CN105825862A - Robot man-machine dialogue echo cancellation system - Google Patents
Robot man-machine dialogue echo cancellation system Download PDFInfo
- Publication number
- CN105825862A CN105825862A CN201510002883.4A CN201510002883A CN105825862A CN 105825862 A CN105825862 A CN 105825862A CN 201510002883 A CN201510002883 A CN 201510002883A CN 105825862 A CN105825862 A CN 105825862A
- Authority
- CN
- China
- Prior art keywords
- module
- echo
- robot
- signal
- echo cancellation
- 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.)
- Pending
Links
Abstract
A robot man-machine dialogue echo cancellation system comprises a main control module, an echo cancellation module, a voice partial pressure module, a microphone, and a speaker. The voice partial pressure module is used for setting the partial pressure ratio of the resistance of a potentiometer and sending the strength of echo signals to the echo cancellation module. The speaker is used for playing test sound made by a robot. The microphone is used for collecting sound signals. The echo cancellation module is connected with the voice partial pressure module, and is used for cancelling echo signals. The main control module is used for adjusting the partial pressure ratio of the resistance of the potentiometer and controlling the process of echo cancellation. Compared with the prior art, the system adopting the technical scheme has the advantages of low cost and low control difficulty. Processor resources are saved greatly, and the risk of algorithm divergence failure is avoided.
Description
Technical field
The invention belongs to robot voice identification field, particularly relate to a kind of robot human computer conversation's echo cancelling system.
Background technology
In existing service robot good in interactive function, user sends voice messaging to robot, and voice messaging is gathered by mike by robot, and encoded being transferred to completes speech recognition after processor carries out software processes.This voice messaging of response is replied by speaker by robot afterwards.But the now playback of speaker easily by robot Mike's Resurvey, is mistakenly considered the new voice message of user by robot, causes voice to obscure and misidentifies.If the shielded sound acquisition function when playback, it is primarily due to answer voice length different, it is impossible to the suitable shielding time is set, next to that secondary Instant audio messages and the instruction of user cannot be gathered during playback, is substantially reduced experience and the satisfaction of user.If using voice elimination algorithm, first algorithm easily to dissipate inefficacy, next to that algorithm is complicated, can significantly take processor resource.
Summary of the invention
In consideration of it, be necessary to provide a kind of noiseless, echo cancelling system of low cost.
For achieving the above object, the present invention adopts the following technical scheme that
A kind of robot human computer conversation's echo cancelling system, it is characterised in that include a main control module, an echo cancellation module, a voice division module, a mike and a speaker,
Voice division module, for arranging the intrinsic standoff ratio of potentiometer resistance, by echo signal strength transfer to echo cancellation module；
Speaker, the test tone sent for broadcasting machine people；
Mike, for collected sound signal；
Echo cancellation module, is connected with voice division module, for carrying out the elimination of echo signal；
Main control module, for adjusting the intrinsic standoff ratio of potentiometer resistance, controls to eliminate the flow process of echo；
Preferably, voice division module includes that digital regulation resistance and fixed value resistance, described digital regulation resistance and fixed value resistance are connected in series.
Preferably, when the test tone that described speaker broadcast sound volume is A, described mike gathers the test tone signal after volume attenuation simultaneously, and the volume of this signal is that the relation of B, A and B is:
B=A*K
Wherein, K is the attenuation quotient of volume.
Preferably, echo cancellation module includes subtractor and analog switch,
Described analog switch, for connection and the disconnection of control echo cancellation module and voice division module；
Described subtractor, eliminates echo volume at mike in exporting.
Preferably, also include: audio coding decoding module and power amplifier module,
Described audio coding decoding module is for being converted to digital signal by the acoustical signal of simulation；
Described power amplifier module is connected between audio coding decoding module and voice division module, is used for low power acoustical signal is converted to have high-power signal output.
Preferably, after main control module adjusts the intrinsic standoff ratio of potentiometer resistance, user acoustical signal and playback echo deduct elimination value by fixing, it is achieved the elimination of speech echo.
Technical scheme, the playback bleeder mechanism comprising programmable digital potentiometer and the echo cancelling device comprising numerical control analog switch is added in robot voice system, elimination amount is corrected when each system start-up, complete the robot playback echo cancellation performance in good in interactive function, make the speech recognition system of robot be no longer influenced by the interference of playback echo and produce and obscure or misidentify.With low cost and control difficulty low, compared with echo cancellation algorithm, be greatly saved processor resource not algorithm and dissipate the risk of inefficacy.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of embodiment of the present invention.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage become apparent from, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Referring to Fig. 1, a kind of robot human computer conversation's echo cancelling system, including main control module 10, echo cancellation module 20, voice division module 30, mike 40 and a speaker 50.
Voice division module 30, for arranging the intrinsic standoff ratio of potentiometer resistance, and by echo signal strength transfer to echo cancellation module.
Described voice division module 30 includes digital regulation resistance 31 and fixed value resistance 32, and described digital regulation resistance 31 and fixed value resistance 32 are connected in series, and arrange the resistance of digital regulation resistance so that the intrinsic standoff ratio of digital regulation resistance 31 and fixed resistance 32 is K1.
Speaker 50, the test tone sent for broadcasting machine people.Sound is welcome in the test that speaker 50 broadcasting machine people sends, and the volume of this welcome sound is set to A.Now, voice division module 30 does not access echo cancellation module.
Mike 40, for collected sound signal.
When the test tone that speaker 50 broadcast sound volume is A, mike 40 gathers the test tone signal after volume attenuation simultaneously, and the volume of this signal is B.This is due in actual route of transmission, from speaker 50 to the communication process of mike 40, sound has the decay that coefficient is K.This decay volume meets below equation:
B=A*K (1)
Echo cancellation module 20, is connected with voice division module 30 communication, for carrying out the elimination of echo signal.
This echo cancellation module 20 includes subtractor 21 and analog switch 22.Described analog switch 22, for connection and the disconnection of control echo cancellation module 20 and voice division module 30.Described subtractor 21, for eliminating echo volume at mike in exporting.When playing test volume unchangedization, i.e. volume is still, after quick closing valve 22 Guan Bi is intended in B time control molding, to obtain the dividing potential drop test tone C after voice division module 30 dividing potential drop.This test tone C meets shown in formula 2:
C=A*K-A*K1 (2)
Formula (3) can be drawn by formula (1) and formula (2):
K=B*K1/ (B-C) (3)
Main control module 10, for adjusting the intrinsic standoff ratio of potentiometer resistance, controls to eliminate the flow process of echo.
Main control module 10 adjusts the intrinsic standoff ratio of potentiometer resistance, and the intrinsic standoff ratio after adjustment is K2, meets following condition:
K2=K=B*K1/ (B-C)
Control analog switch 22 in main control module 10 control echo cancellation module 20, keeps the state that the test tone signal after dividing potential drop accesses subtractor rear end.In use the most later, user acoustical signal and playback echo deduct K2*A=K0*A by fixing.Namely fixing elimination speaker is through the loudspeaker signal of delivering path decay A0 times in the acoustical signal that MIC receives, real-time eliminates the speech echo of robot, makes robot voice system not disturbed by echo.
Additionally, this echo cancelling system also includes audio coding decoding module 60 and power amplifier module 70.
Audio coding decoding module 60 is for for being converted to digital signal by the acoustical signal of simulation.
Audio coding decoding module 60 communication is connected between main control module 10 and echo cancellation module, including coding module 61 and decoder module 62.The speech simulation amount of input is converted to digital quantity by coding module 61, and is encoded to specific form, such as usb audio stream.Digital quantity is converted to analog quantity by decoder module 62, and function is similar to digital to analog converter (DA).
Power amplifier module 70 communication is connected between audio coding decoding module 60 and voice division module 30.For low power acoustical signal being converted to the big signal output with certain power.
The above is only the preferred embodiment of the present invention; it should be pointed out that, for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (6)
1. robot human computer conversation's echo cancelling system, it is characterised in that include a main control module, an echo cancellation module, a voice division module, a mike and a speaker,
Voice division module, for arranging the intrinsic standoff ratio of potentiometer resistance, by echo signal strength transfer to echo cancellation module；
Speaker, the test tone sent for broadcasting machine people；
Mike, for collected sound signal；
Echo cancellation module, is connected with voice division module, for carrying out the elimination of echo signal；
Main control module, for adjusting the intrinsic standoff ratio of potentiometer resistance, controls to eliminate the flow process of echo.
2. robot as claimed in claim 1 human computer conversation's echo cancelling system, it is characterised in that described voice division module includes that digital regulation resistance and fixed value resistance, described digital regulation resistance and fixed value resistance are connected in series.
3. robot as claimed in claim 1 human computer conversation's echo cancelling system, it is characterized in that, when the test tone that described speaker broadcast sound volume is A, described mike gathers the test tone signal after volume attenuation simultaneously, the volume of this signal is that the relation of B, A and B is:
B=A*K
Wherein, K is the attenuation quotient of volume.
4. robot as claimed in claim 1 human computer conversation's echo cancelling system, it is characterised in that described echo cancellation module includes subtractor and analog switch,
Described analog switch, for connection and the disconnection of control echo cancellation module and voice division module；
Described subtractor, eliminates echo volume at mike in exporting.
5. robot as claimed in claim 1 human computer conversation's echo cancelling system, it is characterised in that described system also includes: audio coding decoding module and power amplifier module,
Described audio coding decoding module is for being converted to digital signal by the acoustical signal of simulation；
Described power amplifier module is connected between audio coding decoding module and voice division module, is used for low power acoustical signal is converted to have high-power signal output.
6. robot as claimed in claim 1 human computer conversation's echo cancelling system, it is characterised in that after main control module adjusts the intrinsic standoff ratio of potentiometer resistance, deducts elimination value by fixing in user acoustical signal and playback echo, it is achieved the elimination of speech echo.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510002883.4A CN105825862A (en) | 2015-01-05 | 2015-01-05 | Robot man-machine dialogue echo cancellation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510002883.4A CN105825862A (en) | 2015-01-05 | 2015-01-05 | Robot man-machine dialogue echo cancellation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105825862A true CN105825862A (en) | 2016-08-03 |
Family
ID=56513608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510002883.4A Pending CN105825862A (en) | 2015-01-05 | 2015-01-05 | Robot man-machine dialogue echo cancellation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105825862A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107071652A (en) * | 2016-12-27 | 2017-08-18 | 深圳市优必选科技有限公司 | A kind of service robot |
| CN107146629A (en) * | 2017-04-27 | 2017-09-08 | 深圳市益光实业有限公司 | The echo cancellation system recognized based on vehicle-mounted voice |
| CN107705799A (en) * | 2017-11-24 | 2018-02-16 | 深圳狗尾草智能科技有限公司 | Chat robots echo cancel method and device |
| CN108322859A (en) * | 2018-02-05 | 2018-07-24 | 北京百度网讯科技有限公司 | Equipment, method and computer readable storage medium for echo cancellor |
| CN108877825A (en) * | 2018-06-26 | 2018-11-23 | 珠海宏桥高科技有限公司 | A kind of Network echo cancellation element and method based on voice-activated and logic control |
| CN108899056A (en) * | 2018-06-28 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of control system and SSD of main control chip |
| CN110223707A (en) * | 2019-07-10 | 2019-09-10 | 青岛海信电器股份有限公司 | Display device |
| CN110349582A (en) * | 2019-07-10 | 2019-10-18 | 青岛海信电器股份有限公司 | Display device and far field speech processing circuit |
| WO2020006699A1 (en) * | 2018-07-04 | 2020-01-09 | 华为技术有限公司 | Method and apparatus for voice processing |
| CN111601198A (en) * | 2020-04-24 | 2020-08-28 | 达闼科技成都有限公司 | Method and device for tracking speaker by using microphone and computing equipment |
| WO2021004067A1 (en) * | 2019-07-10 | 2021-01-14 | 海信视像科技股份有限公司 | Display device |
| CN113038345A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | System for optimizing audio signal in audio acquisition process |
| CN113035224A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | Equipment for eliminating echo and improving audio quality |
| CN113035218A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | Method for optimizing audio signal in audio acquisition process |
| CN113035219A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | Method for eliminating echo and improving audio quality |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1262012A (en) * | 1997-05-07 | 2000-08-02 | 艾利森公司 | Improved acoustic echo canceler for telecommunications system |
| JP2002290286A (en) * | 2001-03-28 | 2002-10-04 | Matsushita Electric Works Ltd | Echo suppressor |
| CN101765982A (en) * | 2007-07-26 | 2010-06-30 | 雅马哈株式会社 | Echo canceller |
| CN202475574U (en) * | 2012-03-12 | 2012-10-03 | 杭州艾力特音频技术有限公司 | Echo-cancelling talkback equipment |
| CN103188585A (en) * | 2011-12-31 | 2013-07-03 | 冠捷投资有限公司 | Voice frequency adjusting device and adjusting method thereof |
| CN103700374A (en) * | 2013-12-25 | 2014-04-02 | 宁波菊风系统软件有限公司 | Method for determining system time delay in acoustic echo cancellation and acoustic echo cancellation method |
-
2015
- 2015-01-05 CN CN201510002883.4A patent/CN105825862A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1262012A (en) * | 1997-05-07 | 2000-08-02 | 艾利森公司 | Improved acoustic echo canceler for telecommunications system |
| JP2002290286A (en) * | 2001-03-28 | 2002-10-04 | Matsushita Electric Works Ltd | Echo suppressor |
| CN101765982A (en) * | 2007-07-26 | 2010-06-30 | 雅马哈株式会社 | Echo canceller |
| CN103188585A (en) * | 2011-12-31 | 2013-07-03 | 冠捷投资有限公司 | Voice frequency adjusting device and adjusting method thereof |
| CN202475574U (en) * | 2012-03-12 | 2012-10-03 | 杭州艾力特音频技术有限公司 | Echo-cancelling talkback equipment |
| CN103700374A (en) * | 2013-12-25 | 2014-04-02 | 宁波菊风系统软件有限公司 | Method for determining system time delay in acoustic echo cancellation and acoustic echo cancellation method |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107071652A (en) * | 2016-12-27 | 2017-08-18 | 深圳市优必选科技有限公司 | A kind of service robot |
| CN107071652B (en) * | 2016-12-27 | 2023-08-04 | 深圳市优必选科技有限公司 | Service robot |
| CN107146629A (en) * | 2017-04-27 | 2017-09-08 | 深圳市益光实业有限公司 | The echo cancellation system recognized based on vehicle-mounted voice |
| CN107705799B (en) * | 2017-11-24 | 2020-12-11 | 苏州狗尾草智能科技有限公司 | Chat robot echo cancellation method and device |
| CN107705799A (en) * | 2017-11-24 | 2018-02-16 | 深圳狗尾草智能科技有限公司 | Chat robots echo cancel method and device |
| CN108322859A (en) * | 2018-02-05 | 2018-07-24 | 北京百度网讯科技有限公司 | Equipment, method and computer readable storage medium for echo cancellor |
| CN108877825A (en) * | 2018-06-26 | 2018-11-23 | 珠海宏桥高科技有限公司 | A kind of Network echo cancellation element and method based on voice-activated and logic control |
| CN108899056A (en) * | 2018-06-28 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of control system and SSD of main control chip |
| WO2020006699A1 (en) * | 2018-07-04 | 2020-01-09 | 华为技术有限公司 | Method and apparatus for voice processing |
| CN110223707A (en) * | 2019-07-10 | 2019-09-10 | 青岛海信电器股份有限公司 | Display device |
| CN110349582A (en) * | 2019-07-10 | 2019-10-18 | 青岛海信电器股份有限公司 | Display device and far field speech processing circuit |
| WO2021004067A1 (en) * | 2019-07-10 | 2021-01-14 | 海信视像科技股份有限公司 | Display device |
| CN110349582B (en) * | 2019-07-10 | 2021-11-19 | 海信视像科技股份有限公司 | Display device and far-field voice processing circuit |
| CN113035218A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | Method for optimizing audio signal in audio acquisition process |
| CN113035224A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | Equipment for eliminating echo and improving audio quality |
| CN113035219A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | Method for eliminating echo and improving audio quality |
| CN113038345A (en) * | 2019-12-09 | 2021-06-25 | 北京君正集成电路股份有限公司 | System for optimizing audio signal in audio acquisition process |
| CN113035218B (en) * | 2019-12-09 | 2022-08-02 | 北京君正集成电路股份有限公司 | Method for optimizing audio signal in audio acquisition process |
| CN113038345B (en) * | 2019-12-09 | 2023-03-14 | 北京君正集成电路股份有限公司 | System for optimizing audio signal in audio acquisition process |
| CN113035219B (en) * | 2019-12-09 | 2023-10-31 | 北京君正集成电路股份有限公司 | Method for eliminating echo and improving audio quality |
| CN111601198A (en) * | 2020-04-24 | 2020-08-28 | 达闼科技成都有限公司 | Method and device for tracking speaker by using microphone and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105825862A (en) | Robot man-machine dialogue echo cancellation system | |
| CN111836147B (en) | Noise reduction device and method | |
| CN105074814B (en) | Low time delay multiple driver self-adapted noise elimination (ANC) system of personal audio set | |
| CN105284126B (en) | The self-adapted noise elimination system and method for the dynamic bias of coefficient including self-adapted noise elimination system | |
| US9460701B2 (en) | Systems and methods for adaptive noise cancellation by biasing anti-noise level | |
| CN203761556U (en) | Double-microphone noise reduction earphone | |
| US9100747B2 (en) | Signal processing device and signal processing method | |
| CN103597540A (en) | Ear-coupling detection and adjustment of adaptive response in noise-canceling in personal audio devices | |
| US9392364B1 (en) | Virtual microphone for adaptive noise cancellation in personal audio devices | |
| CN102088648A (en) | Method for dynamic suppression of surrounding acoustic noise when listening to electrical inputs | |
| CN103517192A (en) | Hearing aid comprising a feedback alarm | |
| CN103458137A (en) | Systems and methods for voice enhancement in audio conference | |
| US9601128B2 (en) | Communication apparatus and voice processing method therefor | |
| CN106448691A (en) | Speech enhancement method used for loudspeaking communication system | |
| CN106488370A (en) | The method of the feedback for suppressing in hearing device | |
| CN111372121A (en) | Echo cancellation method, device, storage medium and processor | |
| CN104580764B (en) | Ultrasonic pairing signal control in TeleConference Bridge | |
| CN108076239A (en) | A kind of method for improving IP phone echo | |
| CN110012378B (en) | Method for reducing noise of voice, earplug and computer storage medium | |
| CN103248845A (en) | Voice-self adaptive television | |
| US20220319532A1 (en) | Pre-conditioning audio for machine perception | |
| CN105162427A (en) | Playing handling method and device for audio switching | |
| CN112954243A (en) | Wireless earphone live broadcasting system | |
| CN108289267A (en) | Eliminate echo cancelling device, method, speaker, the voice frequency sender of TV interference | |
| JP4696776B2 (en) | Audio processing device and microphone device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |
|
| RJ01 | Rejection of invention patent application after publication |