CN109360562A - Echo cancel method, device, medium and voice awakening method and equipment - Google Patents
Echo cancel method, device, medium and voice awakening method and equipment Download PDFInfo
- Publication number
- CN109360562A CN109360562A CN201811494159.8A CN201811494159A CN109360562A CN 109360562 A CN109360562 A CN 109360562A CN 201811494159 A CN201811494159 A CN 201811494159A CN 109360562 A CN109360562 A CN 109360562A
- Authority
- CN
- China
- Prior art keywords
- voice
- wake
- signal
- output
- echo
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000004044 response Effects 0.000 claims abstract description 60
- 230000007246 mechanism Effects 0.000 claims description 56
- 230000005540 biological transmission Effects 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 230000003321 amplification Effects 0.000 claims description 5
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 5
- 238000013459 approach Methods 0.000 claims description 3
- 230000001755 vocal effect Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 13
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000002618 waking effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
- 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
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- 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
- G10L2021/02082—Noise filtering the noise being echo, reverberation of the speech
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)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Cable Transmission Systems, Equalization Of Radio And Reduction Of Echo (AREA)
Abstract
The embodiment of the invention discloses a kind of echo cancel method, device, medium and voice awakening method and equipment, this method comprises: obtaining the voice signal to be output to wake-up device；According to the voice signal to be output and the pre-stored device frequency response curve to wake-up device, echo cancellor is carried out to generate wake-up voice to the received initial wake-up voice of microphone institute.The echo signal as caused by play signal in initial wake-up voice generally can not be eliminated clean technical problem completely by the echo cancel method for solving the prior art, reach raising echo cancellor effect, and then improve the technical effect that voice wakes up success rate.
Description
Technical field
The present embodiments relate to voice processing technology field more particularly to a kind of echo cancel method, device, medium with
And voice awakening method and equipment.
Background technique
It is waken up when wake-up device by voice, initial wake-up language is usually obtained by the microphone to wake-up device
Then sound carries out processing extraction wake-up signal to the initial voice that wakes up.Wherein, when handling initial speech, if to
Wake-up device, which exists, puts voice outside, then need to be considered as in the initial wake-up voice of echo cancellation technology removal by play signal institute
The echo signal of generation.
The prior art is to acquire audio signal in the power amplifier output end to wake-up device, then through I2S (built in integrated circuit
Audio-frequency bus) it is transmitted directly to AEC (acoustic echo cancellation, the echo cancellor) broadcasting of module as back production
Signal, or the audio signal of acquisition is converted into digital signal by ADC, then be transferred to echo cancellation module through I2S.Echo
Cancellation module is compared using the wake-up sound that the play signal of back production is recorded with microphone, eliminates the broadcasting letter waken up in voice
Number, leave voice.But the initial echo signal waken up in voice generally can not be eliminated clean, voice wake-up by such method completely
Effect is poor.
Summary of the invention
The embodiment of the invention provides a kind of echo cancel method, device, medium and voice awakening method and equipment, solutions
The initial echo signal waken up in voice generally can not be eliminated clean, voice completely by the echo cancel method for the prior art of having determined
The poor problem of wake-up effect, to improve echo cancellor effect.
In a first aspect, being waken up the embodiment of the invention provides a kind of echo cancel method for voice, comprising:
Obtain the voice signal to be output to wake-up device；
According to the voice signal to be output and the pre-stored device frequency response curve to wake-up device, to Mike
The received initial wake-up voice of wind institute carries out echo cancellor to generate wake-up voice.
Second aspect, the embodiment of the invention also provides a kind of echo cancelling devices, are configured in voice wake-up device, packet
It includes:
First obtains module, for obtaining the voice signal to be output to wake-up device；
Voice determining module is waken up, for according to the voice signal to be output and pre-stored setting to wake-up device
Standby frequency response curve carries out echo cancellor to the received initial wake-up voice of microphone institute to generate wake-up voice.
The third aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Echo of the computer executable instructions when being executed by computer processor for executing as described in relation to the first aspect determines method.
Fourth aspect, the embodiment of the invention also provides a kind of voice awakening methods, comprising:
The initial wake-up voice to wake-up device is obtained by microphone；
It is determined according to echo cancel method described in the initial wake-up voice and first aspect and wakes up voice；
Enabling signal is determined according to the wake-up voice, and is started by the enabling signal to wake-up device.
5th aspect, the embodiment of the invention also provides a kind of voice wake-up devices, comprising:
Second voice obtains module, for being obtained by microphone to wake-up device initial speech wake-up signal；
Echo cancellation module wakes up for according to claim 1-the 5 any echo cancel methods and initial speech
Signal determines voice wake-up signal；
System module for determining enabling signal according to the wake-up voice, and starts according to the enabling signal wait call out
Awake equipment.
The technical solution of echo cancel method provided by the invention, comprising: obtain and believe to the voice to be output of wake-up device
Number；According to voice signal to be output and the pre-stored device frequency response curve to wake-up device, microphone is received
Initial wake-up voice carry out echo cancellor to generate wake-up voice.Believed by device frequency response curve and voice to be output
Number, it is estimated that the play signal that the broadcasting mechanism to wake-up device is exported, since output frequency response curve is introduced wait call out
The broadcasting mechanism for equipment of waking up treats the influence of output voice signal, therefore is based only upon voice signal to be output compared with the existing technology
It carries out for echo cancellor, echo cancellor effect can be greatly improved, and then improve voice wake-up effect.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing does one and simply introduces, it should be apparent that, drawings in the following description are some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, it can also be obtained according to these attached drawings others
Attached drawing.
Fig. 1 is the flow chart for the echo cancel method that the embodiment of the present invention one provides；
Fig. 2 is the frequency response curve schematic diagram to wake-up device that the embodiment of the present invention one provides；
Fig. 3 is the structural block diagram of echo cancelling device provided by Embodiment 2 of the present invention；
Fig. 4 is the flow chart for the voice awakening method that the embodiment of the present invention three provides；
Fig. 5 is the structural block diagram for the voice wake-up device that the embodiment of the present invention four provides.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, hereinafter with reference to attached in the embodiment of the present invention
Figure, clearly and completely describes technical solution of the present invention by embodiment, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is the flow chart for the echo cancel method that the embodiment of the present invention one provides.The technical solution of the present embodiment is applicable in
In improve voice wake up success rate the case where.This method can be realized by the way of software and/or hardware, and configure in system
It is applied in module.This method specifically comprises the following steps:
The voice signal to be output of S101, acquisition to wake-up device.
If having playing function to wake-up device, when carrying out voice wake-up to it, microphone institute is received initially to be called out
Echo is generally comprised in awake voice, which generated by the play signal of the broadcasting mechanism to wake-up device, due in reality
In the usage scenario on border, it has not been convenient to obtain actual play signal, therefore the present embodiment obtains voice signal to be output.Wherein,
Voice signal to be output is the speech output signal on system module to the voice transfer path for playing mechanism, such as system module
The speech output signal of speech output signal or the power amplifier module output of output.Broadcasting mechanism is loudspeaker.
S102, according to voice signal to be output and the pre-stored device frequency response curve to wake-up device, to wheat
Received initial the wake-ups voice progress echo cancellor of gram wind institute is to generate wake-up voice.
Voice signal to be output can be had an impact due to playing mechanism, i.e., the broadcasting voice signal that plays back of mechanism with
The frequency of voice signal before broadcasting is different, for this purpose, the present embodiment introduces device frequency response curve (referring to fig. 2), that is, passes through
Device frequency response curve simulates the influence that voice signal to be output is corresponded to the broadcasting mechanism of wake-up device, thus according to defeated
Voice signal estimates the play signal that is exported to the broadcasting mechanism of wake-up device with device frequency response curve to get arriving out
Estimate play signal.Wherein, frequency response refer to by one with constant voltage output audio signal be connected with system when, speaker
The acoustic pressure of generation with the variation of frequency and there is a phenomenon where increasing or decaying, phase change with frequency, this acoustic pressure and
Phase is known as frequency response with the associated variation relation of frequency.
After estimation play signal obtains, it is based on sef-adapting filter, it is true according to estimation play signal and initial wake-up signal
Determine echo signal；Echo signal is subtracted from initial speech wake-up signal to generate wake-up voice.Compared to sef-adapting filter
According to echo signal determined by voice signal to be output and initial wake-up signal, the sef-adapting filter of the present embodiment is according to estimating
The echo signal that meter play signal and initial wake-up signal determine is closer to actual scene, therefore the initial broadcasting waken up in voice
Signal removes more clean, and obtained wake-up voice is purer, is greatly improved the success rate of voice wake-up.
Device frequency response curve usually requires to obtain by means of testing, is then stored in in wake-up device,
Echo cancellation module is directly read when carrying out echo cancellor.The determination method of device frequency response curve are as follows: obtain to be output
The transmission that voice signal will enter/broadcasting mechanism and voice signal to be output enter play mechanism before need by
All transmission mechanisms, and the gain of all transmission mechanisms is disposed as 1；By different frequency, the frequency sweep vocal input of same magnitude
The transmission that will enter/broadcasting mechanism, and the output after the processing of all transmission mechanisms of frequency sweep sound is made extremely to play mechanism；Recording is broadcast
The frequency sweep sound for the different frequency that laying mechanism plays, and determined according to the frequency sweep sound recorded currently to the test frequency response of wake-up device
Curve；It obtains currently to the default device frequency response curve of wake-up device, and described default based on test frequency response curve adjustment
Device frequency response curve makes default device frequency response curve approach test frequency response curve bent with generating device frequency response
Line.
It is understood that if voice signal to be output is extracted before playing mechanism from voice transfer path ends
Voice signal, then may not need setting transmission path on each module gain, directly the voice signal is exported to broadcasting
Mechanism；For example, the voice signal is at least through function if voice signal to be output is the voice signal of system module output
Amplification module reaches broadcasting mechanism and then exports the voice signal to function at this time, it may be necessary to set 1 for the gain of power amplifier module
Amplification module, then exported by power amplifier module to broadcasting mechanism；If voice signal to be output is the voice signal of power amplifier module output,
So directly the voice signal is exported to broadcasting mechanism.
Under normal conditions, each different to the device frequency response curve between wake-up device, even same model,
Also not exactly the same with a batch of frequency response curve to wake-up device, best echo cancellor effect, then obtains in order to obtain
To optimal voice wake-up effect, especially when the play signal and higher wake-up voice similarity that wake-up device is played,
It needs individually to obtain each to the device frequency response curve of wake-up device in principle.But it is understood that if wait wake up
Voice that equipment is played and wake up differing greatly between voice, then when voice wakes up for echo cancellation technology according to
Lai Xinghui is reduced, and same model or can use the same device frequency response curve to wake-up device with a batch of at this time.
The technical solution of echo cancel method provided by the invention, comprising: obtain and believe to the voice to be output of wake-up device
Number；According to voice signal to be output and the pre-stored device frequency response curve to wake-up device, microphone is received
Initial wake-up voice carry out echo cancellor to generate wake-up voice.Believed by device frequency response curve and voice to be output
Number, it is estimated that the play signal that the broadcasting mechanism to wake-up device is exported, since output frequency response curve is introduced wait call out
The broadcasting mechanism for equipment of waking up treats the influence of output voice signal, therefore is based only upon voice signal to be output compared with the existing technology
It carries out for echo cancellor, echo cancellor effect can be greatly improved, and then improve voice wake-up effect.
Embodiment two
Fig. 3 is the structural block diagram of echo cancelling device provided in an embodiment of the present invention.The device is above-mentioned any for executing
Echo cancel method provided by embodiment, the device are chosen as software or hardware realization.The device includes:
First obtains module 11, for obtaining the voice signal to be output to wake-up device；
Voice determining module 12 is waken up, for according to voice signal to be output and the pre-stored equipment to wake-up device
Frequency response curve carries out echo cancellor to the received initial wake-up voice of microphone institute to generate wake-up voice.
The technical solution of echo cancelling device provided by the invention is obtained by obtaining module to the to be output of wake-up device
Voice signal；By waking up voice determining module according to voice signal to be output and the pre-stored equipment frequency to wake-up device
Rate response curve carries out echo cancellor to the received initial wake-up voice of microphone institute to generate wake-up voice.Pass through equipment frequency
Rate response curve and voice signal to be output, it is estimated that the play signal that the broadcasting mechanism to wake-up device is exported, by
The influence that output voice signal is treated to the broadcasting mechanism of wake-up device is introduced in output frequency response curve, therefore relative to existing
Technology is based only upon voice signal to be output and carries out for echo cancellor, can greatly improve echo cancellor effect, and then improve language
Sound wake-up effect.
Voice Rouser provided by the embodiment of the present invention can be performed voice provided by any embodiment of the invention and call out
Awake method, has the corresponding functional module of execution method and beneficial effect.
Embodiment three
Fig. 4 is the flow chart for the voice awakening method that the embodiment of the present invention three provides.The technical solution of the present embodiment is applicable in
In improve voice wake up success rate the case where.This method can be realized by the way of software and/or hardware, and configure in system
It is applied in module.This method specifically comprises the following steps:
S201, the initial wake-up voice to wake-up device is obtained by microphone.
When treating wake-up device and carrying out voice wake-up, echo cancellation module needs to first pass through microphone and obtains to be set wait wake up
Standby initial wake-up voice.For example, user first says wake-up voice to this microphone when carrying out voice wake-up to TV, return
Sound cancellation module obtains the initial wake-up language including the play signal for waking up voice, the mechanism that televises output by Mike
Sound.
S202, the determining wake-up voice of echo cancel method described in voice and previous embodiment is waken up according to initial.
Echo cancellation module is after getting initial wake-up voice, the echo cancel method pair according to previous embodiment
The initial voice that wakes up carries out echo cancellation process, removes the wherein echo signal as caused by play signal, to obtain waking up language
Sound.Specifically:
Echo cancellation module also obtains voice signal to be output while obtaining initial wake-up voice by microphone.
Wherein, voice signal to be output is the speech output signal on system module to the voice transfer path for playing mechanism, for example is
The speech output signal of module of uniting output or the speech output signal of power amplifier module output.
Voice signal to be output can be had an impact due to playing mechanism, i.e., the broadcasting voice signal that plays back of mechanism with
The frequency of voice signal before broadcasting is not identical, for this purpose, the present embodiment introduces device frequency response curve (referring to fig. 2), i.e., it is logical
Cross the simulation of device frequency response curve and correspond to the influence of voice signal to be output to the broadcasting mechanism of wake-up device, thus according to
Output voice signal and device frequency response curve estimate the play signal that is exported to the broadcasting mechanism of wake-up device to get
To estimation play signal.Wherein, frequency response refer to by one with constant voltage output audio signal be connected with system when, sound
The acoustic pressure that case generates with the variation of frequency and there is a phenomenon where increase or decaying, phase change with frequency, this acoustic pressure
It is known as frequency response with the associated variation relation of frequency with phase.
After estimation play signal obtains, it is based on sef-adapting filter, it is true according to estimation play signal and initial wake-up signal
Determine echo signal；Echo signal is subtracted from initial speech wake-up signal to generate wake-up voice.Compared to sef-adapting filter
According to echo signal determined by voice signal to be output and initial wake-up signal, the sef-adapting filter of the present embodiment is according to estimating
The echo signal that meter play signal and initial wake-up signal determine is closer to actual scene, therefore the initial broadcasting waken up in voice
Signal removes more clean, and obtained wake-up voice is purer, is greatly improved the success rate of voice wake-up.
Device frequency response curve usually requires to obtain by means of testing, is then stored in in wake-up device,
Echo cancellation module is directly read when carrying out echo cancellor.The determination method of device frequency response curve are as follows: obtain to be output
The transmission that voice signal will enter/broadcasting mechanism and voice signal to be output enter play mechanism before need by
All transmission mechanisms, and the gain of all transmission mechanisms is disposed as 1；By different frequency, the frequency sweep vocal input of same magnitude
The transmission that will enter/broadcasting mechanism, and the output after the processing of all transmission mechanisms of frequency sweep sound is made extremely to play mechanism；Recording is broadcast
The frequency sweep sound for the different frequency that laying mechanism plays, and determined according to the frequency sweep sound recorded currently to the test frequency response of wake-up device
Curve；It obtains currently to the default device frequency response curve of wake-up device, and described default based on test frequency response curve adjustment
Device frequency response curve makes default device frequency response curve approach test frequency response curve bent with generating device frequency response
Line.
It is understood that if voice signal to be output is extracted before playing mechanism from voice transfer path ends
Voice signal, then may not need setting transmission path on each module gain, directly the voice signal is exported to broadcasting
Mechanism；For example, the voice signal is at least through function if voice signal to be output is the voice signal of system module output
Amplification module reaches broadcasting mechanism and then exports the voice signal to function at this time, it may be necessary to set 1 for the gain of power amplifier module
Amplification module, then exported by power amplifier module to broadcasting mechanism；If voice signal to be output is the voice signal of power amplifier module output,
So directly the voice signal is exported to broadcasting mechanism.
S203, enabling signal is determined according to wake-up voice, and is started by enabling signal to wake-up device.
Echo cancellation module can will wake up voice output to system module by USB or near-field communication, system module according to
It wakes up voice and determines enabling signal, then started by enabling signal to wake-up device.
The technical solution of voice awakening method provided in an embodiment of the present invention is obtained by microphone to the first of wake-up device
Begin to wake up voice；The determining wake-up voice of echo cancel method described in voice and previous embodiment is waken up according to initial；According to calling out
Awake voice determines enabling signal, and is started by enabling signal to wake-up device.Due to the echo cancel method of previous embodiment
Available very pure wake-up voice, therefore enabling signal can be accurately determined according to voice is waken up, it is ensured that language
Sound wakes up success rate with higher.
Example IV
Fig. 5 is the structural block diagram for the voice wake-up device that the embodiment of the present invention four provides.The equipment includes: the second acquisition mould
Block 2, echo cancellation module 1 and system module 3, second, which obtains module 2, is used to obtain by microphone to the initial language of wake-up device
Sound wake-up signal；Echo cancellation module 1 wakes up letter for the echo cancel method according to previous embodiment and initial speech
Number determine voice wake-up signal；System module 3 is used to determine enabling signal according to waking up voice, and according to enabling signal starting to
Wake-up device.
Wherein, the echo cancellation module 1 of the present embodiment is the chip for being integrated with echo cancellation algorithm, such as DSP
(Digital Signal Processing, abbreviation DSP), FPGA (Field-Programmable Gate Array, referred to as
FPGA) etc., echo cancellation module 1 determines the detailed process of voice wake-up signal referring to previous embodiment, and the present embodiment is herein not
It gives and repeating.
The technical solution of voice wake-up device provided in an embodiment of the present invention obtains module based on voice and is obtained by microphone
Take the initial wake-up voice to wake-up device；It is waken up described in voice and previous embodiment by echo cancellation module according to initial
Echo cancel method, which determines, wakes up voice；Enabling signal is determined according to voice is waken up by system module, and passes through enabling signal
Starting is to wake-up device.It, can due to the available very pure wake-up voice of the echo cancel method of previous embodiment
To accurately determine enabling signal according to wake-up voice, it is ensured that voice wakes up success rate with higher.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction is used to execute a kind of echo cancel method when being executed by computer processor, this method comprises:
Obtain the voice signal to be output to wake-up device；
According to voice signal to be output and the pre-stored device frequency response curve to wake-up device, to microphone institute
Received initial wake-up voice carries out echo cancellor to generate wake-up voice.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed echo cancellor provided by any embodiment of the invention
Relevant operation in method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, abbreviation ROM), random access memory (Random such as computer
Access Memory, abbreviation RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are used so that a calculating
Machine equipment (can be personal computer, server or the network equipment etc.) executes echo described in each embodiment of the present invention
Removing method.
It is worth noting that, included each unit and module are only pressed in the embodiment of above-mentioned echo cancelling device
It is divided, but is not limited to the above division according to function logic, as long as corresponding functions can be realized；In addition,
The specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of echo cancel method wakes up for voice characterized by comprising
Obtain the voice signal to be output to wake-up device；
According to the voice signal to be output and the pre-stored device frequency response curve to wake-up device, to microphone institute
Received initial wake-up voice carries out echo cancellor to generate wake-up voice.
2. the method according to claim 1, wherein the to be output voice signal of the acquisition to wake-up device,
Include:
The voice signal on the system module to the voice transfer path for playing mechanism to wake-up device is obtained, and the voice is believed
Number be used as voice signal to be output.
3. according to the method described in claim 2, it is characterized in that, the voice signal to be output of system module output is through function
Amplification module is exported to mechanism is played, correspondingly, described obtain the voice transfer for extremely playing mechanism to the system module of wake-up device
Speech output signal on path, comprising:
The speech output signal exported to the system module of wake-up device is obtained, or obtains and is exported to the power amplifier module of wake-up device
Speech output signal.
4. the method according to claim 1, wherein described according to the voice signal to be output and being stored in advance
The device frequency response curve to wake-up device, to received initial the wake-ups voice progress echo cancellor of microphone institute to generate
Wake up voice, comprising:
The voice signal to be output is handled according to the device frequency response curve to obtain estimation play signal；
Based on sef-adapting filter, echo signal is determined according to the estimation play signal and initial wake-up signal；
The echo signal is subtracted from the initial speech wake-up signal to generate wake-up voice.
5. according to the method described in claim 3, it is characterized in that, the determination method of the device frequency response curve includes:
It obtains transmission/broadcasting mechanism that voice signal to be output will enter and the voice signal to be output and broadcasts entering
Needed before laying mechanism by all transmission mechanisms, and the gain of all transmission mechanisms is disposed as 1；
The transmission that the frequency sweep vocal input of different frequency, same magnitude will be entered/broadcasting mechanism, and pass through the frequency sweep sound
It exports after all transmission mechanism processing to the broadcasting mechanism；
The frequency sweep sound for playing the different frequency that mechanism plays is recorded, and is determined according to the frequency sweep sound recorded currently to wake-up device
Test frequency response curve；
It obtains currently to the default device frequency response curve of wake-up device, and described pre- based on test frequency response curve adjustment
If device frequency response curve, the default device frequency response curve is made to approach the test frequency response curve with generating device frequency
Rate response curve.
6. a kind of echo cancelling device is configured in voice wake-up device characterized by comprising
First obtains module, for obtaining the voice signal to be output to wake-up device；
Voice determining module is waken up, for according to the voice signal to be output and the pre-stored equipment frequency to wake-up device
Rate response curve carries out echo cancellor to the received initial wake-up voice of microphone institute to generate wake-up voice.
7. a kind of storage medium comprising computer executable instructions, which is characterized in that the computer executable instructions by
For executing as echo as claimed in any one of claims 1 to 5 determines method when computer processor executes.
8. a kind of voice awakening method characterized by comprising
The initial wake-up voice to wake-up device is obtained by microphone；
It determines according to the initial wake-up voice and any echo cancel method of claim 1-5 and wakes up voice；
Enabling signal is determined according to the wake-up voice, and is started by the enabling signal to wake-up device.
9. a kind of voice wake-up device characterized by comprising
Second voice obtains module, for being obtained by microphone to wake-up device initial speech wake-up signal；
Echo cancellation module, for according to claim 1-the 5 any echo cancel methods and initial speech wake-up signal
Determine voice wake-up signal；
System module for determining enabling signal according to the wake-up voice, and starts according to the enabling signal and sets wait wake up
It is standby.
10. voice wake-up device according to claim 9, which is characterized in that the echo cancellation module and the system
Module is connected by USB or near-field communication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811494159.8A CN109360562B (en) | 2018-12-07 | 2018-12-07 | Echo cancellation method, device, medium, and voice wake-up method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811494159.8A CN109360562B (en) | 2018-12-07 | 2018-12-07 | Echo cancellation method, device, medium, and voice wake-up method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109360562A true CN109360562A (en) | 2019-02-19 |
| CN109360562B CN109360562B (en) | 2022-06-28 |
Family
ID=65331716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811494159.8A Active CN109360562B (en) | 2018-12-07 | 2018-12-07 | Echo cancellation method, device, medium, and voice wake-up method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109360562B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136736A (en) * | 2019-05-27 | 2019-08-16 | 广州视源电子科技股份有限公司 | A kind of echo cancellation system, method, apparatus, equipment and storage medium |
| 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 |
| CN110660407A (en) * | 2019-11-29 | 2020-01-07 | 恒玄科技(北京)有限公司 | Audio processing method and device |
| CN111179931A (en) * | 2020-01-03 | 2020-05-19 | 青岛海尔科技有限公司 | Method and device for voice interaction and household appliance |
| CN111798852A (en) * | 2019-06-27 | 2020-10-20 | 深圳市豪恩声学股份有限公司 | Voice wake-up recognition performance test method, device and system and terminal equipment |
| CN111798864A (en) * | 2020-07-02 | 2020-10-20 | 杭州海康威视数字技术股份有限公司 | Echo cancellation method and device, electronic equipment and storage medium |
| KR20200141126A (en) * | 2019-06-10 | 2020-12-18 | 주식회사 케이티 | Device and method for preventing misperception of wake word |
| WO2021004067A1 (en) * | 2019-07-10 | 2021-01-14 | 海信视像科技股份有限公司 | Display device |
| CN113038048A (en) * | 2021-03-02 | 2021-06-25 | 海信视像科技股份有限公司 | Far-field voice awakening method and display device |
| CN113763945A (en) * | 2020-12-29 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Voice awakening method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177723A (en) * | 2011-12-20 | 2013-06-26 | 上海博泰悦臻电子设备制造有限公司 | Speech processing device, vehicle-mounted terminal device and speech processing method |
| CN105187594A (en) * | 2015-07-28 | 2015-12-23 | 小米科技有限责任公司 | Echo canceling method and device |
| CN107452398A (en) * | 2017-08-09 | 2017-12-08 | 深圳创维数字技术有限公司 | Echo acquisition methods, electronic equipment and computer-readable recording medium |
| CN108538305A (en) * | 2018-04-20 | 2018-09-14 | 百度在线网络技术（北京）有限公司 | Audio recognition method, device, equipment and computer readable storage medium |
| US10109294B1 (en) * | 2016-03-25 | 2018-10-23 | Amazon Technologies, Inc. | Adaptive echo cancellation |
-
2018
- 2018-12-07 CN CN201811494159.8A patent/CN109360562B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177723A (en) * | 2011-12-20 | 2013-06-26 | 上海博泰悦臻电子设备制造有限公司 | Speech processing device, vehicle-mounted terminal device and speech processing method |
| CN105187594A (en) * | 2015-07-28 | 2015-12-23 | 小米科技有限责任公司 | Echo canceling method and device |
| US10109294B1 (en) * | 2016-03-25 | 2018-10-23 | Amazon Technologies, Inc. | Adaptive echo cancellation |
| CN107452398A (en) * | 2017-08-09 | 2017-12-08 | 深圳创维数字技术有限公司 | Echo acquisition methods, electronic equipment and computer-readable recording medium |
| CN108538305A (en) * | 2018-04-20 | 2018-09-14 | 百度在线网络技术（北京）有限公司 | Audio recognition method, device, equipment and computer readable storage medium |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136736A (en) * | 2019-05-27 | 2019-08-16 | 广州视源电子科技股份有限公司 | A kind of echo cancellation system, method, apparatus, equipment and storage medium |
| KR102402465B1 (en) * | 2019-06-10 | 2022-05-26 | 주식회사 케이티 | Device and method for preventing misperception of wake word |
| KR20200141126A (en) * | 2019-06-10 | 2020-12-18 | 주식회사 케이티 | Device and method for preventing misperception of wake word |
| CN111798852A (en) * | 2019-06-27 | 2020-10-20 | 深圳市豪恩声学股份有限公司 | Voice wake-up recognition performance test method, device and system and terminal equipment |
| CN111798852B (en) * | 2019-06-27 | 2024-03-29 | 深圳市豪恩声学股份有限公司 | Voice wakeup recognition performance test method, device, system and terminal equipment |
| CN110223707A (en) * | 2019-07-10 | 2019-09-10 | 青岛海信电器股份有限公司 | Display device |
| WO2021004067A1 (en) * | 2019-07-10 | 2021-01-14 | 海信视像科技股份有限公司 | 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 |
| CN110660407A (en) * | 2019-11-29 | 2020-01-07 | 恒玄科技(北京)有限公司 | Audio processing method and device |
| CN110660407B (en) * | 2019-11-29 | 2020-03-17 | 恒玄科技(北京)有限公司 | Audio processing method and device |
| CN111179931A (en) * | 2020-01-03 | 2020-05-19 | 青岛海尔科技有限公司 | Method and device for voice interaction and household appliance |
| CN111179931B (en) * | 2020-01-03 | 2023-07-21 | 青岛海尔科技有限公司 | Method and device for voice interaction and household appliance |
| CN111798864A (en) * | 2020-07-02 | 2020-10-20 | 杭州海康威视数字技术股份有限公司 | Echo cancellation method and device, electronic equipment and storage medium |
| CN111798864B (en) * | 2020-07-02 | 2024-06-04 | 杭州海康威视数字技术股份有限公司 | Echo cancellation method and device, electronic equipment and storage medium |
| CN113763945A (en) * | 2020-12-29 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Voice awakening method, device, equipment and storage medium |
| CN113763945B (en) * | 2020-12-29 | 2024-05-17 | 北京沃东天骏信息技术有限公司 | Voice awakening method, device, equipment and storage medium |
| CN113038048A (en) * | 2021-03-02 | 2021-06-25 | 海信视像科技股份有限公司 | Far-field voice awakening method and display device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109360562B (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360562A (en) | Echo cancel method, device, medium and voice awakening method and equipment | |
| US11017799B2 (en) | Method for processing voice in interior environment of vehicle and electronic device using noise data based on input signal to noise ratio | |
| CN111883156B (en) | Audio processing method and device, electronic equipment and storage medium | |
| US11064296B2 (en) | Voice denoising method and apparatus, server and storage medium | |
| US11502859B2 (en) | Method and apparatus for waking up via speech | |
| CN111951819A (en) | Echo cancellation method, device and storage medium | |
| JP2019128939A (en) | Gesture based voice wakeup method, apparatus, arrangement and computer readable medium | |
| WO2020097828A1 (en) | Echo cancellation method, delay estimation method, echo cancellation apparatus, delay estimation apparatus, storage medium, and device | |
| CN105612576A (en) | Limiting active noise cancellation output | |
| US11587560B2 (en) | Voice interaction method, device, apparatus and server | |
| WO2015039441A1 (en) | Sound volume adjusting method and device | |
| US20140334631A1 (en) | Noise reduction | |
| CN104505099A (en) | Method and equipment for removing known interference in voice signal | |
| CN110956976A (en) | Echo cancellation method, device, equipment and readable storage medium | |
| CN112309416B (en) | Vehicle-mounted voice echo eliminating method, system, vehicle and storage medium | |
| CN111081246B (en) | Method and device for awakening live broadcast robot, electronic equipment and storage medium | |
| CN112289336A (en) | Audio signal processing method and device | |
| CN111402910B (en) | Method and equipment for eliminating echo | |
| CN111356058B (en) | Echo cancellation method and device and intelligent sound box | |
| CN106297816B (en) | Echo cancellation nonlinear processing method and device and electronic equipment | |
| JP5970125B2 (en) | Control device, control method and program | |
| CN110021289B (en) | Sound signal processing method, device and storage medium | |
| CN110797040A (en) | Noise elimination method, intelligent sound box and storage medium | |
| CN105812568A (en) | Mobile terminal and method for automatically playing music | |
| CN105828252A (en) | Distribution method for microphone control and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |