CN109360562B - Echo cancellation method, device, medium, and voice wake-up method and device - Google Patents
Echo cancellation method, device, medium, and voice wake-up method and device Download PDFInfo
- Publication number
- CN109360562B CN109360562B CN201811494159.8A CN201811494159A CN109360562B CN 109360562 B CN109360562 B CN 109360562B CN 201811494159 A CN201811494159 A CN 201811494159A CN 109360562 B CN109360562 B CN 109360562B
- Authority
- CN
- China
- Prior art keywords
- voice
- signal
- output
- wake
- awakened
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000004044 response Effects 0.000 claims abstract description 60
- 230000007246 mechanism Effects 0.000 claims description 57
- 230000005540 biological transmission Effects 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 5
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 13
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 230000002238 attenuated effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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 an echo cancellation method, an echo cancellation device, an echo cancellation medium, a voice awakening method and voice awakening equipment, wherein the method comprises the following steps: acquiring a voice signal to be output of a device to be awakened; and according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate awakening voice. The technical problem that echo signals generated by playing signals in initial awakening voice cannot be completely eliminated by an echo eliminating method in the prior art is solved, the echo eliminating effect is improved, and the technical effect of improving the success rate of voice awakening is achieved.
Description
Technical Field
The embodiment of the invention relates to the technical field of voice processing, in particular to an echo cancellation method, an echo cancellation device, an echo cancellation medium, a voice awakening method and voice awakening equipment.
Background
When a device to be woken up is woken up by voice, an initial wake-up voice is generally acquired by a microphone of the device to be woken up, and then the initial wake-up voice is processed to extract a wake-up signal. When the initial voice is processed, if the device to be wakened has the outgoing voice, the echo cancellation technology is considered to be adopted to remove the echo signal generated by the playing signal in the initial wakening voice.
In the prior art, an audio signal is collected at an output end of a power amplifier of a device to be woken up, and then directly transmitted to an AEC (acoustic echo cancellation) module through an I2S (integrated circuit built-in audio bus) to be used as a playback signal for playback, or the collected audio signal is converted into a digital signal through an ADC, and then transmitted to an echo cancellation module through an I2S. The echo cancellation module compares the picked playing signal with the awakening sound recorded by the microphone to cancel the playing signal in the awakening voice and leave the voice. However, this method usually cannot completely eliminate the echo signal in the initial wake-up voice, and the voice wake-up effect is poor.
Disclosure of Invention
The embodiment of the invention provides an echo cancellation method, an echo cancellation device, an echo cancellation medium, a voice awakening method and voice awakening equipment, and solves the problems that echo signals in initial awakening voice cannot be completely eliminated and the voice awakening effect is poor in the echo cancellation method in the prior art, so that the echo cancellation effect is improved.
In a first aspect, an embodiment of the present invention provides an echo cancellation method for voice wakeup, including:
acquiring a voice signal to be output of a device to be awakened;
and according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate awakening voice.
In a second aspect, an embodiment of the present invention further provides an echo cancellation device configured in a voice wake-up device, including:
the first acquisition module is used for acquiring a voice signal to be output of the equipment to be awakened;
and the awakening voice determining module is used for performing echo cancellation on the initial awakening voice received by the microphone according to the to-be-output voice signal and a pre-stored device frequency response curve of the to-be-awakened device so as to generate the awakening voice.
In a third aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the echo determination method according to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a voice wake-up method, including:
acquiring initial awakening voice of equipment to be awakened through a microphone;
determining a wake-up voice according to the initial wake-up voice and the echo cancellation method of the first aspect;
and determining a starting signal according to the awakening voice, and starting the equipment to be awakened through the starting signal.
In a fifth aspect, an embodiment of the present invention further provides a voice wake-up device, including:
The second voice acquisition module is used for acquiring an initial voice wake-up signal of the equipment to be woken up through the microphone;
an echo cancellation module for determining a voice wake-up signal according to the echo cancellation method of any one of claims 1 to 5 and the initial voice wake-up signal;
and the system module is used for determining a starting signal according to the awakening voice and starting the equipment to be awakened according to the starting signal.
The technical scheme of the echo cancellation method provided by the invention comprises the following steps: acquiring a voice signal to be output of a device to be awakened; and according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate the awakening voice. The playing signal output by the playing mechanism of the device to be awakened can be estimated through the device frequency response curve and the voice signal to be output, and because the influence of the playing mechanism of the device to be awakened on the voice signal to be output is introduced into the output frequency response curve, compared with the prior art that echo cancellation is carried out only on the voice signal to be output, the echo cancellation effect can be greatly improved, and then the voice awakening effect is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of an echo cancellation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a frequency response curve of a device to be woken up according to an embodiment of the present invention;
fig. 3 is a block diagram of an echo cancellation device according to a second embodiment of the present invention;
fig. 4 is a flowchart of a voice wake-up method according to a third embodiment of the present invention;
fig. 5 is a block diagram of a voice wake-up apparatus according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through embodiments with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Fig. 1 is a flowchart of an echo cancellation method according to an embodiment of the present invention. The technical scheme of the embodiment is suitable for improving the success rate of voice awakening. The method can be realized in a software and/or hardware mode and is configured to be applied in a system module. The method specifically comprises the following steps:
s101, acquiring a voice signal to be output of the equipment to be awakened.
If the device to be woken up has a playing function, when the device to be woken up is woken up by voice, the initial wake-up voice received by the microphone usually contains an echo, the echo is generated by a playing signal of a playing mechanism of the device to be woken up, and because in an actual use scene, the actual playing signal is inconvenient to obtain, the voice signal to be output is obtained in the embodiment. The voice signal to be output is a voice output signal on a voice transmission path from the system module to the playing mechanism, such as a voice output signal output by the system module or a voice output signal output by the power amplification module. The playback mechanism is a speaker.
S102, according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate awakening voice.
Since the playing mechanism may affect the voice signal to be output, that is, the frequency of the voice signal played by the playing mechanism is different from the frequency of the voice signal before playing, for this reason, an equipment frequency response curve (see fig. 2) is introduced in this embodiment, that is, the influence of the playing mechanism of the device to be awakened on the voice signal to be output is simulated by the equipment frequency response curve, so that the playing signal output by the playing mechanism of the device to be awakened is estimated according to the voice signal to be output and the equipment frequency response curve, that is, the estimated playing signal is obtained. The frequency response refers to a phenomenon that when an audio signal output by constant voltage is connected with a system, sound pressure generated by a sound box is increased or attenuated along with the change of frequency, and the phase is changed along with the change of frequency, and the related change relationship between the sound pressure and the phase and the frequency is called frequency response.
After the estimated playing signal is obtained, based on the adaptive filter, determining an echo signal according to the estimated playing signal and the initial wake-up signal; the echo signal is subtracted from the initial voice wake-up signal to generate a wake-up voice. Compared with the echo signal determined by the adaptive filter according to the voice signal to be output and the initial wake-up signal, the echo signal determined by the adaptive filter according to the estimated play signal and the initial wake-up signal is closer to the actual scene, so that the play signal in the initial wake-up voice is removed more cleanly, the obtained wake-up voice is purer, and the success rate of voice wake-up can be greatly improved.
The device frequency response curve is usually acquired by a test means and then stored in the device to be woken up, and the echo cancellation module directly reads the echo when performing echo cancellation. The method for determining the frequency response curve of the equipment comprises the following steps: acquiring a transmission/playback mechanism to which a voice signal to be output is about to enter and all transmission mechanisms which the voice signal to be output needs to pass before entering the playback mechanism, and setting the gains of all the transmission mechanisms to be 1; inputting sweep frequency sound with different frequencies and the same amplitude into a transmission/playing mechanism to be entered, and outputting the sweep frequency sound to the playing mechanism after the sweep frequency sound is processed by all the transmission mechanisms; recording the frequency sweep sound with different frequencies played by the playing mechanism, and determining a test frequency response curve of the current equipment to be awakened according to the recorded frequency sweep sound; and acquiring a preset device frequency response curve of the current device to be awakened, and adjusting the preset device frequency response curve based on the test frequency response curve to enable the preset device frequency response curve to approach the test frequency response curve so as to generate a device frequency response curve.
It can be understood that, if the voice signal to be output is the voice signal extracted before the playing mechanism from the end of the voice transmission path, the voice signal can be directly output to the playing mechanism without setting the gain of each module on the transmission path; for example, if the voice signal to be output is the voice signal output by the system module, the voice signal at least reaches the playing mechanism through the power amplifier module, at this time, the gain of the power amplifier module needs to be set to 1, and then the voice signal is output to the power amplifier module and then output to the playing mechanism through the power amplifier module; if the voice signal to be output is the voice signal output by the power amplification module, the voice signal is directly output to the playing mechanism.
In general, the frequency response curves of devices to be awakened are different, and even if the frequency response curves of devices to be awakened of the same model and the same batch are not completely the same, in order to obtain the best echo cancellation effect and then the best voice awakening effect, especially when the similarity between the played signal played by the device to be awakened and the awakening voice is high, the device frequency response curve of each device to be awakened needs to be obtained independently in principle. However, it can be understood that if the difference between the voice played by the device to be woken up and the voice to be woken up is large, the dependency on the echo cancellation technique is reduced when the device to be woken up is woken up by voice, and the same device frequency response curve can be adopted by the devices to be woken up of the same model or the same batch.
The technical scheme of the echo cancellation method provided by the invention comprises the following steps: acquiring a voice signal to be output of a device to be awakened; and according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate the awakening voice. The playing signal output by the playing mechanism of the device to be awakened can be estimated through the device frequency response curve and the voice signal to be output, and because the influence of the playing mechanism of the device to be awakened on the voice signal to be output is introduced into the output frequency response curve, compared with the prior art that echo cancellation is carried out only on the voice signal to be output, the echo cancellation effect can be greatly improved, and the voice awakening effect is further improved.
Example two
Fig. 3 is a block diagram of an echo cancellation device according to an embodiment of the present invention. The apparatus is adapted to perform the echo cancellation method provided in any of the above embodiments, and the apparatus may be implemented in software or hardware. The device includes:
the first obtaining module 11 is configured to obtain a to-be-output voice signal of a to-be-woken device;
and a wake-up voice determining module 12, configured to perform echo cancellation on the initial wake-up voice received by the microphone according to the to-be-output voice signal and a pre-stored device frequency response curve of the to-be-wake-up device to generate a wake-up voice.
According to the technical scheme of the echo cancellation device, the voice signal to be output of the equipment to be awakened is obtained through the obtaining module; and performing echo cancellation on the initial wake-up voice received by the microphone to generate wake-up voice according to the voice signal to be output and a pre-stored device frequency response curve of the device to be woken up through the wake-up voice determining module. The playing signal output by the playing mechanism of the device to be awakened can be estimated through the device frequency response curve and the voice signal to be output, and because the influence of the playing mechanism of the device to be awakened on the voice signal to be output is introduced into the output frequency response curve, compared with the prior art that echo cancellation is carried out only on the voice signal to be output, the echo cancellation effect can be greatly improved, and then the voice awakening effect is improved.
The voice awakening device provided by the embodiment of the invention can execute the voice awakening method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
Fig. 4 is a flowchart of a voice wake-up method according to a third embodiment of the present invention. The technical scheme of the embodiment is suitable for improving the success rate of voice awakening. The method can be realized in a software and/or hardware mode and is configured to be applied in a system module. The method specifically comprises the following steps:
s201, acquiring initial awakening voice of the equipment to be awakened through a microphone.
When the device to be awakened is awakened by voice, the echo cancellation module needs to acquire the initial awakening voice of the device to be awakened through the microphone. For example, when a television is woken up by voice, a user speaks a wake-up voice to the microphone first, and the echo cancellation module obtains an initial wake-up voice including the wake-up voice and a play signal output by the television playing mechanism through the microphone.
S202, determining the awakening voice according to the initial awakening voice and the echo cancellation method in the embodiment.
After the echo cancellation module obtains the initial wake-up voice, the echo cancellation module performs echo cancellation processing on the initial wake-up voice according to the echo cancellation method described in the foregoing embodiment, and removes an echo signal generated by the play signal, so as to obtain the wake-up voice. The method specifically comprises the following steps:
The echo cancellation module acquires initial wake-up voice through a microphone and simultaneously acquires a voice signal to be output. The voice signal to be output is a voice output signal on a voice transmission path from the system module to the playing mechanism, such as a voice output signal output by the system module or a voice output signal output by the power amplification module.
Since the playing mechanism may affect the voice signal to be output, that is, the frequency of the voice signal played by the playing mechanism is different from the frequency of the voice signal before playing, for this reason, an equipment frequency response curve (see fig. 2) is introduced in this embodiment, that is, the influence of the playing mechanism of the device to be awakened on the voice signal to be output is simulated by the equipment frequency response curve, so that the playing signal output by the playing mechanism of the device to be awakened is estimated according to the voice signal to be output and the equipment frequency response curve, that is, the estimated playing signal is obtained. The frequency response refers to a phenomenon that when an audio signal output by constant voltage is connected with a system, sound pressure generated by a sound box is increased or attenuated along with the change of frequency, and the phase is changed along with the change of frequency, and the related change relationship between the sound pressure and the phase and the frequency is called frequency response.
After the estimated playing signal is obtained, based on the adaptive filter, determining an echo signal according to the estimated playing signal and the initial wake-up signal; the echo signal is subtracted from the initial voice wake-up signal to generate a wake-up voice. Compared with the echo signal determined by the adaptive filter according to the to-be-output voice signal and the initial wake-up signal, the echo signal determined by the adaptive filter according to the estimated play signal and the initial wake-up signal is closer to the actual scene, so that the play signal in the initial wake-up voice is removed more cleanly, the obtained wake-up voice is purer, and the success rate of voice wake-up can be greatly improved.
The device frequency response curve is usually acquired by a test means and then stored in the device to be wakened, and the echo cancellation module directly reads the curve when performing echo cancellation. The method for determining the frequency response curve of the equipment comprises the following steps: acquiring a transmission/playing mechanism to which a voice signal to be output is about to enter and all transmission mechanisms through which the voice signal to be output needs to pass before entering the playing mechanism, and setting the gain of all the transmission mechanisms to be 1; inputting sweep frequency sound with different frequencies and the same amplitude into a transmission/playing mechanism to be entered, and outputting the sweep frequency sound to the playing mechanism after the sweep frequency sound is processed by all the transmission mechanisms; recording the frequency sweep sounds with different frequencies played by the player mechanism, and determining a test frequency response curve of the current equipment to be awakened according to the recorded frequency sweep sounds; and acquiring a preset device frequency response curve of the current device to be awakened, and adjusting the preset device frequency response curve based on the test frequency response curve to enable the preset device frequency response curve to approach the test frequency response curve so as to generate a device frequency response curve.
It can be understood that, if the voice signal to be output is the voice signal extracted from the end of the voice transmission path before the playing mechanism, the voice signal can be directly output to the playing mechanism without setting the gain of each module on the transmission path; for example, if the voice signal to be output is a voice signal output by the system module, the voice signal at least reaches the playing mechanism through the power amplifier module, at this time, the gain of the power amplifier module needs to be set to 1, and then the voice signal is output to the power amplifier module and then output to the playing mechanism by the power amplifier module; if the voice signal to be output is the voice signal output by the power amplification module, the voice signal is directly output to the playing mechanism.
And S203, determining a starting signal according to the awakening voice, and starting the equipment to be awakened through the starting signal.
The echo cancellation module can output the awakening voice to the system module through a USB or near field communication, the system module determines a starting signal according to the awakening voice, and then starts the equipment to be awakened through the starting signal.
According to the technical scheme of the voice awakening method provided by the embodiment of the invention, the initial awakening voice of the equipment to be awakened is acquired through the microphone; determining a wake-up voice according to the initial wake-up voice and the echo cancellation method described in the foregoing embodiment; and determining a starting signal according to the awakening voice, and starting the equipment to be awakened through the starting signal. Since the echo cancellation method of the foregoing embodiment can obtain a very pure wake-up voice, the start signal can be accurately determined according to the wake-up voice, and it can be ensured that the voice wake-up has a high success rate.
Example four
Fig. 5 is a block diagram of a voice wake-up device according to a fourth embodiment of the present invention. The apparatus includes: the device comprises a second acquisition module 2, an echo cancellation module 1 and a system module 3, wherein the second acquisition module 2 is used for acquiring an initial voice wake-up signal of the device to be woken up through a microphone; the echo cancellation module 1 is configured to determine a voice wake-up signal according to the echo cancellation method and the initial voice wake-up signal described in the foregoing embodiment; the system module 3 is used for determining a starting signal according to the awakening voice and starting the equipment to be awakened according to the starting signal.
The echo cancellation module 1 of this embodiment is a chip integrated with an echo cancellation algorithm, for example, a DSP (Digital Signal Processing, abbreviated as DSP), an FPGA (Field-Programmable Gate Array, abbreviated as FPGA), and the specific process of the echo cancellation module 1 determining the voice wake-up Signal is referred to in the foregoing embodiment, which is not described herein again.
According to the technical scheme of the voice awakening device, the initial awakening voice of the device to be awakened is obtained through the microphone based on the voice obtaining module; determining a wake-up voice according to the initial wake-up voice and the echo cancellation method of the embodiment by an echo cancellation module; and determining a starting signal according to the awakening voice through the system module, and starting the equipment to be awakened through the starting signal. Since the echo cancellation method of the foregoing embodiment can obtain a very pure wake-up voice, the start signal can be accurately determined according to the wake-up voice, and it can be ensured that the voice wake-up has a high success rate.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for echo cancellation, the method including:
acquiring a voice signal to be output of a device to be awakened;
and according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate the awakening voice.
Of course, the storage medium containing computer-executable instructions provided in the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the echo cancellation method provided in any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute the echo cancellation method according to the embodiments of the present invention.
It should be noted that, in the embodiment of the echo cancellation device, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. An echo cancellation method for voice wakeup, comprising:
acquiring a voice signal to be output of a device to be awakened;
According to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened, performing echo cancellation on the initial awakening voice received by the microphone to generate awakening voice;
the acquiring of the to-be-output voice signal of the to-be-awakened device includes:
and acquiring a voice signal on a voice transmission path from a system module of the device to be awakened to the playing mechanism, and taking the voice signal as a voice signal to be output.
2. The method according to claim 1, wherein the voice signal to be output, output by the system module, is output to the playing mechanism through the power amplifier module, and correspondingly, the obtaining the voice output signal on the voice transmission path from the system module of the device to be woken up to the playing mechanism includes:
and acquiring a voice output signal output by a system module of the equipment to be awakened, or acquiring a voice output signal output by a power amplification module of the equipment to be awakened.
3. The method of claim 1, wherein performing echo cancellation on an initial wake-up voice received by a microphone to generate a wake-up voice according to the voice signal to be output and a pre-stored device frequency response curve of a device to be woken up, comprises:
Processing the voice signal to be output according to the equipment frequency response curve to obtain an estimated playing signal;
based on an adaptive filter, determining an echo signal according to the estimated playing signal and the initial voice wake-up signal;
subtracting the echo signal from the initial voice wake-up signal to generate a wake-up voice.
4. The method of claim 2, wherein the method of determining the frequency response curve of the device comprises:
acquiring a transmission/playing mechanism to which a voice signal to be output is about to enter and all transmission mechanisms through which the voice signal to be output needs to pass before entering the playing mechanism, and setting the gains of all the transmission mechanisms to be 1;
inputting sweep frequency sound with different frequencies and the same amplitude into a transmission/playing mechanism to be entered, and outputting the sweep frequency sound to the playing mechanism after the sweep frequency sound is processed by all the transmission mechanisms;
recording the frequency sweep sounds with different frequencies played by the player mechanism, and determining a test frequency response curve of the current equipment to be awakened according to the recorded frequency sweep sounds;
and acquiring a preset device frequency response curve of the current device to be awakened, and adjusting the preset device frequency response curve based on the test frequency response curve to enable the preset device frequency response curve to approach the test frequency response curve so as to generate a device frequency response curve.
5. An echo cancellation device configured in a voice wake-up apparatus, comprising:
the first acquisition module is used for acquiring a voice signal to be output of the equipment to be awakened; the awakening voice determining module is used for performing echo cancellation on the initial awakening voice received by the microphone according to the voice signal to be output and a pre-stored device frequency response curve of the device to be awakened so as to generate awakening voice;
the voice signal to be output is a voice output signal on a voice transmission path from the system module to the playing mechanism.
6. A storage medium containing computer-executable instructions, which when executed by a computer processor, operate to perform the echo cancellation method of any one of claims 1-4.
7. A voice wake-up method, comprising:
acquiring initial awakening voice of equipment to be awakened through a microphone;
determining a wake-up tone based on the initial wake-up tone and the echo cancellation method of any one of claims 1-4;
and determining a starting signal according to the awakening voice, and starting the equipment to be awakened through the starting signal.
8. A voice wake-up device, comprising:
The second voice acquisition module is used for acquiring an initial voice wake-up signal of the equipment to be woken up through the microphone;
an echo cancellation module for determining a wake-up voice according to the echo cancellation method of any one of claims 1 to 4 and an initial voice wake-up signal;
and the system module is used for determining a starting signal according to the awakening voice and starting the equipment to be awakened according to the starting signal.
9. The voice wake-up apparatus according to claim 8, wherein the echo cancellation module is connected to the system module via 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 CN109360562A (en) | 2019-02-19 |
| CN109360562B true 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) |
Families Citing this family (13)
| 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 | Echo cancellation system, method, device, equipment and storage medium |
| KR102402465B1 (en) * | 2019-06-10 | 2022-05-26 | 주식회사 케이티 | Device and method for preventing misperception of wake word |
| 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 |
| 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 |
| WO2021004067A1 (en) * | 2019-07-10 | 2021-01-14 | 海信视像科技股份有限公司 | Display device |
| CN110660407B (en) * | 2019-11-29 | 2020-03-17 | 恒玄科技(北京)有限公司 | Audio processing method and device |
| 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 |
| 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 |
| 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 |
| CN113038048B (en) * | 2021-03-02 | 2022-10-28 | 海信视像科技股份有限公司 | Far-field voice awakening method and display device |
| CN114974238A (en) * | 2022-05-14 | 2022-08-30 | 云知声智能科技股份有限公司 | Method and device for reducing resource consumption of intelligent voice equipment, electronic equipment and storage medium |
| CN115442711A (en) * | 2022-08-10 | 2022-12-06 | 星宸科技股份有限公司 | Audio processing device and method with echo cancellation mechanism |
Family Cites Families (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 |
| CN105187594B (en) * | 2015-07-28 | 2018-09-04 | 小米科技有限责任公司 | A kind of method and apparatus for eliminating echo |
| US10109294B1 (en) * | 2016-03-25 | 2018-10-23 | Amazon Technologies, Inc. | Adaptive echo cancellation |
| CN107452398B (en) * | 2017-08-09 | 2021-03-16 | 深圳创维数字技术有限公司 | Echo acquisition method, electronic device and computer readable storage 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 |
-
2018
- 2018-12-07 CN CN201811494159.8A patent/CN109360562B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109360562A (en) | 2019-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360562B (en) | Echo cancellation method, device, medium, and voice wake-up method and device | |
| CN111883156B (en) | Audio processing method and device, electronic equipment and storage medium | |
| US8498429B2 (en) | Acoustic correction apparatus, audio output apparatus, and acoustic correction method | |
| CN110956976B (en) | Echo cancellation method, device and equipment and readable storage medium | |
| CN110677717B (en) | Audio compensation method, smart television and storage medium | |
| WO2021103710A1 (en) | Live broadcast audio processing method and apparatus, and electronic device and storage medium | |
| CN111128167B (en) | Far-field voice awakening method and device, electronic product and storage medium | |
| CN111402910A (en) | Method and equipment for eliminating echo | |
| US20190221226A1 (en) | Electronic apparatus and echo cancellation method applied to electronic apparatus | |
| CN105991857A (en) | Method and device for adjusting reference signal | |
| CN114697782A (en) | Earphone wind noise identification method and device and earphone | |
| CN113517000A (en) | Echo cancellation test method, terminal and storage device | |
| CN112053669A (en) | Method, device, equipment and medium for eliminating human voice | |
| WO2014192235A1 (en) | Controller, control method, and program | |
| WO2018133247A1 (en) | Abnormal sound detection method and apparatus | |
| CN107750038B (en) | Volume adjusting method, device, equipment and storage medium | |
| CN110797040A (en) | Noise elimination method, intelligent sound box and storage medium | |
| US20110188641A1 (en) | Method and apparatus for removing noise signal from input signal | |
| CN108932953B (en) | Audio equalization function determination method, audio equalization method and equipment | |
| CN112118511A (en) | Earphone noise reduction method and device, earphone and computer readable storage medium | |
| CN112017649A (en) | Audio processing method and device, electronic equipment and readable storage medium | |
| TW201743197A (en) | Electronic device and method for dynamically adjusting output of headset | |
| CN111724808A (en) | Audio signal processing method, device, terminal and storage medium | |
| CN113613143B (en) | Audio processing method, device and storage medium suitable for mobile terminal | |
| CN115240700B (en) | Acoustic device and sound processing method thereof |
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 |