as carbon futures price prediction models.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer-readable instruction executes the process of the above-mentioned method embodiment.
  • FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • An embodiment of the present application further provides a computer non-volatile readable storage medium, on which computer readable instructions are stored, and when the computer readable instructions are executed, the processes as in the foregoing method embodiments are executed.
  • a computer non-volatile readable storage medium on which computer readable instructions are stored, and when the computer readable instructions are executed, the processes as in the foregoing method embodiments are executed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

提供了基于语音分析的管理音乐的方法、装置和计算机设备，包括：智能耳机接收到用户发出的采集音频片段的指令后，获取设置在智能耳机上的佩戴传感器采集的佩戴值（S1）；判断佩戴值是否在预设的佩戴值范围内（S2）；若是，判定用户佩戴智能耳机，并采集声音得到音频信息（S3）；提取出音频信息中的频谱以及声纹信息（S4）；将声纹信息输入到性别判断模型中，得到声纹信息的性别类型（S5）；分别计算服务器中带有性别类型标签的音乐文件与频谱的相似度，得到多个第一相似度值（S6）；将最大的第一相似度值对应的音乐文件作为目标音乐文件，并播放目标音乐文件（S7）；接收用户发送的下载指令，以下载目标音乐文件（S8）。

Description

基于语音分析的管理音乐的方法、装置和计算机设备
本申请要求于2019年1月31日提交中国专利局、申请号为201910100398.9，发明名称为“基于语音分析的管理音乐的方法、装置和计算机设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及价格预测领域，特别是涉及到一种基于语音分析的管理音乐的方法、装置和计算机设备。
 背景技术
目前有听歌识曲的技术，是将音频文件（wav波形声音）进行傅里叶变换，可以得出这段录音的频谱，然后再与服务器中的音乐文件进行匹配看与哪首音乐文件的频谱相同。如果相同就说明音频文件是音乐文件中的音频。用户在采集音频文件时，一般是在听歌过程中想起来了另一首歌，然后发出采集音频文件的指令；但是有时候将耳机放置在空地处，会使耳机被误操作而生成采集音频文件的指令，这样使耳机产生无用功，浪费不必要的计算资源。
 技术问题
本申请的主要目的为提供一种自动识别指令的有效性后识别音乐的基于语音分析的管理音乐的方法、装置和计算机设备。
 技术解决方案
为了实现上述申请目的，本申请提出一种基于语音分析的管理音乐的方法，包括：
智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
判断所述佩戴值是否在预设的佩戴值范围内；
若是，判定用户佩戴所述智能耳机，并采集声音，得到音频信息；
提取出所述音频信息中的频谱以及声纹信息；
将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
接收所述用户发送的下载指令，以下载所述目标音乐文件。
本申请还提供一种基于语音分析的管理音乐的装置，其特征在于，包括：
获取佩戴模块，用于智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
判断佩戴模块，用于判断所述佩戴值是否在预设的佩戴值范围内；
采集声音模块，用于若所述佩戴值在预设的佩戴值范围内，则判定用户佩戴所述智能耳机，控制麦克风采集声音，得到音频信息；
提取模块，用于提取出所述音频信息中的频谱以及声纹信息；
判断性别模块，用于将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
匹配计算模块，用于分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
确定模块，用于将最大的第一相似度值对应的音乐文件作为所述目标音乐文件；
下载模块，用于将所述目标音乐文件下载到所述智能耳机的存储器中。
本申请还提供一种计算机设备，包括存储器和处理器，所述存储器存储有计算机可读指令，所述处理器执行所述计算机可读指令时实现上述方法的步骤。
本申请还提供一种计算机非易失性可读存储介质，其上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现上述的方法的步骤。
 有益效果
本申请的基于语音分析的管理音乐的方法、装置和计算机设备，自动检测智能耳机是否是与人体接触来判定发出的指令是否是误操作，从而可以减小不必要的音乐识别。识别出音乐文件后将音乐文件自动下载到智能耳机的存储器中，节省用户的下载时间；同时还自动根据音乐的标签来向用户推荐与音乐的标签相同的风格，给用户更好的体验。在识别音乐时，不仅通过频谱来识别音乐，还根据音乐的歌词来进行复核，使识别出的音乐文件更加准确。将下载的音乐发送给用户的朋友，以便用户与朋友分享音乐。
 附图说明
图1为本申请一实施例的基于语音分析的管理音乐的方法的流程示意图；
图2为本申请一实施例的基于语音分析的管理音乐的装置的结构示意框图；
图3为本申请一实施例的基于语音分析的管理音乐的装置的结构示意框图；
图4为本申请一实施例的基于语音分析的管理音乐的装置的结构示意框图；
图5为本申请一实施例的基于语音分析的管理音乐的装置的结构示意框图；
图6为本申请一实施例的基于语音分析的管理音乐的装置的结构示意框图；
图7为本申请一实施例的基于语音分析的管理音乐的装置的结构示意框图；
图8为本申请一实施例的计算机设备的结构示意框图。
 本发明的最佳实施方式
参照图1，本申请实施例提供一种基于语音分析的管理音乐的方法，包括步骤：
S1、智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
S2、判断所述佩戴值是否在预设的佩戴值范围内；
S3、若是，判定用户佩戴所述智能耳机，并采集声音，得到音频信息；
S4、提取出所述音频信息中的频谱以及声纹信息；
S5、将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
S6、分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
S7、将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
S8、接收所述用户发送的下载指令，以下载所述目标音乐文件。
如上述步骤S1所述，智能耳机是基于普通耳机的基础上，还加载了存储器、通信模块、处理器、麦克风的智能硬件。智能耳机上设置有按键、传感器等输入装置，用户通过输入装置在智能耳机上发出采集音频片段的指令后，智能耳机控制智能耳机上的佩戴传感器采集的佩戴值，佩戴传感器是检测智能耳机是否与用户接触并佩戴的传感器，因用户佩戴智能耳机的时候与用户没有佩戴智能耳机时，智能耳机处于不同的位置状态，根据智能耳机上设置的不同传感器以检测出不同的位置状态的值，从而来判断用户是否佩戴了该智能耳机。佩戴传感器接收到智能耳机发出的指令后，采集与用户的接触程度，得到佩戴值，然后将得到的佩戴值反馈给智能耳机。
如上述步骤S2所述，智能耳机接收到佩戴传感器采集的佩戴值后，与预设的佩戴值范围进行比较，判断采集的佩戴值是否在该范围内，如果在，进行判定该耳机是用户戴着的，因此判定智能耳机接收到采集音频片段是指令是由用户发出的，不是不小心碰到的误操作。其中，佩戴值范围是用户根据自身的身体素质、佩戴传感器的具体类型、佩戴传感器在智能耳机上的具体位置而设置的。
如上述步骤S3所述，当佩戴值在预设的佩戴值范围内，则说明用户是佩戴了智能耳机的，因此智能耳机确认采集音频片段的指令不是误操作而是用户操作的，然后控制麦克风开始采集周围的声音，将麦克风采集的声音形成音频信息。在一具体实施例中，智能耳机接收到上述指令后，控制麦克风连续采集声音10秒，得到时长为10秒的音频信息。
如上述步骤S4所述，智能耳机首先将音频信息进行预处理，包括将音频信息进行加窗处理，得到音频片断序列，然后对音频片断序列中的每一帧进行快速傅立叶变换，得到时序频谱集合。然后对上述时序频谱集合进行基督提取，得到基频序列，这个基频序列实际上就是上述音频信息的音高随时变化的函数。然后将基频序列进行音名转换，得到音名序列。最后将音名序列进行音符切分，最终得到该音频信息的频谱。也可以采用其他公开文献中记载的提取频谱的方法来对本申请中的音频信息进行提取频谱。声纹是用电声学仪器显示的携带言语信息的声波频谱。现代科学研究表明，声纹不仅具有特定性，而且有相对稳定性的特点。音频信息中是包括了人唱歌时发出的声音。每个人的声音都是不相同的，对应的声纹也是不相同的。智能耳机将音频信号进行分帧，提取语音声学特征，并将语音声学特征进行处理，计算得到声纹信息，该声纹信息中音频信息中演唱者的声纹信息。
如上述步骤S5所述，将声纹信息输入到性别判断模型中，性别判断模型输出该声纹信息的性别类型。因男性的声音与女性的声音有明显不同的地方。其中，在一具体实施例中，性别判断模型的性别类型包括男性、女性、中性。因有些唱歌的人声音在艺术上不太好区分出性别来。
如上述步骤S6所述，根据性别判断模型输出的性别类型，在将音频信息中的频谱与预设的服务器中的音乐文件进行相似度计算时，将带有声纹信息的性别类型的标签的音乐文件筛选出来，只与筛选出来的音乐文件进行相似度计算，减小计算的对象，提高计算的速度。智能耳机在将音频信息中的频谱每与一个带有上述性别标签的音乐文件进行相似度计算后，得到一个第一相似度值，计算多次，得到多个音乐文件对应的第一相似度值。预设的服务器是工作人员预先设置的，用于存储音乐文件的服务器。
如上述步骤S7所述，将最高的第一相似度值对应的音乐文件确定为目标音乐文件。服务器中具有多个音乐文件，每个音乐文件均有与其对应的频谱。智能耳机通过通信模块访问云端，将音频信息的频谱与云端的服务器中的音乐文件的频谱依次比对，看音频信息的频谱是否与上述音乐文件的频谱相同或属于音乐文件的频谱的一部分，如果是，则判定该音乐文件为目标音乐文件，同时获取该目标音乐文件信息，播放目标音乐文件。
如上述步骤S8所述，智能耳机播放目标音乐文件后，生成一个是否下载目标音乐文件的对话框，以供用户选择是否下载。用户在该对话框中选择确认下载后，智能耳机将目标音乐文件从云端下载下来，存储在智能耳机的存储器中。便于用户收藏这首音乐。
在一个实施例中，上述音频信息包括第一歌词，上述目标音乐文件包括第二歌词文本，上述将所述目标音乐文件下载到所述智能耳机的存储器中的步骤之前，包括：
S801、解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；
S802、计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；
S803、判断所述第二相似度值是否高于预设的相似度阈值；
S804、若是，生成下载目标音乐文件的指令。
本实施例中，音频信息中包含有第一歌词，即音频信息中是一个人在唱歌，发出了文字。智能耳机获取到音频信息，对音频信息进行语义分析，识别出其中的文本，即第一歌词文本。音乐文件中包括音乐的音频、演唱者、专辑名称、歌名、歌词文本等各种与音乐相关的信息。然后智能耳机读取目标音乐文件中的第二歌词文本，将第一歌词文本与第二歌词文本匹配计算得到两者的相似度，匹配计算的方法为：计算第一歌词文本与第二歌词文本的相似度，得到第二相似度值；具体计算方法是，以第一歌词文本的字符与第二歌词文本中的字符的重合度，若第一歌词文本的全部字符与第二歌词文本中的部分字符或全部字符完全重合，则两者的相似度是100%。相似度阈值是工作人员预先设置的用于判定第一歌词文本是否属于第二歌词文本中的临界值，设置的相似度阈值的大小基于语义分析技术中将音频信息转换成文本的成功率。判断上述第二相似度值是否高于预设的相似度阈值，若第二相似度值高于相似度阈值，说明第一歌词文本与第二歌词文本完全相同或第一歌词文本与第二歌词文本的大部分相同，则判定第一歌词文本与第二歌词文本匹配，则进一步确定音频信息中的频谱就是目标音乐文件中的音乐。因而，生成下载目标音乐文件的指令。在音乐中，有很多音乐的频谱是相同的，比如《常回家看看》中的“老人不图儿女为家做多大贡献”和《大中国》“家里盘着两条龙是长江与黄河”，这两句的频谱是一样的，如果只是单纯的通过这一句歌的频谱来查找目标音乐文件，很有可能查找错误，因此，本方案通过进一步的比对音频信息中的歌词来使智能耳机更准确的下载到用户需要听到的音乐。
在一个实施例中，上述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，所述佩戴值是温度值，所述佩戴值范围是温度值范围；上述判断所述佩戴值是否在预设的佩戴值范围内的步骤，包括：
S21、判断所述佩戴值的采集来源；
S22、若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；
S24、判断所述佩戴值是否在所述温度值范围内；
S25、若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
本实施例中，接触式温度传感器是用于检测与其直接接触的物体的温度，其安装在智能耳机的扬声器处，当用户佩戴上智能耳机时，接触式温度传感器与用户的耳机或头部接触，采集到与用户接触的头部的位置的温度值；当用户没有佩戴上智能耳机时，接触式温度传感器没有接触人体，与空气接触或是与其他物体接触，采集到错误的信号或者是其他物体的温度值。温度值范围是用户根据自身的身体素质以及与用户接触的位置的正常温度值设置的。当用户没有设置时，智能耳机自动通过上述通信模块访问对应的服务器而获取到正常人体温度值范围。在其他实施例中，佩戴传感器还可以是设置在智能耳机处的与人体接触的压力传感器、距离传感器等。智能耳机获取到佩戴值后，根据佩戴值的大小以及单位，可以获取到采集来源，即佩戴传感器的具体类型。当佩戴值是一个温度值，则判定采集来源是一个温度传感器，即设置在耳机上与人的耳机接触的接触式温度传感器。然后从存储器中调用出该接触式温度传感器的温度值范围，将该温度值范围作为上述佩戴值范围。然后将上述佩戴值与佩戴值范围进行比较，看佩戴值是否在佩戴值范围内，如果在，就判定用户佩戴了智能耳机。
在一个实施例中，上述将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型的步骤之前，包括：
S501、将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
本实施例中，本实施例中，在对性别判断模型进行训练时，以神经网络为基本模型，将多个预先采集的样本声纹信息输入到神经网络中，并对样本声纹信息的性别作为输出的结果。具体的，可以先将全部的男性的样本声纹信息输入到神经网络中，输出结果全部是男性。然后将全部的女性的样本声纹信息输入到神经网络中，输出的结果全部是女性。如此训练。神经网络模型基于男性的样本声纹信息以及女性的样本声纹信息，分别得到男性的参数以及女性的参数，对应的得到了基于神经网络模型的性别判断模型。在另一具体实施例中，在训练时，还有中性的样本声纹信息，训练过程与上述训练过程一样。则最终得到了可以识别男性、女性、中性的性别判断模型。该模型只是用于识别声音的特征，而不是用于识别用户的本身的性别。
在一个实施例中，上述接收所述用户发送的下载指令，以下载所述目标音乐文件的步骤之后，包括：
S9、将所述目标音乐文件的下载链接发送给指定的联系人。
本实施例中，智能耳机下载了目标音乐文件后，再在存储器中查找联系方式，该联系方式是用户的亲密朋友的联系电话或邮箱，智能耳机将下载链接通过通信模块发送给上述邮箱或手机，便于用户与他人一起分享喜好的音乐。
在一个实施例中，上述接收所述用户发送的下载指令，以下载所述目标音乐文件的步骤之后，包括：
S10、将所述目标音乐文件所在的专辑中的其他音乐文件下载到所述存储器中。
本实施例中，用户喜欢一首音乐，对应的用户也想听与这首音乐相关联的其他音乐。一般，每首音乐均会在一个专辑中，每个音乐文件中的信息也包括专辑信息。智能耳机读取目标音乐文件中的专辑信息，再访问云端，查找带有该专辑信息的其他音乐文件，然后将其他音乐文件下载到智能耳机的存储器中，直接下载用户喜欢的音乐，给用户更好的服务体验。
在一个实施例中，上述播放所述目标音乐文件的步骤，包括：
S71、获取所述目标音乐文件的脉冲编码调制信息；
S72、将所述脉冲编码调制信息进行计算，得到所述目标音乐文件的分贝值；
S73、根据所述分贝值以及预设的分贝阈值，调整所述智能耳机的输出功率；
S74、以所述输出功率播放所述目标音乐文件。
本实施例中，智能耳机确定了目标音乐文件后，在服务器中获取到该目标音乐文件的具体信息，其中包括了目标音乐文件的脉冲编码调制信息（即PCM）。然后对PCM进行处理，得到目标音乐文件的分贝值。具体的计算过程为：首先对PCM进行滤波和放大处理，然后进行分帧，对每一帧进行采样，然后累加每个采样点的值，得到一个总值，然后将该总值除以采样个数，得到声音平均能量值。再将平均能量值做100与32767之间的等比量化，得到1-100的量化值，即目标音乐文件输出的分贝值。然后调用用户预设的分贝阈值，该分贝阈值是用户根据自身的喜好设置的最舒适与最习惯的听到的音乐的声音大小。智能耳机根据分贝值与分贝阈值的大小，同时获取到智能耳机的扬声器的额定功率，将分贝阈值乘以额定功率，再除以分贝值，得到智能耳机的扬声器的输出功率。即，以该输出功率播放该目标音乐文件，可以使扬声器输出目标音乐文件的声音大小是分贝阈值。然后控制扬声器以该输出功率播放目标音乐文件。因每个音乐文件的分贝值不同，这样播放出来的声音大不一样，如果第二个音乐文件的分贝值是第一个音乐文件的分贝值的两倍，而第一首音乐文件切换到第二个音乐文件播放时，智能耳机的功率不变，这样会使用户突然接收到非常高分贝的音乐，对用户的耳朵会有一定的损害，因此，在播放目标音乐文件前，先计算目标音乐文件的分贝值，再根据分贝值以及用户设置的分贝阈值，对智能耳机的输出功率进行调整，使目标音乐文件播放出来的声音大小符合用户的需要，给用户带来良好的体验效果。
综上所述，本申请的基于语音分析的管理音乐的方法，自动检测智能耳机是否是与人体接触来判定发出的指令是否是误操作，从而可以减小不必要的音乐识别。识别出音乐文件后将音乐文件自动下载到智能耳机的存储器中，节省用户的下载时间；同时还自动根据音乐的标签来向用户推荐与音乐的标签相同的风格，给用户更好的体验。在识别音乐时，不仅通过频谱来识别音乐，还根据音乐的歌词来进行复核，使识别出的音乐文件更加准确。将下载的音乐发送给用户的朋友，以便用户与朋友分享音乐。
参照图2，本申请实施例中还提供一种基于语音分析的管理音乐的装置，包括：
获取佩戴模块1，用于智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
判断佩戴模块2，用于判断所述佩戴值是否在预设的佩戴值范围内；
采集声音模块3，用于若所述佩戴值在预设的佩戴值范围内，则判定用户佩戴所述智能耳机，并采集声音，得到音频信息；
提取模块4，用于提取出所述音频信息中的频谱以及声纹信息；
判断性别模块5，用于将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
匹配计算模块6，用于分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
确定模块7，用于将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
下载模块8，用于接收所述用户发送的下载指令，以下载所述目标音乐文件。
参照图3，在一个实施例中，上述基于语音分析的管理音乐的装置，还包括：
解析歌词模块801，用于解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；
相似度计算模块802，用于计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；
判断相似度模块803，用于判断所述第二相似度值是否高于预设的相似度阈值；
生成指令模块804，用于若所述第二相似度值高于预设的相似度阈值，则生成下载目标音乐文件的指令。
在一个实施例中，上述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，所述佩戴值是温度值，所述佩戴值范围是温度值范围；所述判断佩戴模块2包括：
第一判断单元，用于判断所述佩戴值的采集来源；
确定单元，用于若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；
第二判断单元，用于判断所述佩戴值是否在所述温度值范围内；
判定单元，用于若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
参照图4，在一个实施例中，上述基于语音分析的管理音乐的装置，还包括：
训练模块501，用于将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
参照图5，在一个实施例中，上述基于语音分析的管理音乐的装置，还包括：
发送模块9，用于将所述目标音乐文件的下载链接发送给指定的联系人。
参照图6，在一个实施例中，上述基于语音分析的管理音乐的装置，还包括：
存储模块10，用于将所述目标音乐文件所在的专辑中的其他音乐文件下载到所述存储器中。
在一个实施例中，上述确定模块7包括：
获取单元，用于获取所述目标音乐文件的脉冲编码调制信息；
计算单元，用于将所述脉冲编码调制信息进行计算，得到所述目标音乐文件的分贝值；
调整单元，用于根据所述分贝值以及预设的分贝阈值，调整所述智能耳机的输出功率；
播放单元，用于以所述输出功率播放所述目标音乐文件。
在一个实施例中，上述计算单元包括：
分帧子单元，用于将所述脉冲编码调制信息进行滤波和放大处理，然后进行分帧；
采样子单元，用于对每一帧进行采样，并累加每个采样得到的值，得到所述脉冲编码调制信息的总值；
计算子单元，用于将所述总值除以帧的数量，得到所述脉冲编码调制信息对应的声音平均能量值；
量化子单元，用于将所述平均能量值进行量化，得到所述目标音乐文件输出的分贝值。
综上所述，本申请的基于语音分析的管理音乐的装置，自动检测智能耳机是否是与人体接触来判定发出的指令是否是误操作，从而可以减小不必要的音乐识别。识别出音乐文件后将音乐文件自动下载到智能耳机的存储器中，节省用户的下载时间；同时还自动根据音乐的标签来向用户推荐与音乐的标签相同的风格，给用户更好的体验。在识别音乐时，不仅通过频谱来识别音乐，还根据音乐的歌词来进行复核，使识别出的音乐文件更加准确。将下载的音乐发送给用户的朋友，以便用户与朋友分享音乐。参照图8，本申请实施例中还提供一种计算机设备，该计算机设备可以是服务器，其内部结构可以如图8所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设计的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储音频信息、音乐文件等数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种基于语音分析的管理音乐的方法。
上述处理器执行上述基于语音分析的管理音乐的方法的步骤：智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；判断所述佩戴值是否在预设的佩戴值范围内；若是，判定用户佩戴所述智能耳机，并采集声音，得到音频信息；提取出所述音频信息中的频谱以及声纹信息；将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；将最大第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；接收所述用户发送的下载指令，以下载所述目标音乐文件。
在一个实施例中，上述音频信息包括第一歌词，上述目标音乐文件包括第二歌词文本，上述处理器执行上述将所述目标音乐文件下载到所述智能耳机的存储器中的步骤之前，包括：解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；判断所述第二相似度值是否高于预设的相似度阈值；若是，生成下载目标音乐文件的指令。
在一个实施例中，上述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，上述佩戴值是温度值，上述佩戴值范围是温度值范围；所述判断所述佩戴值是否在预设的佩戴值范围内的步骤，包括：判断所述佩戴值的采集来源；若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；判断所述佩戴值是否在所述温度值范围内；若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
在一个实施例中，上述处理器执行上述将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型的步骤之前，包括：将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
在一个实施例中，上述处理器执行上述接收所述用户发送的下载指令，以下载所述目标音乐文件的步骤之后，包括：将所述目标音乐文件的下载链接发送给指定的联系人。
在一个实施例中，上述处理器执行上述接收所述用户发送的下载指令，以下载所述目标音乐文件的步骤之后，包括：将所述目标音乐文件所在的专辑中的其他音乐文件下载到所述存储器中。
在一个实施例中，上述处理器执行上述播放所述目标音乐文件的步骤，包括：获取所述目标音乐文件的脉冲编码调制信息；将所述脉冲编码调制信息进行计算，得到所述目标音乐文件的分贝值；根据所述分贝值以及预设的分贝阈值，调整所述智能耳机的输出功率；以所述输出功率播放所述目标音乐文件。
综上所述，本申请的计算机设备自动检测智能耳机是否是与人体接触来判定发出的指令是否是误操作，从而可以减小不必要的音乐识别。识别出音乐文件后将音乐文件自动下载到智能耳机的存储器中，节省用户的下载时间；同时还自动根据音乐的标签来向用户推荐与音乐的标签相同的风格，给用户更好的体验。在识别音乐时，不仅通过频谱来识别音乐，还根据音乐的歌词来进行复核，使识别出的音乐文件更加准确。将下载的音乐发送给用户的朋友，以便用户与朋友分享音乐。
参照图8，本申请实施例中还提供一种计算机设备，该计算机设备可以是服务器，其内部结构可以如图8所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设计的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统、计算机可读指令和数据库。该内存器为非易失性存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储碳期货价格预测模型等数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令在执行时，执行如上述各方法的实施例的流程。本领域技术人员可以理解，图8中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定。
本申请一实施例还提供一种计算机非易失性可读存储介质，其上存储有计算机可读指令，该计算机可读指令在执行时，执行如上述各方法的实施例的流程。以上所述仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请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，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于语音分析的管理音乐的方法，其特征在于，包括：
    智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
    判断所述佩戴值是否在预设的佩戴值范围内；
    若是，判定用户佩戴所述智能耳机，并采集声音，得到音频信息；
    提取出所述音频信息中的频谱以及声纹信息；
    将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
    分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
    将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
    接收所述用户发送的下载指令，以下载所述目标音乐文件。
  2. 如权利要求1所述的基于语音分析的管理音乐的方法，其特征在于，所述音频信息包括第一歌词，所述目标音乐文件包括第二歌词文本，所述将所述目标音乐文件下载到所述智能耳机的存储器中的步骤之前，包括：
    解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；
    计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；
    判断所述第二相似度值是否高于预设的相似度阈值；
    若是，生成下载目标音乐文件的指令。
  3. 如权利要求1所述的基于语音分析的管理音乐的方法，其特征在于，所述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，所述佩戴值是温度值，所述佩戴值范围是温度值范围；所述判断所述佩戴值是否在预设的佩戴值范围内的步骤，包括：
    判断所述佩戴值的采集来源；
    若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；
    判断所述佩戴值是否在所述温度值范围内；
    若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
  4. 如权利要求1所述的基于语音分析的管理音乐的方法，其特征在于，所述将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型的步骤之前，包括：
    将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
  5. 如权利要求1所述的基于语音分析的管理音乐的方法，其特征在于，所述播放所述目标音乐文件的步骤，包括：
    获取所述目标音乐文件的脉冲编码调制信息；
    将所述脉冲编码调制信息进行计算，得到所述目标音乐文件的分贝值；
    根据所述分贝值以及预设的分贝阈值，调整所述智能耳机的输出功率；
    以所述输出功率播放所述目标音乐文件。
  6. 如权利要求5所述的基于语音分析的管理音乐的方法，其特征在于，所述将所述脉冲编码调制信息进行计算，得到所述目标音乐文件的分贝值的步骤，包括：
    将所述脉冲编码调制信息进行滤波和放大处理，然后进行分帧；
    对每一帧进行采样，并累加每个采样得到的值，得到所述脉冲编码调制信息的总值；
    将所述总值除以帧的数量，得到所述脉冲编码调制信息对应的声音平均能量值；
    将所述平均能量值进行量化，得到所述目标音乐文件输出的分贝值。
  7. 一种基于语音分析的管理音乐的装置，其特征在于，包括：
    获取佩戴模块，用于智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
    判断佩戴模块，用于判断所述佩戴值是否在预设的佩戴值范围内；
    采集声音模块，用于若所述佩戴值在预设的佩戴值范围内，则判定用户佩戴所述智能耳机，控制麦克风采集声音，得到音频信息；
    提取模块，用于提取出所述音频信息中的频谱以及声纹信息；
    判断性别模块，用于将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
    匹配计算模块，用于分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
    确定模块，用于将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
    下载模块，用于接收所述用户发送的下载指令，以下载所述目标音乐文件。
  8. 根据权利要求7所述的基于语音分析的管理音乐的装置，其特征在于，所述基于语音分析的管理音乐的装置，还包括：
    解析歌词模块，用于解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；
    相似度计算模块，用于计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；
    判断相似度模块，用于判断所述第二相似度值是否高于预设的相似度阈值；
    生成指令模块，用于若所述第二相似度值高于预设的相似度阈值，则生成下载目标音乐文件的指令。
  9. 根据权利要求7所述的基于语音分析的管理音乐的装置，其特征在于，所述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，所述佩戴值是温度值，所述佩戴值范围是温度值范围；所述判断佩戴模块包括：
    第一判断单元，用于判断所述佩戴值的采集来源；
    确定单元，用于若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；
    第二判断单元，用于判断所述佩戴值是否在所述温度值范围内；
    判定单元，用于若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
  10. 根据权利要求7所述的基于语音分析的管理音乐的装置，其特征在于，所述基于语音分析的管理音乐的装置，还包括：
    训练模块，用于将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
  11. 根据权利要求7所述的基于语音分析的管理音乐的装置，其特征在于，所述确定模块包括：
    获取单元，用于获取所述目标音乐文件的脉冲编码调制信息；
    计算单元，用于将所述脉冲编码调制信息进行计算，得到所述目标音乐文件的分贝值；
    调整单元，用于根据所述分贝值以及预设的分贝阈值，调整所述智能耳机的输出功率；
    播放单元，用于以所述输出功率播放所述目标音乐文件。
  12. 根据权利要求7所述的基于语音分析的管理音乐的装置，其特征在于，所述计算单元包括：
    分帧子单元，用于将所述脉冲编码调制信息进行滤波和放大处理，然后进行分帧；
    采样子单元，用于对每一帧进行采样，并累加每个采样得到的值，得到所述脉冲编码调制信息的总值；
    计算子单元，用于将所述总值除以帧的数量，得到所述脉冲编码调制信息对应的声音平均能量值；
    量化子单元，用于将所述平均能量值进行量化，得到所述目标音乐文件输出的分贝值。
  13. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机可读指令，其特征在于，所述处理器执行所述计算机可读指令时实现基于语音分析的管理音乐的方法，该基于语音分析的管理音乐的方法，包括：
    智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
    判断所述佩戴值是否在预设的佩戴值范围内；
    若是，判定用户佩戴所述智能耳机，并采集声音，得到音频信息；
    提取出所述音频信息中的频谱以及声纹信息；
    将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
    分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
    将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
    接收所述用户发送的下载指令，以下载所述目标音乐文件。
  14. 根据权利要求13的计算机设备，其特征在于，所述音频信息包括第一歌词，所述目标音乐文件包括第二歌词文本，所述将所述目标音乐文件下载到所述智能耳机的存储器中的步骤之前，包括：
    解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；
    计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；
    判断所述第二相似度值是否高于预设的相似度阈值；
    若是，生成下载目标音乐文件的指令。
  15. 根据权利要求13所述的计算机设备，其特征在于，所述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，所述佩戴值是温度值，所述佩戴值范围是温度值范围；所述判断所述佩戴值是否在预设的佩戴值范围内的步骤，包括：
    判断所述佩戴值的采集来源；
    若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；
    判断所述佩戴值是否在所述温度值范围内；
    若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
  16. 根据权利要求13所述的计算机设备，其特征在于，所述将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型的步骤之前，包括：
    将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
  17. 一种计算机非易失性可读存储介质，其上存储有计算机可读指令，其特征在于，所述计算机可读指令被处理器执行时实现基于语音分析的管理音乐的方法，该基于语音分析的管理音乐的方法，包括：
    智能耳机接收到用户发出的采集音频片段的指令后，获取设置在所述智能耳机上的佩戴传感器采集的佩戴值，所述佩戴传感器用于检测用户是否佩戴所述智能耳机；
    判断所述佩戴值是否在预设的佩戴值范围内；
    若是，判定用户佩戴所述智能耳机，并采集声音，得到音频信息；
    提取出所述音频信息中的频谱以及声纹信息；
    将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型；
    分别计算预设的服务器中带有所述性别类型标签的音乐文件与所述频谱的相似度，得到多个第一相似度值；
    将最大的第一相似度值对应的音乐文件作为所述目标音乐文件，并播放所述目标音乐文件；
    接收所述用户发送的下载指令，以下载所述目标音乐文件。
  18. 根据权利要求17的计算机非易失性可读存储介质，其特征在于，所述音频信息包括第一歌词，所述目标音乐文件包括第二歌词文本，所述处理器将所述目标音乐文件下载到所述智能耳机的存储器中的步骤之前，包括：
    解析出所述音频信息中的第一歌词对应的第一歌词文本，并获取所述目标音乐文件的第二歌词文本；
    计算所述第一歌词文本与所述第二歌词文本的相似度，得到第二相似度值；
    判断所述第二相似度值是否高于预设的相似度阈值；
    若是，生成下载目标音乐文件的指令。
  19. 根据权利要求17所述的计算机非易失性可读存储介质，其特征在于，所述佩戴传感器是设置在所述智能耳机上与人的耳朵接触的接触式温度传感器，所述佩戴值是温度值，所述佩戴值范围是温度值范围；所述处理器判断所述佩戴值是否在预设的佩戴值范围内的步骤，包括：
    判断所述佩戴值的采集来源；
    若判定所述采集来源是所述接触式温度传感器，从存储器中调用预设的温度值范围，以所述温度值范围作为所述佩戴值范围；
    判断所述佩戴值是否在所述温度值范围内；
    若所述佩戴值在所述温度值范围内，则判定用户佩戴所述智能耳机。
  20. 根据权利要求17所述的计算机非易失性可读存储介质，其特征在于，所述处理器将所述声纹信息输入到预设的性别判断模型中，得到所述声纹信息的性别类型的步骤之前，包括：
    将多个样本声纹信息以及样本声纹信息对应的性别输入到神经网络模型中，进行训练，得到所述性别判断模型。
PCT/CN2019/089117 2019-01-31 2019-05-29 基于语音分析的管理音乐的方法、装置和计算机设备 Ceased WO2020155490A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910100398.9 2019-01-31
CN201910100398.9A CN109785859B (zh) 2019-01-31 2019-01-31 基于语音分析的管理音乐的方法、装置和计算机设备

Publications (1)

Publication Number Publication Date
WO2020155490A1 true WO2020155490A1 (zh) 2020-08-06

Family

ID=66503021

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/089117 Ceased WO2020155490A1 (zh) 2019-01-31 2019-05-29 基于语音分析的管理音乐的方法、装置和计算机设备

Country Status (2)

Country Link
CN (1) CN109785859B (zh)
WO (1) WO2020155490A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112291767A (zh) * 2020-10-28 2021-01-29 广东美她实业投资有限公司 基于智能蓝牙耳机的外卖下单方法、设备及可读存储介质
CN115497505A (zh) * 2022-08-23 2022-12-20 惠州华阳通用电子有限公司 一种车载音乐识别方法
CN118968982A (zh) * 2024-08-05 2024-11-15 赣州得辉达科技有限公司 基于数据分析的音箱控制管理方法及系统

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109785859B (zh) * 2019-01-31 2024-02-02 平安科技（深圳）有限公司 基于语音分析的管理音乐的方法、装置和计算机设备
CN112102848B (zh) * 2019-06-17 2024-04-26 华为技术有限公司 一种用于识别音乐的方法、芯片和终端
CN110246505A (zh) * 2019-06-24 2019-09-17 付金龙 声波控制灯带闪动的方法、系统及电子设备
CN110362711A (zh) * 2019-06-28 2019-10-22 北京小米智能科技有限公司 歌曲推荐方法及装置
CN111064846A (zh) * 2019-12-13 2020-04-24 歌尔科技有限公司 一种头戴式设备及语音秘书的设置方法、装置
CN111125432B (zh) * 2019-12-25 2023-07-11 重庆能投渝新能源有限公司石壕煤矿 一种视频匹配方法及基于该方法的培训快速匹配系统
CN111368136A (zh) * 2020-03-31 2020-07-03 北京达佳互联信息技术有限公司 歌曲识别方法、装置、电子设备及存储介质
CN111488485B (zh) * 2020-04-16 2023-11-17 北京雷石天地电子技术有限公司 基于卷积神经网络的音乐推荐方法、存储介质和电子装置
CN111768782A (zh) * 2020-06-30 2020-10-13 广州酷狗计算机科技有限公司 音频识别方法、装置、终端及存储介质
CN113518202A (zh) * 2021-04-07 2021-10-19 华北电力大学扬中智能电气研究中心 一种安防监控方法、装置、电子设备及存储介质
CN113380249B (zh) * 2021-06-11 2024-06-25 北京声智科技有限公司 语音控制方法、装置、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1785891A1 (en) * 2005-11-09 2007-05-16 Sony Deutschland GmbH Music information retrieval using a 3D search algorithm
CN104657438A (zh) * 2015-02-02 2015-05-27 联想(北京)有限公司 信息处理方法及电子设备
CN105338447A (zh) * 2015-10-19 2016-02-17 京东方科技集团股份有限公司 耳机控制电路及方法、耳机以及音频输出装置及方法
CN108737872A (zh) * 2018-06-08 2018-11-02 百度在线网络技术（北京）有限公司 用于输出信息的方法和装置
CN109145148A (zh) * 2017-06-28 2019-01-04 百度在线网络技术（北京）有限公司 信息处理方法和装置
CN109785859A (zh) * 2019-01-31 2019-05-21 平安科技（深圳）有限公司 基于语音分析的管理音乐的方法、装置和计算机设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101662617B1 (ko) * 2015-05-19 2016-10-06 오영권 블루투스헤드셋 및 이를 포함하는 손목시계
CN108391206A (zh) * 2018-03-30 2018-08-10 广东欧珀移动通信有限公司 信号处理方法、装置、终端、耳机及可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1785891A1 (en) * 2005-11-09 2007-05-16 Sony Deutschland GmbH Music information retrieval using a 3D search algorithm
CN104657438A (zh) * 2015-02-02 2015-05-27 联想(北京)有限公司 信息处理方法及电子设备
CN105338447A (zh) * 2015-10-19 2016-02-17 京东方科技集团股份有限公司 耳机控制电路及方法、耳机以及音频输出装置及方法
CN109145148A (zh) * 2017-06-28 2019-01-04 百度在线网络技术（北京）有限公司 信息处理方法和装置
CN108737872A (zh) * 2018-06-08 2018-11-02 百度在线网络技术（北京）有限公司 用于输出信息的方法和装置
CN109785859A (zh) * 2019-01-31 2019-05-21 平安科技（深圳）有限公司 基于语音分析的管理音乐的方法、装置和计算机设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112291767A (zh) * 2020-10-28 2021-01-29 广东美她实业投资有限公司 基于智能蓝牙耳机的外卖下单方法、设备及可读存储介质
CN115497505A (zh) * 2022-08-23 2022-12-20 惠州华阳通用电子有限公司 一种车载音乐识别方法
CN118968982A (zh) * 2024-08-05 2024-11-15 赣州得辉达科技有限公司 基于数据分析的音箱控制管理方法及系统

Also Published As

Publication number Publication date
CN109785859A (zh) 2019-05-21
CN109785859B (zh) 2024-02-02

Similar Documents

Publication Publication Date Title
WO2020155490A1 (zh) 基于语音分析的管理音乐的方法、装置和计算机设备
CN107623614B (zh) 用于推送信息的方法和装置
JP6113302B2 (ja) 音声データの伝送方法及び装置
CN112216294A (zh) 音频处理方法、装置、电子设备及存储介质
US10854182B1 (en) Singing assisting system, singing assisting method, and non-transitory computer-readable medium comprising instructions for executing the same
CN110675886A (zh) 音频信号处理方法、装置、电子设备及存储介质
CN110889008B (zh) 一种音乐推荐方法、装置、计算装置和存储介质
CN115881145B (zh) 语音处理和训练方法以及电子设备
CN107274876A (zh) 一种听音绘谱仪
CN105280196A (zh) 副歌检测方法及系统
WO2019233361A1 (zh) 对音乐进行音量调节的方法及设备
CN106205652A (zh) 一种音频跟读评测方法及装置
WO2014173325A1 (zh) 喉音识别方法及装置
CN107679196A (zh) 一种多媒体识别方法、电子设备及存储介质
CN112349266A (zh) 一种语音编辑方法及相关设备
US20160034247A1 (en) Extending Content Sources
TWI831822B (zh) 語音處理方法與資訊裝置
CN105810219B (zh) 多媒体文件的播放方法、播放系统和音频终端
CN116110431B (zh) 歌唱音准评分方法及其装置、设备、介质、产品
CN105632523A (zh) 调节音频数据的音量输出值的方法和装置及终端
CN113196384B (zh) 在请求时间将补充音频内容动态插入到音频记录中的方法和系统
CN113220913B (zh) 多媒体文件处理方法、装置和交互系统
CN100458914C (zh) 语音识别系统以及方法
WO2022041177A1 (zh) 通信消息处理方法、设备及即时通信客户端
CN116403570A (zh) 音频数据处理方法、装置及电子设备

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: 19912346

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: 19912346

Country of ref document: EP

Kind code of ref document: A1