WO2017113974A1 - Procédé et dispositif de traitement de la parole, et terminal - Google Patents

Procédé et dispositif de traitement de la parole, et terminal Download PDF

Info

Publication number
WO2017113974A1
WO2017113974A1 PCT/CN2016/104016 CN2016104016W WO2017113974A1 WO 2017113974 A1 WO2017113974 A1 WO 2017113974A1 CN 2016104016 W CN2016104016 W CN 2016104016W WO 2017113974 A1 WO2017113974 A1 WO 2017113974A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
information
processing
sensitive
emotional state
Prior art date
Application number
PCT/CN2016/104016
Other languages
English (en)
Chinese (zh)
Inventor
聂影
刘东海
许行
Original Assignee
宇龙计算机通信科技(深圳)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 宇龙计算机通信科技(深圳)有限公司 filed Critical 宇龙计算机通信科技(深圳)有限公司
Publication of WO2017113974A1 publication Critical patent/WO2017113974A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
    • 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
    • G10L25/63—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 estimating an emotional state
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
    • H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
    • H04M1/72436—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for text messaging, e.g. short messaging services [SMS] or e-mails
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/725—Cordless telephones

Definitions

  • the present invention relates to the field of voice communication technologies, and in particular, to a method, an apparatus, and a terminal for voice processing.
  • the communication terminal may detect and acquire an emotional state of the terminal user, and issue a corresponding control instruction according to the emotional state, so as to enable a preset application that can adjust the emotional state of the terminal user.
  • the technical problem to be solved by the embodiments of the present invention is to provide a method, a device, and a terminal for voice processing, which can improve the true reliability of voice information transmission.
  • the embodiment of the present invention provides a method for voice processing, where the method includes:
  • the performing voice processing on the acquired voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information.
  • the method before determining whether to enable the voice processing function according to the determined emotional state information, the method further includes:
  • the voice processing permission is used to determine whether to enable the voice processing function
  • the performing voice processing on the obtained voice information according to the preset voice response table includes:
  • the sensitive vocabulary is converted into a replacement vocabulary corresponding to the sensitive vocabulary in the preset voice response table.
  • the performing voice processing on the obtained voice information according to the preset voice response table includes:
  • the voice information includes a sensitive vocabulary
  • the voice information is intercepted, and the prompt information is sent, and the prompt information is used to prompt that the sensitive information indicated by the sensitive vocabulary in the voice information is unreasonable.
  • the emotional state information is determined according to one or more combinations of volume, tone, frequency, and type of the voice information; or determined by collecting facial feature information of the user during a voice call.
  • an embodiment of the present invention provides a device for voice processing, where the device includes:
  • a determining module configured to determine a current emotional state information of the user when the voice call event is detected; and further determining whether to enable the voice processing function according to the determined emotional state information;
  • a processing module configured to: when the determining module determines to enable the voice processing function, perform voice processing on the obtained voice information according to the preset voice response table;
  • the performing voice processing on the acquired voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information.
  • the device further includes:
  • Obtaining a module configured to obtain a state type corresponding to the user's emotional state information
  • a configuration module configured to configure a corresponding voice processing authority for each state type obtained by the acquiring module; the voice processing permission is used to determine whether the voice processing function is enabled;
  • a generating module configured to generate a preset voice switch configuration table according to the user emotional state information acquired by the acquiring module and the voice processing authority configured by the configuration module, so that the determining module is configured according to the preset voice switch configuration table Performing the determining, according to the determined emotional state information, whether to enable the voice processing function.
  • the processing module is specifically configured to detect whether the voice information includes a sensitive vocabulary; when detecting that the voice information includes a sensitive vocabulary, converting the sensitive vocabulary into the preset voice response table The replacement vocabulary corresponding to the sensitive vocabulary.
  • the processing module is specifically configured to detect whether the voice information includes a sensitive vocabulary; when detecting that the voice information includes a sensitive vocabulary, determine whether the sensitive information indicated by the sensitive vocabulary is reasonable, and if the judgment is unreasonable And intercepting the voice information, and sending prompt information, where the prompt information is used to prompt that the sensitive information indicated by the sensitive vocabulary in the voice information is unreasonable.
  • the emotional state information is determined according to one or more of a volume, a tone, a frequency, and a type of the voice information; or, by collecting facial feature information of the user during a voice call.
  • an embodiment of the present invention further provides a terminal, where the terminal includes the voice processing device.
  • the voice response table is configured to perform voice processing on the obtained voice information, where the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information, so as to prevent the terminal user from being In some bad emotional state, the wrong voice information is sent to the answering party, thereby improving the authenticity and reliability of the voice information transmission.
  • FIG. 1 is a schematic flow chart of a voice processing method according to an embodiment of the present invention.
  • FIG. 2 is a schematic flow chart of another voice processing method according to an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a voice processing device according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of another voice processing apparatus according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
  • the embodiment of the invention provides a method and a device for displaying the processing result, so as to perform a quick search on the keyword and obtain the result information that the user most wants, which is simple in operation and high in efficiency.
  • FIG. 1 is a schematic flowchart of a voice processing method according to an embodiment of the present invention.
  • the method in the embodiment of the present invention may be applied to a terminal with a communication network function, such as a smart phone, a tablet computer, or a smart wearable device. Specifically, it can be implemented by a processor of these communication terminals.
  • the method of the embodiment of the invention further includes the following steps.
  • the terminal when the communication terminal detects that the terminal user uses the terminal to perform a voice call (such as voice chat, voice video, etc.), the terminal may trigger the camera of the terminal to capture the current facial expression feature information of the user. Determining, according to the facial expression feature information, the current emotional state information of the user (such as capturing the collected facial expression feature information as anger, the current user emotional state information determined by the communication terminal is anger); or, the communication terminal collects the voice call
  • the voice information in the process determines the current emotional state information of the user by analyzing one or more of the characteristics of the volume, tone, frequency, type, and the like in the voice information (eg, the volume in the voice information is large, and the speaking speed is fast (that is, the frequency is fast), then the current emotional state information of the user determined by the communication terminal is arrogant).
  • the communication terminal may upload the current facial feature expression information of the user collected by the terminal to the cloud server, and the cloud server receives and analyzes the current emotional state information of the user corresponding to the facial feature expression information, where The cloud server may further return the analyzed current emotional state information of the user to the communication terminal, where the communication terminal receives the current emotional state information of the user returned by the cloud server; similarly, the communication terminal may also Transmitting the voice information collected by the terminal during the voice call to the cloud server, where the cloud server receives the voice information, and by analyzing characteristics such as volume, tone, frequency, and type in the voice information One or more of the current emotional state information of the user corresponding to the voice information, and the cloud server may further return the analyzed current emotional state information of the user to the communication terminal, where the communication terminal Receiving the current emotional state letter of the user returned by the cloud server .
  • the communication terminal may include an Internet device such as a personal computer, a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palmtop computer, a mobile Internet device (MID), or a wearable smart device, and the embodiment of the present invention Not limited.
  • an Internet device such as a personal computer, a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palmtop computer, a mobile Internet device (MID), or a wearable smart device, and the embodiment of the present invention Not limited.
  • S102 Determine, according to the emotional state information, whether to enable the voice processing function.
  • the communication terminal may collect facial feature expression information and/or voice information of the user during the voice communication process, and the communication terminal determines, according to the collected facial feature expression information and/or the voice information.
  • the user's emotional state information (such as happy, excited, happy, sad, angry, etc.)
  • the communication terminal may also classify all or part of the determined user emotional state information to obtain at least one state type.
  • several common user emotional state information and a state type corresponding to the user emotional state information are given in Table 1 below.
  • the communication terminal may further configure a corresponding voice processing authority for each state type obtained by the classification, where the voice processing authority is used by the communication terminal to determine whether the terminal performs the voice processing function of the terminal; the communication terminal
  • a preset voice switch configuration table may be generated according to each user state information in the state type and voice processing rights configured for the state type. Illustratively, a preset voice switch configuration table is given in Table 2 below.
  • the communication terminal may determine, according to the emotional state information determined by S101 and the generated voice switch configuration table, whether the communication terminal starts the voice processing function of the terminal.
  • the communication terminal may obtain the information with the emotional state information as angry.
  • the corresponding status type is anger. Referring to the voice switch configuration table preset in Table 2, the communication terminal can determine that when the status type is anger, the communication terminal turns on the voice processing function of the terminal.
  • the terminal user or the system may set a voice response table for performing voice processing in the communication terminal in advance; when the communication terminal determines in S102 that the voice processing function of the terminal is turned on, the communication terminal may be according to the terminal.
  • the preset voice response table performs voice processing on the obtained voice information. Illustratively, as shown in Table 3 below, a preset speech response table is presented.
  • the communication terminal may detect whether the voice information includes a sensitive vocabulary (such as a rude vocabulary, etc.), and if the communication terminal detects that a sensitive vocabulary exists in the voice information, the communication terminal according to the terminal
  • the preset voice response table replaces the sensitive vocabulary with a replacement vocabulary corresponding to the sensitive vocabulary in the voice response table (as in Table 3, "going out” is replaced with "please go away")
  • the communication terminal may transmit the processed voice information (that is, the voice information including the replacement vocabulary) to the answering party; and/or,
  • the communication terminal may detect whether the voice information includes a sensitive vocabulary (such as a decision regarding money, etc.), and if the communication terminal detects that there is a sensitive vocabulary in the voice information, the communication terminal may follow the preset
  • the voice response table determines whether the sensitive information indicated by the sensitive vocabulary is reasonable.
  • the communication terminal intercepts the voice information including the sensitive vocabulary. And sending one or more prompt information, the prompt information is used to prompt the end user to send the voice information including the sensitive vocabulary unreasonable or prompt the user to think twice.
  • the voice response table is configured to perform voice processing on the obtained voice information, where the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information, so as to prevent the terminal user from being In some bad emotional state, the wrong voice information is sent to the answering party, thereby improving the authenticity and reliability of the voice information transmission.
  • FIG. 2 is a schematic flowchart of another voice processing method according to an embodiment of the present invention.
  • the method in the embodiment of the present invention can be applied to a terminal with a communication network function, such as a smart phone, a tablet computer, or a smart wearable device.
  • the specifics can be implemented by the processors of these communication terminals.
  • the method of the embodiment of the invention further includes the following steps.
  • S205 Determine, according to the emotional state information and the preset voice switch configuration table, whether to enable the voice processing function.
  • the terminal user or the system may set a voice response table for performing voice processing in the communication terminal in advance; when the communication terminal determines to turn on the voice processing function of the terminal in S206, and detects that the voice information is included in the voice information.
  • the communication terminal may replace the sensitive vocabulary in the acquired voice information with the replacement vocabulary corresponding to the sensitive vocabulary in the voice response table according to the voice response table preset in the terminal (as in Table 3 above). Replace "going out” with "please go away”).
  • the communication terminal when the communication terminal determines to turn on the voice processing function of the terminal in S206, and detects that the voice information includes a sensitive vocabulary, the communication terminal may determine, according to the preset voice response table, Whether the sensitive information indicated by the sensitive vocabulary is reasonable; when the communication terminal determines that it is reasonable, the step S210 is continued; when the communication terminal determines that it is unreasonable, the step S209 is continued.
  • the communication terminal may upload the sensitive vocabulary in the voice information to a cloud server, where the cloud server stores all or part of daily data recorded by the terminal user on the communication terminal;
  • the server may analyze whether the sensitive information indicated by the sensitive vocabulary is reasonable according to the data stored in the server for affecting whether the sensitive information indicated by the sensitive vocabulary is reasonable, and the cloud server returns the judgment result to the location.
  • the communication terminal further performing an operation according to a determination result returned by the cloud server, that is, when the determination result received by the communication terminal is reasonable, the communication terminal may include the sensitive vocabulary
  • the voice information is sent to the answering party; when the judgment result received by the communication terminal is unreasonable, the step S209 is continued; or, when the cloud server determines that the sensitive information indicated by the sensitive vocabulary is unreasonable, Sending an interception prompt instruction to the communication terminal, the communication end Responding to the intercepting prompt instruction to perform step S209; when the cloud server determines that the sensitive information indicated by the sensitive vocabulary is reasonable, sending a voice information sending instruction to the communication terminal, the communication terminal responding to the The voice information sending instruction sends the voice information including the sensitive vocabulary to the answering party.
  • the communication terminal analyzes whether the sensitive information indicated by the sensitive vocabulary is reasonable according to data stored in the terminal for influencing whether the sensitive information indicated by the sensitive vocabulary is reasonable, and when the communication terminal determines When it is reasonable, the communication terminal may send the voice information including the sensitive vocabulary to the answering party; when the communication terminal determines that it is unreasonable, proceed to step S209.
  • step S207 and step S208 may be juxtaposed, that is, the communication terminal may select any one of S207 and S208 to perform, or both S207 and S208, and the order of S207 and S208 is variable. That is, the communication terminal may perform S208 after executing S208, which is not limited in the embodiment of the present invention.
  • the voice response table is configured to perform voice processing on the obtained voice information, where the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information, so as to prevent the terminal user from being In some bad emotional state, the wrong voice information is sent to the answering party, thereby improving the authenticity and reliability of the voice information transmission.
  • FIG. 3 is a schematic structural diagram of a voice processing device according to an embodiment of the present invention.
  • the device in the embodiment of the present invention may be disposed in a terminal with a communication network function, such as a smart phone, a tablet computer, or a smart wearable device.
  • the device 3 includes:
  • the determining module 30 is configured to determine a current emotional state information of the user when the voice call event is detected; and further determine whether to enable the voice processing function according to the determined emotional state information;
  • the processing module 31 is configured to: when the determining module 30 determines that the voice processing function is enabled, perform voice processing on the obtained voice information according to the preset voice response table;
  • the performing the voice processing on the obtained voice information to obtain the voice processing information includes: converting processing or prompting processing on the sensitive vocabulary in the acquired voice information.
  • the voice response table is configured to perform voice processing on the obtained voice information, where the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information, so as to prevent the terminal user from being In some bad emotional state, the wrong voice information is sent to the answering party, thereby improving the authenticity and reliability of the voice information transmission.
  • FIG. 4 it is a schematic structural diagram of another voice processing device according to an embodiment of the present invention.
  • the device in the embodiment of the present invention may be disposed in a communication network such as a smart phone, a tablet computer, or a smart wearable device.
  • the device 4 includes a determining module 30 and a processing module 31, and further includes:
  • the obtaining module 32 is configured to obtain a state type corresponding to the user's emotional state information
  • the configuration module 33 is configured to configure a corresponding voice processing authority for each state type acquired by the obtaining module 32; the voice processing authority is used to determine whether to enable the voice processing function;
  • the generating module 34 is configured to generate a preset voice switch configuration table according to the user emotion state information acquired by the acquiring module 32 and the voice processing authority configured by the configuration module 33, so that the determining module is configured according to the preset voice
  • the switch configuration table performs the determining, according to the determined emotional state information, whether to enable the voice processing function.
  • the processing module 31 is specifically configured to detect whether the voice information includes a sensitive vocabulary; when detecting that the voice information includes a sensitive vocabulary, converting the sensitive vocabulary into the preset voice response table The replacement vocabulary corresponding to the sensitive vocabulary
  • the processing module 31 is specifically configured to detect whether the voice information includes a sensitive vocabulary; when detecting that the voice information includes a sensitive vocabulary, determine whether the sensitive information indicated by the sensitive vocabulary is reasonable, and if it is determined not to If it is reasonable, the voice information is intercepted, and the prompt information is sent, and the prompt information is used to prompt the sensitive information indicated by the sensitive vocabulary in the voice information to be unreasonable.
  • the emotional state information is determined according to one or more of a volume, a tone, a frequency, and a type of the voice information; or, by collecting facial feature information of the user during a voice call.
  • the voice response table is configured to perform voice processing on the obtained voice information, where the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information, so as to prevent the terminal user from being In some bad emotional state, the wrong voice information is sent to the answering party, thereby improving the authenticity and reliability of the voice information transmission.
  • the terminal may be a device with a communication network function, such as a smart phone, a tablet computer, or a smart wearable device.
  • the terminal in the embodiment of the present invention may include a display screen, a button, a speaker, a pickup, and the like.
  • the processor 502 can call the code stored in the memory 503 via the bus 501 to perform related functions.
  • the processor 502 is configured to determine, when the voice call event is detected, the current emotional state information of the user; determine, according to the emotional state information, whether to enable the voice processing function; when determining to enable the voice processing function, according to The preset voice response table performs voice processing on the obtained voice information.
  • the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information.
  • the processor 502 is further configured to: obtain a state type corresponding to the user's emotional state information; configure a corresponding voice processing authority for each state type; and the voice processing permission is used to determine whether to enable the voice processing function. Generating a preset voice switch configuration table according to the user's emotional state information and the voice processing authority, so as to perform the determining according to the determined voice state configuration table according to the preset voice switch configuration table, and determining whether to enable voice Processing function.
  • the processor 502 is further configured to detect whether the voice information includes a sensitive vocabulary; and when detecting that the voice information includes a sensitive vocabulary, converting the sensitive vocabulary into the preset voice A replacement vocabulary corresponding to the sensitive vocabulary in the response table.
  • the processor 502 is further configured to detect whether the voice information includes a sensitive vocabulary; and when detecting that the voice information includes a sensitive vocabulary, determine whether the sensitive information indicated by the sensitive vocabulary is reasonable; If it is determined that the information is unreasonable, the voice information is intercepted, and the prompt information is sent, and the prompt information is used to prompt that the sensitive information indicated by the sensitive vocabulary in the voice information is unreasonable.
  • the processor 502 is further configured to determine, according to one or more combinations of volume, tone, frequency, and type of the voice information, or by collecting a voice call process. The user's facial feature information is determined.
  • the voice response table is configured to perform voice processing on the obtained voice information, where the voice processing on the obtained voice information includes: converting processing or prompting processing on sensitive words in the acquired voice information, so as to prevent the terminal user from being In some bad emotional state, the wrong voice information is sent to the answering party, thereby improving the authenticity and reliability of the voice information transmission.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes some or all of the steps of the operation method of any of the audio playback applications described in the foregoing method embodiments.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Health & Medical Sciences (AREA)
  • Child & Adolescent Psychology (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Telephone Function (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

La présente invention concerne, selon un mode de réalisation, un procédé et un dispositif de traitement de la parole, et un terminal. Le procédé comporte les étapes consistant à : lors de la détection d'un événement de communication vocale, déterminer des informations se rapportant à l'état de l'humeur en cours d'un utilisateur ; déterminer, en fonction des informations se rapportant à l'état de l'humeur, s'il faut démarrer ou non une fonction de traitement de la parole ; et s'il est déterminé que la fonction de traitement de la parole doit être démarrée, effectuer un traitement de la parole sur les informations vocales acquises en fonction d'une table de réponses vocales prédéfinies, dans lequel le traitement de la parole effectué sur les informations vocales acquises comporte : l'étape consistant à effectuer une reformulation ou une suggestion concernant un terme sensible dans les informations vocales acquises. La présente invention peut faciliter l'expression de la signification réelle souhaitée être communiquée par des informations vocales.
PCT/CN2016/104016 2015-12-30 2016-10-31 Procédé et dispositif de traitement de la parole, et terminal WO2017113974A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201511022337.3 2015-12-30
CN201511022337.3A CN105681546A (zh) 2015-12-30 2015-12-30 一种语音处理的方法、装置以及终端

Publications (1)

Publication Number Publication Date
WO2017113974A1 true WO2017113974A1 (fr) 2017-07-06

Family

ID=56298149

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/104016 WO2017113974A1 (fr) 2015-12-30 2016-10-31 Procédé et dispositif de traitement de la parole, et terminal

Country Status (2)

Country Link
CN (1) CN105681546A (fr)
WO (1) WO2017113974A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109256151A (zh) * 2018-11-21 2019-01-22 努比亚技术有限公司 通话语音调控方法、装置、移动终端及可读存储介质
US10748644B2 (en) 2018-06-19 2020-08-18 Ellipsis Health, Inc. Systems and methods for mental health assessment
CN111696538A (zh) * 2020-06-05 2020-09-22 北京搜狗科技发展有限公司 语音处理方法、装置和介质
CN111783447A (zh) * 2020-05-28 2020-10-16 中国平安财产保险股份有限公司 基于ngram距离的敏感词检测方法、装置、设备及存储介质
CN112309403A (zh) * 2020-03-05 2021-02-02 北京字节跳动网络技术有限公司 用于生成信息的方法和装置
US11120895B2 (en) 2018-06-19 2021-09-14 Ellipsis Health, Inc. Systems and methods for mental health assessment

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105681546A (zh) * 2015-12-30 2016-06-15 宇龙计算机通信科技(深圳)有限公司 一种语音处理的方法、装置以及终端
CN107659538A (zh) * 2016-07-25 2018-02-02 北京优朋普乐科技有限公司 一种视频处理的方法及设备
CN107948417A (zh) * 2017-11-22 2018-04-20 周燕红 一种语音数据监控的方法、装置、终端及存储介质
CN107919138B (zh) * 2017-11-30 2021-01-08 维沃移动通信有限公司 一种语音中的情绪处理方法及移动终端
CN110085221A (zh) * 2018-01-26 2019-08-02 上海智臻智能网络科技股份有限公司 语音情感交互方法、计算机设备和计算机可读存储介质
CN108197115B (zh) * 2018-01-26 2022-04-22 上海智臻智能网络科技股份有限公司 智能交互方法、装置、计算机设备和计算机可读存储介质
CN110085220A (zh) * 2018-01-26 2019-08-02 上海智臻智能网络科技股份有限公司 智能交互装置
CN110085262A (zh) * 2018-01-26 2019-08-02 上海智臻智能网络科技股份有限公司 语音情绪交互方法、计算机设备和计算机可读存储介质
CN109213468B (zh) * 2018-08-23 2020-04-28 阿里巴巴集团控股有限公司 一种语音播放方法和装置
CN109714248B (zh) * 2018-12-26 2021-05-18 联想(北京)有限公司 一种数据处理方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070286386A1 (en) * 2005-11-28 2007-12-13 Jeffrey Denenberg Courteous phone usage system
CN101662546A (zh) * 2009-09-16 2010-03-03 中兴通讯股份有限公司 情绪监控的方法及装置
CN103516915A (zh) * 2012-06-27 2014-01-15 百度在线网络技术（北京）有限公司 在移动终端通话过程中敏感词汇的替换方法、系统及装置
CN103903627A (zh) * 2012-12-27 2014-07-02 中兴通讯股份有限公司 一种语音数据的传输方法及装置
CN104616666A (zh) * 2015-03-03 2015-05-13 广东小天才科技有限公司 一种基于语音分析改善对话沟通效果的方法及装置
CN105681546A (zh) * 2015-12-30 2016-06-15 宇龙计算机通信科技(深圳)有限公司 一种语音处理的方法、装置以及终端

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093752A (zh) * 2013-01-16 2013-05-08 华南理工大学 一种基于手机语音的情感分析方法及其系统
CN104113634A (zh) * 2013-04-22 2014-10-22 三星电子（中国）研发中心 一种对语音进行处理的方法
CN103269405A (zh) * 2013-05-23 2013-08-28 深圳市中兴移动通信有限公司 友好提示的方法及装置
CN103491251A (zh) * 2013-09-24 2014-01-01 深圳市金立通信设备有限公司 一种监控用户通话的方法及终端

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070286386A1 (en) * 2005-11-28 2007-12-13 Jeffrey Denenberg Courteous phone usage system
CN101662546A (zh) * 2009-09-16 2010-03-03 中兴通讯股份有限公司 情绪监控的方法及装置
CN103516915A (zh) * 2012-06-27 2014-01-15 百度在线网络技术（北京）有限公司 在移动终端通话过程中敏感词汇的替换方法、系统及装置
CN103903627A (zh) * 2012-12-27 2014-07-02 中兴通讯股份有限公司 一种语音数据的传输方法及装置
CN104616666A (zh) * 2015-03-03 2015-05-13 广东小天才科技有限公司 一种基于语音分析改善对话沟通效果的方法及装置
CN105681546A (zh) * 2015-12-30 2016-06-15 宇龙计算机通信科技(深圳)有限公司 一种语音处理的方法、装置以及终端

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10748644B2 (en) 2018-06-19 2020-08-18 Ellipsis Health, Inc. Systems and methods for mental health assessment
US11120895B2 (en) 2018-06-19 2021-09-14 Ellipsis Health, Inc. Systems and methods for mental health assessment
US11942194B2 (en) 2018-06-19 2024-03-26 Ellipsis Health, Inc. Systems and methods for mental health assessment
CN109256151A (zh) * 2018-11-21 2019-01-22 努比亚技术有限公司 通话语音调控方法、装置、移动终端及可读存储介质
CN109256151B (zh) * 2018-11-21 2023-06-27 努比亚技术有限公司 通话语音调控方法、装置、移动终端及可读存储介质
CN112309403A (zh) * 2020-03-05 2021-02-02 北京字节跳动网络技术有限公司 用于生成信息的方法和装置
CN111783447A (zh) * 2020-05-28 2020-10-16 中国平安财产保险股份有限公司 基于ngram距离的敏感词检测方法、装置、设备及存储介质
CN111783447B (zh) * 2020-05-28 2023-02-03 中国平安财产保险股份有限公司 基于ngram距离的敏感词检测方法、装置、设备及存储介质
CN111696538A (zh) * 2020-06-05 2020-09-22 北京搜狗科技发展有限公司 语音处理方法、装置和介质
CN111696538B (zh) * 2020-06-05 2023-10-31 北京搜狗科技发展有限公司 语音处理方法、装置和介质

Also Published As

Publication number Publication date
CN105681546A (zh) 2016-06-15

Similar Documents

Publication Publication Date Title
WO2017113974A1 (fr) Procédé et dispositif de traitement de la parole, et terminal
WO2018070780A1 (fr) Dispositif électronique et son procédé de commande
WO2019174090A1 (fr) Procédé, appareil et dispositif de commande de partage de fichier de capture d'écran, et support de stockage informatique
WO2018018695A1 (fr) Procédé et dispositif de gestion de gel d'application, et terminal
US20120196580A1 (en) Methods and apparatuses for tactile caller identification in hearing-impaired communication systems
WO2015053541A1 (fr) Procédé et appareil pour afficher des informations associées dans un dispositif électronique
WO2015009066A1 (fr) Procédé de fonctionnement d'un service de conversation basé sur une application de messagerie, interface utilisateur et dispositif électronique employant ce procédé et cette interface
WO2017012404A1 (fr) Procédé et terminal de gestion de groupes, et support de stockage
WO2016123898A1 (fr) Procédé de gestion de message court et terminal mobile associé
WO2020253115A1 (fr) Procédé, appareil et dispositif de recommandation de produit basés sur une reconnaissance vocale et support de stockage
WO2021172832A1 (fr) Procédé de modification d'image basée sur la reconnaissance des gestes, et dispositif électronique prenant en charge celui-ci
WO2018035929A1 (fr) Procédé et appareil de traitement de code de vérification
WO2020155773A1 (fr) Procédé de surveillance d'entrée de texte suspecte, dispositif, appareil informatique et support de sockage
WO2015126097A1 (fr) Serveur interactif et procédé permettant de commander le serveur
WO2015199430A1 (fr) Procédé et appareil de gestion de données
WO2018149081A1 (fr) Procédé, dispositif, et terminal de traitement d'informations vocales d'appel de suivi, et support de stockage
WO2016182393A1 (fr) Procédé et dispositif d'analyse de l'émotion d'un utilisateur
WO2021017332A1 (fr) Procédé permettant de signaler une erreur de commande vocale, appareil électrique et support d'informations lisible par ordinateur
WO2018058955A1 (fr) Procédé et système anti-perte pour terminal portable, et terminal portable
WO2014133227A1 (fr) Système pour fournir des informations de présence en utilisant des données audio, et appareil et procédé associés
WO2018151486A1 (fr) Dispositif électronique et procédé de sortie de données de message de dispositif électronique
WO2017039250A1 (fr) Dispositif de communication vidéo et son fonctionnement
WO2017065477A1 (fr) Procédé d'enregistrement d'écran d'exécution et dispositif de traitement électronique associé
WO2015009037A1 (fr) Procédé et dispositif de formation d'un groupe en utilisant des informations d'historique de communications
WO2020034531A1 (fr) Procédé et appareil de nettoyage d'espace, dispositif et support de stockage lisible par ordinateur

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: 16880765

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: 16880765

Country of ref document: EP

Kind code of ref document: A1