WO2015154412A1 - Procédé et dispositif de réveil de système de commande vocale et terminal - Google Patents

Procédé et dispositif de réveil de système de commande vocale et terminal Download PDF

Info

Publication number
WO2015154412A1
WO2015154412A1 PCT/CN2014/088872 CN2014088872W WO2015154412A1 WO 2015154412 A1 WO2015154412 A1 WO 2015154412A1 CN 2014088872 W CN2014088872 W CN 2014088872W WO 2015154412 A1 WO2015154412 A1 WO 2015154412A1
Authority
WO
WIPO (PCT)
Prior art keywords
sound
voiceprint
syllable
control system
voice control
Prior art date
Application number
PCT/CN2014/088872
Other languages
English (en)
Chinese (zh)
Inventor
安顺钰
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2015154412A1 publication Critical patent/WO2015154412A1/fr

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification techniques
    • G10L17/22Interactive procedures; Man-machine interfaces

Definitions

  • the present invention relates to the field of communications, and in particular, to a method, an apparatus, and a terminal for waking up a voice control system.
  • Voice control has gradually become the mainstream of modern interaction.
  • most of the current voice control is still activated by the touch mode, and the advantages of voice control cannot be maximized, and the hands are freed to liberate the eyes.
  • a small part can wake up the voice control system through fixed phrases, but these fixed phrases are already set before the terminal leaves the factory, can not be changed, and the false recognition rate is very high, which greatly hinders the user from using the voice control system.
  • the phrase is fixed and unchangeable, any user can wake up the voice control system, and there is a big security risk. How to start the voice control system in an intuitive and safe way is an urgent problem to be solved.
  • the invention provides a method, a device and a terminal for waking up a voice control system, so as to at least solve the problem that the method for waking up the voice control system in the related art has low accuracy and high security risk.
  • a method for waking up a voice control system includes: receiving a sound for waking up a voice control system; determining whether a voiceprint portion of the voice sound wave is within a first predetermined threshold; Whether the syllable portion in the sound wave is within the second predetermined threshold; if the determination result is yes, the voice control system is woken up.
  • the voice control system before receiving the sound for waking up the voice control system, further comprising: recording the sound at least twice; recording the voiceprint portion and the syllable portion of the recorded at least two sound sound waves; The voiceprint portion and the syllable portion determine the first predetermined threshold and the second predetermined threshold.
  • recording the voiceprint portion and the syllable portion in the at least two sound sound waves recorded includes: selecting a sound that meets a predetermined condition from the at least two recorded sounds, wherein the predetermined condition includes at least The variation of the amplitude and/or frequency of the voiceprint portion and the syllable portion is within a predetermined range; the voiceprint portion and the syllable portion in the selected sound sound wave are recorded.
  • recording the voiceprint portion and the syllable portion in the selected sound sound wave comprises: simultaneously recording the voiceprint portion and the syllable portion; storing the recorded voiceprint portion and the syllable portion in the same In the word.
  • the first predetermined threshold comprises at least one of: an amplitude threshold of the voiceprint portion, a frequency threshold of the voiceprint portion; or, the second predetermined threshold includes at least one of: an amplitude threshold of the syllable portion, a syllable Part of the frequency threshold.
  • an apparatus for waking up a voice control system includes: a receiving module configured to receive a sound for waking up a voice control system; and a determining module configured to determine a voiceprint in the sound sound wave Whether the portion is within the first predetermined threshold and whether the syllable portion of the sound sound wave is within the second predetermined threshold; the wake-up module is configured to wake up the voice control if the determination result of the determining module is yes system.
  • the device for waking up the voice control system further comprises: a recording module configured to record the sound at least twice; and a recording module configured to record the voiceprint portion and the syllable in the recorded at least two sound sound waves And a determining module configured to determine the first predetermined threshold and the second predetermined threshold based on the voiceprint portion and the syllable portion.
  • the recording module includes: a selection unit configured to select a sound that meets a predetermined condition from the at least two recorded sounds, wherein the predetermined condition includes at least an amplitude of the voiceprint portion and the syllable portion And/or the change in frequency is within a predetermined range; the recording unit is arranged to record the voiceprint portion and the syllable portion in the selected sound sound wave.
  • a selection unit configured to select a sound that meets a predetermined condition from the at least two recorded sounds, wherein the predetermined condition includes at least an amplitude of the voiceprint portion and the syllable portion And/or the change in frequency is within a predetermined range; the recording unit is arranged to record the voiceprint portion and the syllable portion in the selected sound sound wave.
  • the recording unit includes: a recording subunit configured to simultaneously record the voiceprint portion and the syllable portion; and a storage subunit configured to store the recorded voiceprint portion and the syllable portion in the same In a word.
  • a terminal comprising the apparatus of any of the above.
  • the present invention receiving a sound for waking up the voice control system; determining whether the voiceprint portion of the sound sound wave is within a first predetermined threshold and whether the syllable portion of the sound wave is within a second predetermined threshold; If the result is yes, the voice control system is awakened, and the problem of high security risks of the wake-up voice control system existing in the related art is solved, thereby achieving the effect of improving the security of the terminal.
  • FIG. 1 is a flow chart of a method for waking up a voice control system in accordance with an embodiment of the present invention
  • FIG. 2 is a structural block diagram of an apparatus for waking up a voice control system according to an embodiment of the present invention
  • FIG. 3 is a block diagram showing a preferred structure of an apparatus for waking up a voice control system according to an embodiment of the present invention
  • FIG. 4 is a block diagram showing the structure of a recording module 32 in an apparatus for waking up a voice control system according to an embodiment of the present invention
  • FIG. 5 is a structural block diagram of a recording unit 44 in an apparatus for waking up a voice control system according to an embodiment of the present invention
  • FIG. 6 is a structural block diagram of a terminal according to an embodiment of the present invention.
  • FIG. 7 is a block diagram showing the structure of a system according to an embodiment of the present invention.
  • FIG. 8 is a flow chart of wake-up voice control in accordance with an embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for waking up a voice control system according to an embodiment of the present invention. As shown in FIG. 1, the process includes the following steps:
  • Step S102 receiving a sound for waking up the voice control system
  • Step S104 determining whether the voiceprint portion in the sound sound wave is within a first predetermined threshold and whether the syllable portion in the sound wave is within a second predetermined threshold;
  • step S106 if the determination result is yes, the voice control system is woken up.
  • the wake-up word can be pre-recorded, that is, the sound can be recorded at least twice before receiving the sound for waking up the voice control system; recording the recorded sound waves at least twice a voiceprint portion and a syllable portion; determining a first predetermined threshold and a second predetermined threshold based on the recorded voiceprint portion and the syllable portion. That is to say, the wake-up words can be customized, and the voice control system is awakened according to the customized wake-up words, thereby improving the wake-up rate of the wake-up voice control system.
  • recording the voiceprint portion and the syllable portion in the at least two recorded sound waves comprises: selecting a sound that meets a predetermined condition from at least two recorded sounds, wherein the predetermined condition includes at least sound The variation of the amplitude and/or frequency of the land portion and the syllable portion is within a predetermined range; the voiceprint portion and the syllable portion in the selected sound sound wave are recorded. Selecting a sound that meets the predetermined condition can ensure that the threshold of the voiceprint portion and the threshold of the syllable portion are finally obtained.
  • recording the voiceprint portion and the syllable portion in the selected sound sound wave may include simultaneously recording the voiceprint portion and the syllable portion; storing the recorded voiceprint portion and the syllable portion in the same word.
  • the first predetermined threshold may include at least one of: an amplitude threshold of the voiceprint portion, a frequency threshold of the voiceprint portion; or, the second predetermined threshold may include at least one of: an amplitude threshold of the syllable portion, a frequency of the syllable portion Threshold.
  • a device for waking up the voice control system is provided, and the device is used to implement the foregoing embodiments and preferred embodiments, and details are not described herein.
  • the term "module” may implement a combination of software and/or hardware of a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • the apparatus includes a receiving module 22, a determining module 24, and a waking module 26, which are described below.
  • the receiving module 22 is configured to receive a sound for waking up the voice control system;
  • the determining module 24 is connected to the receiving module 22, and is configured to determine whether the voiceprint portion in the sound sound wave is within a first predetermined threshold and the syllable in the sound sound wave Whether the portion is within the second predetermined threshold;
  • the wake-up module 26 is coupled to the determining module 24, and is configured to wake up the voice control system if the determination result of the determining module 24 is yes.
  • FIG. 3 is a block diagram showing a preferred structure of an apparatus for waking up a voice control system according to an embodiment of the present invention.
  • the apparatus includes a recording module 32, a recording module 34, and a determination, in addition to all the modules shown in FIG. Module 36.
  • the device will be described below.
  • the recording module 32 is configured to record sound at least twice; the recording module 34 is connected to the recording module 32, configured to record the voiceprint portion and the syllable portion of the recorded at least two sound sound waves; and the determining module 36 is connected to the above.
  • the recording module 34 and the receiving module 22 are arranged to determine a first predetermined threshold and a second predetermined threshold based on the voiceprint portion and the syllable portion.
  • FIG. 4 is a structural block diagram of a recording module 32 in an apparatus for waking up a voice control system according to an embodiment of the present invention.
  • the recording module 32 includes a selecting unit 42 and a recording unit 44, and the recording module 32 is performed below. Description.
  • the selecting unit 42 is configured to select a sound that satisfies a predetermined condition from at least two recorded sounds, wherein the predetermined condition includes at least a change in amplitude and/or frequency of the voiceprint portion and the syllable portion within a predetermined range; the recording unit 44 Connected to the above-described selection unit 42, arranged to record the voiceprint portion and the syllable portion in the selected sound sound wave.
  • FIG. 5 is a block diagram showing the structure of a recording unit 44 in an apparatus for waking up a voice control system. As shown in FIG. 5, the recording unit 44 includes a recording subunit 52 and a storage subunit 54. The recording unit 44 will be described below.
  • the recording subunit 52 is arranged to simultaneously record the voiceprint portion and the syllable portion; the storage subunit 54 is connected to the above-described recording subunit 52, and is arranged to store the recorded voiceprint portion and the syllable portion in the same word.
  • FIG. 6 is a structural block diagram of a terminal according to an embodiment of the present invention. As shown in FIG. 6, the terminal 60 includes the device 62 of the wake-up voice control system of any of the above.
  • a simple way to customize the wakeup of the voice system is provided for the problem that the security of the voice control system is high, so that the voice control system is intuitively and safely activated.
  • the user customizes the wake-up words of the voice control system and records them, and simultaneously records the user's voiceprint. Since the wake-up word includes the specified text and voiceprint, the wake-up rate can be greatly improved.
  • the user customizes the wake-up word and performs recording, and simultaneously records the voiceprint of the user.
  • FIG. 7 is a block diagram of a system structure according to an embodiment of the present invention.
  • the system includes the following parts: a touch screen module 71, a sound receiving module 72 (same as the above receiving module 22), and a recording module 73 (same as the above recording).
  • Module 32 voiceprint recording module 74 (same as the above-mentioned recording module 34), voice recognition module 75 (same as the above-mentioned judging module 24), storage module 76 (same as the above-mentioned recording unit 44), central processing module 77 (same as the above-mentioned determining module 36) ).
  • the touch screen module is set to control the recording process
  • the sound receiving module is set to receive the sound
  • the recording module is set to record the wake-up word
  • the voiceprint recording module is set to analyze the recorded sound waveform
  • the voice recognition module is set to analyze the recorded sound waveform
  • the storage module is set.
  • the central processor is set to process data.
  • FIG. 8 is a flow chart of wake-up voice control in accordance with an embodiment of the present invention. As shown in FIG. 8, the process includes the following steps:
  • Step S802 clicking a touch screen to start the program
  • Step S804 the sound receiving module acquires a sound
  • Step S806 the recording module records the sound and transmits the sound to the voiceprint recording module and the voice recognition module;
  • Step S808 the voiceprint recognition module analyzes and records the waveform diagram of the sound, and simultaneously identifies the waveform of the voiceprint portion in the sound wave;
  • Step S810 the voice recognition module analyzes and records the waveform of the sound, and simultaneously identifies the waveform of the syllable portion of the sound wave;
  • Step S812 the operator repeatedly records a number of times until the voiceprint recognition module can well identify the waveform threshold of the voiceprint portion of the sound wave, if not, then proceeds to step S806;
  • Step S814 the operator repeatedly records a number of times until the speech recognition module can well identify the waveform threshold of the syllable portion of the sound wave, if not, then proceeds to step S806;
  • Step S816 the storage module records the sound wave data, and the storage module stores the waveform threshold of the voiceprint portion and the waveform threshold of the syllable portion;
  • Step S820 the sound module receives the sound
  • Step S822 the central processing unit processes and transmits to the voiceprint recording module and the voice recognition module;
  • Step S824 the voiceprint recording module and the voice recognition module can compare the sound waves simultaneously or separately;
  • the wake-up word recording and the voiceprint recording can be completed at the same time.
  • modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein.
  • the steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module.
  • the invention is not limited to any specific combination of hardware and software.
  • the above embodiments and the preferred embodiments solve the problem that the method for waking up the voice control system in the related art has a high security risk, thereby achieving the effect of improving the security of the terminal.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Reverberation, Karaoke And Other Acoustics (AREA)
  • Telephone Function (AREA)

Abstract

L'invention concerne un procédé et un dispositif permettant de réveiller un système de commande vocale et un terminal. Le procédé comprend: la réception d'une voix utilisée pour réveiller un système de commande vocale (S102); la détermination si oui ou non une partie d'empreinte vocale dans une onde sonore de la voix est comprise dans une première valeur seuil prédéterminée et si oui ou non une partie de syllabe dans l'onde sonore est comprise dans une seconde valeur seuil prédéterminée (S104); et si la réponse aux deux déterminations est oui, le réveil du système de commande vocale (S106). Le procédé permet de résoudre le problème existant dans l'état de la technique selon lequel le risque de sécurité du procédé de réveil d'un système de commande vocale est élevé, et permet ainsi d'améliorer la sécurité du terminal.
PCT/CN2014/088872 2014-09-05 2014-10-17 Procédé et dispositif de réveil de système de commande vocale et terminal WO2015154412A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410453261.9A CN104282307A (zh) 2014-09-05 2014-09-05 唤醒语音控制系统的方法、装置及终端
CN201410453261.9 2014-09-05

Publications (1)

Publication Number Publication Date
WO2015154412A1 true WO2015154412A1 (fr) 2015-10-15

Family

ID=52257128

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/088872 WO2015154412A1 (fr) 2014-09-05 2014-10-17 Procédé et dispositif de réveil de système de commande vocale et terminal

Country Status (2)

Country Link
CN (1) CN104282307A (fr)
WO (1) WO2015154412A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108335695A (zh) * 2017-06-27 2018-07-27 腾讯科技(深圳)有限公司 语音控制方法、装置、计算机设备和存储介质
EP3385947A4 (fr) * 2015-11-30 2018-12-05 ZTE Corporation Procédé réalisant un réveil vocal, dispositif, terminal et support de stockage informatique

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105654949B (zh) * 2016-01-07 2019-05-07 北京云知声信息技术有限公司 一种语音唤醒方法及装置
CN106060235A (zh) * 2016-05-05 2016-10-26 广东小天才科技有限公司 一种应用于移动设备的开关机控制方法及装置、移动设备
CN106960669A (zh) * 2017-04-13 2017-07-18 成都步共享科技有限公司 一种共享自行车的声纹识别方法
CN107704275B (zh) * 2017-09-04 2021-07-23 百度在线网络技术(北京)有限公司 智能设备唤醒方法、装置、服务器及智能设备
GB201720418D0 (en) * 2017-11-13 2018-01-24 Cirrus Logic Int Semiconductor Ltd Audio peripheral device
EP4270385A3 (fr) 2018-04-16 2023-12-13 Google LLC Détermination automatique de langue pour la reconnaissance vocale d'énoncé parlé reçu par l'intermédiaire d'une interface d'assistant automatisé
EP4254402A3 (fr) * 2018-04-16 2023-12-20 Google LLC Détermination automatique d'une langue pour la reconnaissance de la parole d'un énoncé vocal reçu par l'intermédiaire d'une interface d'assistant automatisé
WO2019242312A1 (fr) * 2018-06-19 2019-12-26 广东美的厨房电器制造有限公司 Procédé et dispositif d'apprentissage de mots de réveil d'appareil électroménager, et appareil électroménager
CN109036393A (zh) * 2018-06-19 2018-12-18 广东美的厨房电器制造有限公司 家电设备的唤醒词训练方法、装置及家电设备
CN109065044B (zh) * 2018-08-30 2021-04-02 出门问问信息科技有限公司 唤醒词识别方法、装置、电子设备及计算机可读存储介质
CN109887508A (zh) * 2019-01-25 2019-06-14 广州富港万嘉智能科技有限公司 一种基于声纹的会议自动记录方法、电子设备及存储介质
CN110992962B (zh) * 2019-12-04 2021-01-22 珠海格力电器股份有限公司 语音设备的唤醒调整方法、装置、语音设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102404330A (zh) * 2011-11-30 2012-04-04 上海博泰悦臻电子设备制造有限公司 多用户同时在线管理方法和系统
CN102999161A (zh) * 2012-11-13 2013-03-27 安徽科大讯飞信息科技股份有限公司 一种语音唤醒模块的实现方法及应用
CN103456306A (zh) * 2012-05-29 2013-12-18 三星电子株式会社 用于在电子装置中执行语音命令的方法和设备
CN103531201A (zh) * 2013-09-29 2014-01-22 上海云视科技有限公司 终端语音命名唤醒方法和系统
CN103646646A (zh) * 2013-11-27 2014-03-19 联想(北京)有限公司 一种语音控制方法及电子设备
CN103811003A (zh) * 2012-11-13 2014-05-21 联想(北京)有限公司 一种语音识别方法以及电子设备
CN104021790A (zh) * 2013-02-28 2014-09-03 联想(北京)有限公司 声控解锁方法以及电子设备

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6795808B1 (en) * 2000-10-30 2004-09-21 Koninklijke Philips Electronics N.V. User interface/entertainment device that simulates personal interaction and charges external database with relevant data
CN1941080A (zh) * 2005-09-26 2007-04-04 吴田平 一种楼宇对讲门口机声纹识别开锁模块及识别开锁方法
CN101064043A (zh) * 2006-04-29 2007-10-31 上海优浪信息科技有限公司 一种声纹门禁系统及其应用
CN101321387A (zh) * 2008-07-10 2008-12-10 中国移动通信集团广东有限公司 基于通信系统的声纹识别方法及系统
CN102223367B (zh) * 2011-06-10 2014-04-23 安徽科大讯飞信息科技股份有限公司 移动用户访问网站的方法、设备及系统
CN202124017U (zh) * 2011-06-10 2012-01-25 沈阳君天科技股份有限公司 基于嵌入式系统的语音直接启动汽车与防盗的装置
CN102510426A (zh) * 2011-11-29 2012-06-20 安徽科大讯飞信息科技股份有限公司 个人助理应用访问方法及系统
JP5899333B2 (ja) * 2012-02-24 2016-04-06 ナント ホールディングス アイピー,エルエルシー 相互作用に基づいた認証を介したコンテンツの活性化のシステムおよび方法
CN103841248A (zh) * 2012-11-20 2014-06-04 联想(北京)有限公司 一种信息处理的方法及电子设备
CN103871409B (zh) * 2012-12-17 2018-01-23 联想(北京)有限公司 一种语音识别的方法、信息处理的方法及电子设备
CN103531210B (zh) * 2013-10-16 2017-01-18 广州番禺巨大汽车音响设备有限公司 一种基于音响实现蓝光碟数据读取输出的方法及音响系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102404330A (zh) * 2011-11-30 2012-04-04 上海博泰悦臻电子设备制造有限公司 多用户同时在线管理方法和系统
CN103456306A (zh) * 2012-05-29 2013-12-18 三星电子株式会社 用于在电子装置中执行语音命令的方法和设备
CN102999161A (zh) * 2012-11-13 2013-03-27 安徽科大讯飞信息科技股份有限公司 一种语音唤醒模块的实现方法及应用
CN103811003A (zh) * 2012-11-13 2014-05-21 联想(北京)有限公司 一种语音识别方法以及电子设备
CN104021790A (zh) * 2013-02-28 2014-09-03 联想(北京)有限公司 声控解锁方法以及电子设备
CN103531201A (zh) * 2013-09-29 2014-01-22 上海云视科技有限公司 终端语音命名唤醒方法和系统
CN103646646A (zh) * 2013-11-27 2014-03-19 联想(北京)有限公司 一种语音控制方法及电子设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3385947A4 (fr) * 2015-11-30 2018-12-05 ZTE Corporation Procédé réalisant un réveil vocal, dispositif, terminal et support de stockage informatique
CN108335695A (zh) * 2017-06-27 2018-07-27 腾讯科技(深圳)有限公司 语音控制方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN104282307A (zh) 2015-01-14

Similar Documents

Publication Publication Date Title
WO2015154412A1 (fr) Procédé et dispositif de réveil de système de commande vocale et terminal
US10930266B2 (en) Methods and devices for selectively ignoring captured audio data
EP3413305B1 (fr) Reconnaissance de la parole à double mode
US10339166B1 (en) Systems and methods for providing natural responses to commands
US10332524B2 (en) Speech recognition wake-up of a handheld portable electronic device
US11322157B2 (en) Voice user interface
JP6541630B2 (ja) スピーチエンドポインティング
US9741343B1 (en) Voice interaction application selection
US10446141B2 (en) Automatic speech recognition based on user feedback
US9202462B2 (en) Key phrase detection
CN110047481B (zh) 用于语音识别的方法和装置
US20160351196A1 (en) Methods and apparatus for reducing latency in speech recognition applications
WO2017084360A1 (fr) Procédé et système de reconnaissance vocale
WO2016023317A1 (fr) Procédé et terminal de traitement d'informations vocales
BR112015018905B1 (pt) Método de operação de recurso de ativação por voz, mídia de armazenamento legível por computador e dispositivo eletrônico
KR20180084392A (ko) 전자 장치 및 그의 동작 방법
US11790891B2 (en) Wake word selection assistance architectures and methods
WO2014144579A1 (fr) Système et procédé pour mettre à jour un modèle de reconnaissance de parole adaptatif
US20140188472A1 (en) Adaptive voice print for conversational biometric engine
WO2020244257A1 (fr) Procédé et système de réveil vocal, dispositif électronique et support d'informations lisible par ordinateur
US20180174582A1 (en) Methods and apparatus for reducing latency in speech recognition applications
KR102474804B1 (ko) 음성 인식 제어 장치, 그를 포함한 시스템 및 그 방법
US20190147887A1 (en) Audio processing
US11481188B1 (en) Application launch delay and notification
RU2698773C2 (ru) Устройство и способ распознавания речи

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: 14889038

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: 14889038

Country of ref document: EP

Kind code of ref document: A1