WO2017000774A1 - 一种机器人自身音源消除系统 - Google Patents

一种机器人自身音源消除系统 Download PDF

Info

Publication number
WO2017000774A1
WO2017000774A1 PCT/CN2016/085760 CN2016085760W WO2017000774A1 WO 2017000774 A1 WO2017000774 A1 WO 2017000774A1 CN 2016085760 W CN2016085760 W CN 2016085760W WO 2017000774 A1 WO2017000774 A1 WO 2017000774A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
mixed
digital signal
sound source
unit
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/CN2016/085760
Other languages
English (en)
French (fr)
Chinese (zh)
Inventor
刘鑫
高鹏
施家琪
范利春
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.)
Yutou Technology Hangzhou Co Ltd
Original Assignee
Yutou Technology Hangzhou 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 Yutou Technology Hangzhou Co Ltd filed Critical Yutou Technology Hangzhou Co Ltd
Priority to EP16817138.7A priority Critical patent/EP3319088A4/en
Priority to JP2017567760A priority patent/JP2018519552A/ja
Priority to US15/739,320 priority patent/US10482898B2/en
Publication of WO2017000774A1 publication Critical patent/WO2017000774A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0272—Voice signal separating
    • 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
    • G10L13/00—Speech synthesis; Text to speech systems
    • 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • 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
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • 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
    • G10L25/78—Detection of presence or absence of voice signals
    • G10L25/84—Detection of presence or absence of voice signals for discriminating voice from noise
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • 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
    • G10L15/00—Speech recognition
    • G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
    • 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

Definitions

  • the present invention relates to the field of audio recognition, and more particularly to an automatic sound source cancellation system applied to a robot system.
  • Speech recognition and processing technology has increasingly emerged its powerful technical advantages.
  • speech recognition has become more and more widely used in the fields of computers, information processing, communication and electronic systems, and automatic control. Because people in the process of voice communication are inevitably subject to noise from the surrounding environment, transmission media, internal noise of the communication equipment, and interference from other speakers, these interferences will eventually cause the voice received by the receiver to be contaminated by noise. After the noisy speech signal, not the pure original speech signal.
  • the generated music signal is doped into the voice signal picked up by the robot microphone, so that the voice signal entering the automatic voice recognition system is made.
  • the noise ratio decreases, causing certain interference to the recognition rate of the robot's Automatic Speech Recognition (ASR) system, which reduces the recognition rate and affects the user experience of robot speech recognition.
  • ASR Automatic Speech Recognition
  • a robot own sound source elimination system aiming at realizing an interference signal capable of canceling or suppressing the playback of the robot itself and improving the speech recognition rate is provided.
  • a robotic sound source elimination system comprising:
  • a sound collecting unit for collecting a digital signal mixed with left and right channels, and outputting
  • a sound card driving unit connected to the sound collecting unit, for mixing the received reference signal of the robot's own sound source and the digital signal mixed with left and right channels to form a mixed voice signal, and outputting;
  • a signal separation unit connected to the sound card driving unit, configured to separate the mixed voice signal into the digital signal mixed with left and right channels and the reference signal, and determine whether the digital signal mixed with left and right channels is There is an interference signal, the amount of the playback signal is obtained, and output;
  • a sound source eliminating unit connected to the signal separating unit, configured to receive the reference signal, the playing signal amount, and the digital signal mixed with left and right channels, and cancel mixing the left and right channels according to the playing signal amount Interference signals in the digital signal, and output;
  • an identification unit connected to the sound source eliminating unit, for identifying the digital signal mixed with the left and right channels.
  • the sound source elimination unit comprises:
  • a left channel sound source removing module configured to receive the reference signal, the playing signal amount, and the digital signal mixed with left and right channels, and cancel the digital signal mixed with left and right channels according to the playing signal amount The interference signal and output the left channel digital signal.
  • the sound source elimination unit further includes:
  • a right channel sound source removing module configured to receive the reference signal, the playing signal amount, and the digital signal mixed with left and right channels, and cancel the digital signal mixed with left and right channels according to the playing signal amount The interference signal and output the right channel digital signal.
  • the identification unit comprises:
  • a recording adapter for receiving the left channel digital signal and the right channel digital signal, and outputting.
  • the identifying unit further includes:
  • a channel mixing module connected to the recording adapter, for mixing the left channel digital signal and the right channel digital signal to generate a mixed signal, and outputting.
  • the identifying unit further includes:
  • the detecting module is connected to the channel mixing module, configured to detect a voice signal in the mixed signal, obtain a detection result, and output a corresponding notification according to the result.
  • the identifying unit further includes:
  • the voice recognition module is respectively connected to the detecting module and the channel mixing module, and is configured to identify the mixed signal according to the received notification.
  • the robot's own sound source elimination system can cancel or suppress the music interference signal played by the robot itself, and provide a pure voice signal for the voice recognition, thereby improving the voice recognition rate of the robot.
  • FIG. 1 is a block diagram of an embodiment of a robot's own sound source cancellation system according to the present invention.
  • a robot's own sound source cancellation system includes:
  • the sound pickup unit 1 is configured to collect and output a digital signal mixed with left and right channels;
  • the sound card driving unit 2 is connected to the sound collecting unit 1 for mixing the received reference signal of the robot's own sound source and the digital signal mixed with the left and right channels to form a mixed voice signal, and outputting;
  • the signal separating unit 3 is connected to the sound card driving unit 2 for separating the mixed voice signal into a digital signal and a reference signal mixed with the left and right channels, and determining whether there is an interference signal in the digital signal mixed with the left and right channels, and acquiring the playing signal amount. And output;
  • the sound source eliminating unit 4 is connected to the signal separating unit 3 for receiving the reference signal, the playing signal amount, and the digital signal mixed with the left and right channels, and canceling the interference signal in the digital signal mixed with the left and right channels according to the playing signal amount, and Output
  • the identification unit 5 is connected to the sound source eliminating unit 4 for identifying digital signals mixed with left and right channels.
  • the sound card driving unit 2 can be driven by a USB sound card, and the USB sound card is a standard USB sound card driving in the Android system device;
  • the sound collecting unit 1 can adopt a two-channel long-distance sound collecting microphone, which can realize the function of picking up stereo sound; It can also include a USB interface and a 3.5Line-out interface.
  • the 3.5Line-out interface is used to collect the reference signals of the left and right channel PCM (Pulse Code Modulation), and is transmitted to the Android system through the USB interface in synchronization with the voice signal picked up by the microphone.
  • PCM Pulse Code Modulation
  • the robot's own sound source elimination microphone is connected with the robot's main control board, and the USB sound card is driven to connect to the Android system; thus the microphone is mixed with the left and right channel digital signals and from the 3.5Line-out interface.
  • the collected reference signals of the left and right channel PCM are transmitted to the signal separation unit 3 through the USB sound card drive.
  • the signal separation unit 3 separates the mixed voice signal collected by the USB sound card drive into a digital signal and a reference signal mixed with left and right channels. No. According to the digital signal mixed with left and right channels, it is judged whether the system is playing music.
  • the playback semaphore When the system plays music, the playback semaphore is set to True, and then the playback semaphore and the digital signal and reference signal mixed with the left and right channels are mixed.
  • the processing in the synchronous source elimination unit 4 is synchronized; when the system does not play music, the playback semaphore is set to False, and the system processing flow directly enters the identification unit 5.
  • the robot's own sound source elimination system can cancel or suppress the music interference signal played by the robot itself, and provide a pure voice signal for the voice recognition, thereby improving the voice recognition rate of the robot, thereby improving the user's hands-free ( Hands-free) speech recognition experience.
  • the sound source elimination unit 4 may include:
  • the left channel sound source eliminating module 41 is configured to receive the reference signal, the playing signal amount, and the digital signal mixed with the left and right channels, and cancel the interference signal in the digital signal mixed with the left and right channels according to the playing signal amount, and output the left channel Digital signal.
  • the left channel sound source removing module 41 implements suppression of interference of the system to speech recognition when playing music.
  • the channel sound source elimination module There are three input parameters of the channel sound source elimination module: the digital signal mixed by the microphone and the left and right channels, the reference signal of the left and right channel PCM of the own sound source, and the playback signal amount.
  • the playback semaphore is True
  • the left channel sound source canceling module 41 performs self-sound source cancellation on the digital signals of the left and right channels mixed by the microphone pickup.
  • the left channel sound source eliminating module 41 outputs the left channel digital signal; when the music playing signal amount is False, the left channel sound source removing module 41 is jumped out, and the system flow directly enters the identifying unit 5.
  • the sound source elimination unit 4 further includes:
  • the right channel sound source eliminating module 42 is configured to receive the reference signal, the playing signal amount, and the digital signal mixed with the left and right channels, and cancel the interference signal in the digital signal mixed with the left and right channels according to the playing signal amount, and output the right channel Digital signal.
  • the right channel sound source canceling module 42 implements suppression of interference of the system in speech recognition when playing music.
  • the right channel sound source elimination module 42 has three input parameters: a digital signal mixed by the microphone and a left and right channel, a reference signal of the left and right channel PCM of the own sound source, and a playback signal amount. When the playback semaphore is True, the right channel source elimination module 42 mixes the microphones. A digital signal with left and right channels is used to eliminate the source itself.
  • the right channel sound source removing module 42 outputs the right channel digital signal; when the music playing signal amount is False, the right channel sound source removing module 42 is jumped out, and the system flow directly enters the identifying unit 5.
  • the identification unit 5 can comprise:
  • the recording adapter 51 can be connected to the left channel sound source removing module 41 and the right channel sound source eliminating module 42 for receiving the left channel digital signal and the right channel digital signal, and outputting.
  • the recording adapter 51 used has the advantages of good recording effect, pure sound and no noise.
  • the identification unit 5 may further comprise:
  • the channel mixing module 52 is connected to the recording adapter 51 for mixing the left channel digital signal and the right channel digital signal to generate a mixed signal and outputting.
  • the left channel digital signal and the right channel digital signal output from the recording adapter 51 can be mixed and output by the channel mixing module 52.
  • the identification unit 5 may further comprise:
  • the detecting module 53 is connected to the channel mixing module 52 for detecting the voice signal in the mixed signal, acquiring the detection result, and outputting a corresponding notification according to the result.
  • the detecting module 53 is configured to detect the mixed signal, and when the voice signal is detected, generate a corresponding notification event and output it.
  • the identification unit 5 may further comprise:
  • the voice recognition module 54 is respectively connected to the detecting module 53 and the channel mixing module 52 for identifying the mixed signal according to the received notification.
  • a corresponding notification event is generated to activate the voice recognition module 54 to perform voice recognition through the voice recognition module 54.
  • the invention uses a USB sound card driver to transmit the digital signal collected by the microphone to the signal separation unit 3.
  • the robot's own sound source elimination system can realize its own sound source for the robot sound system. Effectively eliminate or inhibit.
  • the signal separation unit 3 can separate the digital signal mixed with the left and right channels and the reference signal collected by the microphone, and simultaneously input to the sound source elimination unit 4 for processing; after the sound source elimination unit 4 processes, the output signal noise is relatively high. Speech signal to improve speech recognition rate.
  • the robot's own sound source cancellation system can also effectively eliminate or suppress the self-sound source of the signal converted from the text format to the voice format.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Circuit For Audible Band Transducer (AREA)
PCT/CN2016/085760 2015-06-30 2016-06-14 一种机器人自身音源消除系统 Ceased WO2017000774A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP16817138.7A EP3319088A4 (en) 2015-06-30 2016-06-14 SYSTEM FOR ROBOTS FOR ELIMINATING A OWN SOUND SOURCE
JP2017567760A JP2018519552A (ja) 2015-06-30 2016-06-14 ロボット自身音源を解消するシステム
US15/739,320 US10482898B2 (en) 2015-06-30 2016-06-14 System for robot to eliminate own sound source

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510381657.1 2015-06-30
CN201510381657.1A CN106328165A (zh) 2015-06-30 2015-06-30 一种机器人自身音源消除系统

Publications (1)

Publication Number Publication Date
WO2017000774A1 true WO2017000774A1 (zh) 2017-01-05

Family

ID=57607848

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/085760 Ceased WO2017000774A1 (zh) 2015-06-30 2016-06-14 一种机器人自身音源消除系统

Country Status (6)

Country Link
US (1) US10482898B2 (https=)
EP (1) EP3319088A4 (https=)
JP (1) JP2018519552A (https=)
CN (1) CN106328165A (https=)
TW (1) TWI588821B (https=)
WO (1) WO2017000774A1 (https=)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110534110B (zh) * 2018-05-25 2022-04-15 深圳市优必选科技有限公司 一种机器人及提高其语音交互识别率的方法、装置和电路
US11270712B2 (en) 2019-08-28 2022-03-08 Insoundz Ltd. System and method for separation of audio sources that interfere with each other using a microphone array
CN111883158B (zh) * 2020-07-30 2024-04-16 广州易点智慧出行科技有限公司 一种回声消除方法和装置
CN113035188A (zh) * 2021-02-25 2021-06-25 平安普惠企业管理有限公司 通话文本生成方法、装置、设备及存储介质
CN115103286B (zh) * 2022-04-29 2024-09-27 北京瑞森新谱科技股份有限公司 一种asio低延时声学采集方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060106601A1 (en) * 2004-11-18 2006-05-18 Samsung Electronics Co., Ltd. Noise elimination method, apparatus and medium thereof
US20080312918A1 (en) * 2007-06-18 2008-12-18 Samsung Electronics Co., Ltd. Voice performance evaluation system and method for long-distance voice recognition
CN101510425A (zh) * 2008-02-15 2009-08-19 株式会社东芝 声音识别装置以及用于执行声音识别的方法
CN102141812A (zh) * 2010-11-16 2011-08-03 深圳中科智酷机器人科技有限公司 机器人
CN102903360A (zh) * 2011-07-26 2013-01-30 财团法人工业技术研究院 以麦克风阵列为基础的语音辨识系统与方法
CN103593048A (zh) * 2013-10-28 2014-02-19 浙江大学 动物机器人系统的语音导航系统及方法

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4974191A (en) * 1987-07-31 1990-11-27 Syntellect Software Inc. Adaptive natural language computer interface system
WO1996012255A1 (fr) * 1994-10-12 1996-04-25 Technical Maintenance Corporation Systeme de reproduction audio-visuelle numerique intelligent
US6689947B2 (en) * 1998-05-15 2004-02-10 Lester Frank Ludwig Real-time floor controller for control of music, signal processing, mixing, video, lighting, and other systems
JP3843743B2 (ja) * 2001-03-09 2006-11-08 独立行政法人科学技術振興機構 ロボット視聴覚システム
US20080119953A1 (en) * 2005-04-07 2008-05-22 Iofy Corporation Device and System for Utilizing an Information Unit to Present Content and Metadata on a Device
JP2007155986A (ja) * 2005-12-02 2007-06-21 Mitsubishi Heavy Ind Ltd 音声認識装置および音声認識装置を備えたロボット
US8155331B2 (en) * 2006-05-10 2012-04-10 Honda Motor Co., Ltd. Sound source tracking system, method and robot
WO2007138503A1 (en) * 2006-05-31 2007-12-06 Philips Intellectual Property & Standards Gmbh Method of driving a speech recognition system
WO2008085206A2 (en) * 2006-12-29 2008-07-17 Prodea Systems, Inc. Subscription management of applications and services provided through user premises gateway devices
US8468244B2 (en) * 2007-01-05 2013-06-18 Digital Doors, Inc. Digital information infrastructure and method for security designated data and with granular data stores
CN101084817B (zh) * 2007-04-26 2012-08-22 复旦大学 开放智能计算构架的家用多功能小型服务机器人
TW200926150A (en) * 2007-12-07 2009-06-16 Univ Nat Chiao Tung Intelligent voice purification system and its method thereof
DE202011111062U1 (de) * 2010-01-25 2019-02-19 Newvaluexchange Ltd. Vorrichtung und System für eine Digitalkonversationsmanagementplattform
JP5328744B2 (ja) * 2010-10-15 2013-10-30 本田技研工業株式会社 音声認識装置及び音声認識方法
CN102890936A (zh) * 2011-07-19 2013-01-23 联想(北京)有限公司 一种音频处理方法、终端设备及系统
CN102305925A (zh) * 2011-07-22 2012-01-04 北京大学 一种机器人连续声源定位方法
CN103718241B (zh) * 2011-11-02 2016-05-04 三菱电机株式会社 噪音抑制装置
JP5971047B2 (ja) * 2012-09-12 2016-08-17 沖電気工業株式会社 音声信号処理装置、方法及びプログラム
CN102915732A (zh) * 2012-10-31 2013-02-06 黑龙江省电力有限公司信息通信分公司 抑制背景广播的语音指令识别方法与装置
US9747899B2 (en) * 2013-06-27 2017-08-29 Amazon Technologies, Inc. Detecting self-generated wake expressions
CN104123950B (zh) * 2014-07-17 2015-11-25 努比亚技术有限公司 一种录音方法及装置
US9849588B2 (en) * 2014-09-17 2017-12-26 Brain Corporation Apparatus and methods for remotely controlling robotic devices

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060106601A1 (en) * 2004-11-18 2006-05-18 Samsung Electronics Co., Ltd. Noise elimination method, apparatus and medium thereof
US20080312918A1 (en) * 2007-06-18 2008-12-18 Samsung Electronics Co., Ltd. Voice performance evaluation system and method for long-distance voice recognition
CN101510425A (zh) * 2008-02-15 2009-08-19 株式会社东芝 声音识别装置以及用于执行声音识别的方法
CN102141812A (zh) * 2010-11-16 2011-08-03 深圳中科智酷机器人科技有限公司 机器人
CN102903360A (zh) * 2011-07-26 2013-01-30 财团法人工业技术研究院 以麦克风阵列为基础的语音辨识系统与方法
CN103593048A (zh) * 2013-10-28 2014-02-19 浙江大学 动物机器人系统的语音导航系统及方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3319088A4 *

Also Published As

Publication number Publication date
EP3319088A4 (en) 2019-01-23
TW201701272A (zh) 2017-01-01
US20190115042A1 (en) 2019-04-18
CN106328165A (zh) 2017-01-11
US10482898B2 (en) 2019-11-19
TWI588821B (zh) 2017-06-21
EP3319088A1 (en) 2018-05-09
JP2018519552A (ja) 2018-07-19

Similar Documents

Publication Publication Date Title
TWI588821B (zh) 機器人自身音源消除系統
US20190371324A1 (en) Suppression of voice response by device rendering trigger audio
EP4456566A3 (en) Linear filtering for noise-suppressed speech detection
CA2524338A1 (en) Hearing aid system, a hearing aid and a method for processing audio signals
US20170084287A1 (en) Electronic device and method of audio processing thereof
CN102915732A (zh) 抑制背景广播的语音指令识别方法与装置
US20150117669A1 (en) Apparatus and method for controlling beamforming microphone considering location of driver seat
CN107004425A (zh) 共享声学空间中的增强型对话通信
CN106569774B (zh) 一种去除噪声的方法及终端
KR20170104566A (ko) 다중 채널의 디지털 마이크
CN103079145A (zh) 新型车载多媒体播放器及其实现方法
US11749293B2 (en) Audio signal processing device
JP2018519552A5 (https=)
CN105049802A (zh) 一种语音识别执法记录仪及其识别方法
CN110996238B (zh) 双耳同步信号处理助听系统及方法
KR20180036032A (ko) 영상처리장치 및 기록매체
CN111512363B (zh) 语音辅助设备和方法
CN103974168A (zh) 一种信息处理方法及电子设备
WO2017045512A1 (zh) 一种语音识别的方法、装置、终端及语音识别设备
JP5377442B2 (ja) 参照情報により雑音から音声を分離するシステム
CN109473096B (zh) 一种智能语音设备及其控制方法
HK1232010A (en) A sound source elimination system of a robot itself
HK1232010A1 (en) A sound source elimination system of a robot itself
CN107545908B (zh) 车载系统的音频信号处理方法及车载系统
KR20170007114A (ko) 음성 신호 처리 장치 및 방법, 그리고 단말

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: 16817138

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017567760

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016817138

Country of ref document: EP