CN114143651A - Voice wake-up method and device for bone conduction headset - Google Patents
Voice wake-up method and device for bone conduction headset Download PDFInfo
- Publication number
- CN114143651A CN114143651A CN202111423091.6A CN202111423091A CN114143651A CN 114143651 A CN114143651 A CN 114143651A CN 202111423091 A CN202111423091 A CN 202111423091A CN 114143651 A CN114143651 A CN 114143651A
- Authority
- CN
- China
- Prior art keywords
- signal
- bone conduction
- voice
- conduction
- awakening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000000988 bone and bone Anatomy 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000001960 triggered effect Effects 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002618 waking effect Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 210000003027 ear inner Anatomy 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011038 discontinuous diafiltration by volume reduction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000002751 lymph Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000002985 organ of corti Anatomy 0.000 description 1
- 210000003625 skull Anatomy 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/1016—Earpieces of the intra-aural type
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2460/00—Details of hearing devices, i.e. of ear- or headphones covered by H04R1/10 or H04R5/033 but not provided for in any of their subgroups, or of hearing aids covered by H04R25/00 but not provided for in any of its subgroups
- H04R2460/13—Hearing devices using bone conduction transducers
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Details Of Audible-Bandwidth Transducers (AREA)
Abstract
The invention discloses a voice awakening method and a voice awakening device for a bone conduction headset, wherein the voice awakening method for the bone conduction headset comprises the following steps: acquiring a bone conduction signal and an air conduction voice signal; sending the bone conduction signal into a bone conduction signal VAD, and judging whether the bone conduction signal VAD is triggered; if the bone conduction signal VAD is triggered, inputting the air conduction voice signal into a voice awakening engine, and judging whether the air conduction voice signal contains awakening words or not; and if the bone conduction earphone contains the awakening word, awakening the bone conduction earphone. Through sending the bone conduction signal into bone conduction signal VAD, judge whether bone conduction signal VAD is triggered, if bone conduction signal VAD is triggered, import air conduction speech signal to voice awakening engine, judge whether contain the word of awakening up in the air conduction speech signal to can realize that only the person can awaken up the equipment, other people can't awaken up, very big promotion user's use experience.
Description
Technical Field
The invention belongs to the technical field of voice awakening, and particularly relates to a voice awakening method and device for a bone conduction headset.
Background
In the prior art, a low-power-consumption command word awakening technology of an earphone and a low-power-consumption command word awakening technology of the earphone are mainly used, and a user can control some operations of the earphone in a voice mode, such as volume increase, volume reduction, music playing, playing pause, previous operation, next operation, call answering, call hanging up and the like.
In the general earphone low-power consumption command word awakening technology, a user controls the earphone to operate through voice, and the voice can come from the user, other people or the environment. That is to say, after wearing the earphone, besides the user can control the earphone through voice, other people beside the user can also control the earphone, and meanwhile, if the environment has voice, the probability of misoperation (mistaken awakening) of the system is also very high, which seriously affects the actual experience of the user.
Disclosure of Invention
An embodiment of the present invention provides a voice wake-up method and apparatus for a bone conduction headset, so as to solve at least one of the above technical problems.
In a first aspect, an embodiment of the present invention provides a voice wake-up method for a bone conduction headset, including: acquiring a bone conduction signal and an air conduction voice signal; sending the bone conduction signal into a bone conduction signal VAD, and judging whether the bone conduction signal VAD is triggered; if the bone conduction signal VAD is triggered, inputting the air conduction voice signal into a voice awakening engine, and judging whether the air conduction voice signal contains awakening words or not; and if the bone conduction earphone contains the awakening word, awakening the bone conduction earphone.
In a second aspect, an embodiment of the present invention provides a voice wake-up device for a bone conduction headset, including: an acquisition program module configured to acquire a bone conduction signal and an air conduction voice signal; a judging program module configured to send the bone conduction signal to a bone conduction signal VAD and judge whether the bone conduction signal VAD is triggered; an input judgment program module configured to input the air conduction voice signal to a voice wake-up engine if the VAD is triggered, and judge whether the air conduction voice signal includes a wake-up word; and the awakening program module is configured to awaken the bone conduction earphone if the awakening program module contains an awakening word.
In a third aspect, a bone conduction headset is provided, comprising: a bone conduction signal processing unit, a speech signal processing unit and a processor capable of performing the method of any one of claims 1-7.
In a fourth aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the voice wake-up method for a bone conduction headset of any embodiment of the present invention.
In a fifth aspect, the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the steps of the voice wake-up method for a bone conduction headset according to any of the embodiments of the present invention.
According to the method and the device, the bone conduction signal is sent to the bone conduction signal VAD, whether the bone conduction signal VAD is triggered or not is judged, if the bone conduction signal VAD is triggered, the air conduction voice signal is input to the voice awakening engine, whether the air conduction voice signal contains awakening words or not is judged, and therefore the fact that only a user can awaken the equipment and other people cannot awaken the equipment can be achieved, and the use experience of the user is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description 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 a voice wake-up method for a bone conduction headset according to an embodiment of the present invention;
fig. 2 is a flowchart of another voice wake-up method for a bone conduction headset according to an embodiment of the present invention;
fig. 3 is a flowchart of a specific example of a voice wake-up method for a bone conduction headset according to an embodiment of the present invention;
fig. 4 is a block diagram of a voice wake-up apparatus for a bone conduction headset according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the 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.
Referring to fig. 1, a flowchart of an embodiment of a voice wake-up method for a bone conduction headset according to the present application is shown.
As shown in fig. 1, in step 101, acquiring a bone conduction signal and an air conduction voice signal;
in step 102, sending the bone conduction signal to a bone conduction signal VAD, and judging whether the bone conduction signal VAD is triggered;
in step 103, if the VAD is triggered, the air conduction speech signal is input to a speech wake-up engine, and it is determined whether the air conduction speech signal includes a wake-up word;
in step 104, if a wake-up word is included, the bone conduction headset is woken up.
In this embodiment, for step 101, the voice wake-up device for bone conduction earphone at least includes two sensors, one is a bone conduction signal sensor, and the other is an air conduction voice signal sensor, and the two sensors can simultaneously acquire a bone conduction signal and an air conduction voice signal, where bone conduction is a voice conduction mode, that is, a voice is converted into mechanical vibration with different frequencies, and a sound wave is transmitted through the skull, the bone labyrinth, the inner ear lymph, the spiral organ, and the auditory center of a human, and the air conduction voice signal is a general voice signal.
Then, in step 102, the voice wake-up device for the bone conduction headset sends the bone conduction signal to the bone conduction signal VAD to determine whether the bone conduction signal VAD is triggered, for example, the bone conduction signal VAD has an obvious voice signal only when the user speaks himself, so that the bone conduction VAD can accurately determine whether the user speaks himself.
Then, in step 103, if the bone conduction signal VAD is triggered, the air conduction voice signal is input to the voice wake-up engine, and it is determined whether the air conduction voice signal includes a wake-up word, for example, if the bone conduction signal VAD is triggered, it indicates that the user himself is speaking, and further, it is determined whether the user speaking includes a wake-up word or a command word, so that it is possible to accurately determine whether the user intends to wake up the bone conduction headset or to chat or sing.
Finally, in step 104, if the air conduction speech signal contains a wake-up word, the bone conduction headset is woken up.
According to the method, the bone conduction signal is sent to the bone conduction signal VAD, whether the bone conduction signal VAD is triggered or not is judged, if the bone conduction signal VAD is triggered, the air conduction voice signal is input to the voice awakening engine, whether the air conduction voice signal contains awakening words or not is judged, and therefore the fact that only a user can awaken the equipment and other people cannot awaken the equipment can be achieved, and the use experience of the user is greatly improved.
In the method according to the above embodiment, after the determining whether the VAD is triggered, the method further includes:
if the bone conduction signal VAD is not triggered, the bone conduction signal and the air conduction voice signal are acquired again, for example, the bone conduction signal VAD is not triggered, which indicates that the user is not speaking, and the acquisition of the bone conduction signal at the next moment is continued.
The method of the embodiment can reduce the false wake-up of the device and reduce the consumption of the device by judging whether the VAD is triggered or not.
In the method according to the above embodiment, after the determining whether the air conduction speech signal includes a wake up word, the method further includes:
if the air conduction voice signal does not contain the awakening word, the bone conduction signal and the air conduction voice signal are acquired again, for example, when the user chats with a friend, the voice of the user does not contain the awakening word, the intention of the user is not to awaken the bone conduction earphone, and the bone conduction signal and the air conduction voice signal at the next moment need to be acquired again.
According to the method, whether the air conduction voice signal contains the awakening word or not is judged, so that mistaken awakening of the equipment can be reduced, and consumption of the equipment is reduced.
In the method of the above embodiment, after waking up the bone conduction earphone if the wake-up word is included, the method further includes:
the air conduction voice signal is recognized and an operation corresponding to the air conduction voice signal is performed, for example, "cuvette, louder" or "cuvette, play next", the operation corresponding to the user's intention is performed after the user's intention is recognized.
Referring to fig. 2, a flowchart of another voice wake-up method for a bone conduction headset according to an embodiment of the present application is shown. The flowchart is mainly a flowchart of a step further defined by the flowchart after "determining whether the air conduction speech signal includes a wake-up word" if the VAD is triggered "in the flowchart of fig. 1.
As shown in fig. 2, in step 201, if a wake-up word is included, matching the voiceprint of the air conduction speech signal with a preset voiceprint, and determining whether the voiceprint of the air conduction speech signal is consistent with the preset voiceprint;
in step 202, if yes, the bone conduction headset is woken up.
In this embodiment, for step 201, if the air conduction voice signal includes the wakeup word, the voiceprint of the air conduction voice signal is matched with the preset voiceprint, and it is determined whether the voiceprint of the air conduction voice signal is consistent with the preset voiceprint, for example, there are other people around the user, the user just speaking triggers the bone conduction signal VAD, and the other people speak the wakeup word and the command word, so that the probability of mistakenly waking up the device is increased.
Then, in step 202, if the voiceprint of the air conduction speech signal is consistent with the preset voiceprint, the bone conduction headset is awakened.
The method of the embodiment can judge whether the user speaks himself or not by performing voiceprint confirmation on the air conduction voice signal, reduces false triggering of equipment, and greatly improves use experience of the user.
In the method according to the above embodiment, after the determining whether the voiceprint of the air conduction speech signal is consistent with the preset voiceprint, the method further includes:
and if the voiceprint of the air conduction voice signal is inconsistent with the preset voiceprint, judging that the bone conduction earphone does not meet the awakening condition, and acquiring the bone conduction signal and the air conduction voice signal again.
According to the method, the voiceprint confirmation is carried out on the air conduction voice signal, so that the false triggering of the equipment can be reduced, and the use experience of a user is greatly improved.
In any of the above methods, the bone conduction signal features and the air conduction signal features can be concatenated to train a unified model, while a unified wake-up engine that can detect bone conduction signals and determine whether it is a wake-up word is provided.
The method of the embodiment trains a unified model by splicing the bone conduction signal characteristic and the air conduction signal characteristic, thereby reducing the calculation power and the power consumption of the equipment.
It should be noted that the above method steps are not intended to limit the execution order of the steps, and in fact, some steps may be executed simultaneously or in the reverse order of the steps, which is not limited herein.
The following description is provided to enable those skilled in the art to better understand the present disclosure by describing some of the problems encountered by the inventors in implementing the present disclosure and by describing one particular embodiment of the finally identified solution.
The inventor finds that the defects in the prior art are mainly caused by the following reasons in the process of implementing the application:
the earphone has the defect that other people or environment can wake up or operate the earphone, and mainly the pure voice wake-up technology does not distinguish the source of voice, so that the equipment and the operating equipment can be woken up by other people or environment.
The inventor also finds that if the defects are solved, the scheme is generally adopted in a voiceprint mode, the voiceprint has strong uniqueness to an individual, and false awakening of others or the environment can be greatly reduced through the voiceprint plus awakening mode. However, the voiceprint needs to be well done, a large model is needed, the large model generally cannot run locally on the low-power-consumption headset, the local resources of the low-power-consumption headset and the voiceprint resources cannot run with great effort, and if the voiceprint is deployed in the cloud, the communication cost of the cloud + end is increased, and the operation delay is increased.
And the problem of operation of other people of the low-power-consumption earphone is solved by combining the bone conduction voice signal with the general voice signal of the earphone. The bone conduction signal characteristics and the common earphone voice signal characteristics and the low-power consumption voice wake-up algorithm need to be deeply known, so that the mode of combining the bone conduction signal and the common voice signal is possible to be thought, the problem of false wake-up of other people is solved, and the problem is difficult to be thought by other people.
The scheme of the application is mainly designed and optimized from the following aspects:
a bone conduction sensor is added on a common low-power-consumption earphone, and has a remarkable characteristic, after a user carries the earphone, only when the user speaks himself, bone conduction signals can be generated, and when the user does not speak, the bone conduction signals are not generated. Bone conduction signals are strongly correlated with the user speaking himself. Therefore, the bone conduction signal is combined with the general voice wake-up signal, so that the purposes that the user wakes up the equipment and other people cannot wake up the equipment can be achieved.
Referring to fig. 3, a flowchart of a specific example of a voice wake-up method for a bone conduction headset according to an embodiment of the present invention is shown.
As shown in fig. 3, signal acquisition:
the earphone at least comprises two sensors, wherein one sensor is a bone conduction signal sensor, the other sensor is an air conduction voice signal sensor, and the system can simultaneously acquire signals of the two sensors.
Bone conduction VAD engine:
the bone conduction signal is input to a trained bone conduction signal VAD engine, VAD refers to voice endpoint detection, and the VAD engine can judge whether a voice signal is input or not. Since the bone conduction signal has an obvious speech signal only when the user speaks himself, the bone conduction VAD engine can judge whether the user speaks himself.
If the bone conduction VAD is not triggered, the fact that the user does not speak at the moment is indicated, and the system continues to input the bone conduction signal at the next moment and judges.
If the bone conduction VAD triggers, the system inputs the air conduction signal into the voice awakening engine to indicate that the user speaks at the moment
A voice wake-up engine:
and triggering the bone conduction VAD, inputting the air conduction signal into a voice awakening engine, and judging which control command word preset by the system is awakened or not awakened by the voice awakening engine.
And if the voice awakening engine judges that the control command words preset by the system are not awakened, the system collects signals continuously collected at the next moment.
And if the voice awakening engine judges that a certain control command word preset by the system is awakened, the system performs corresponding operation.
The corresponding operation is as follows:
and if the voice awakening engine judges that a certain control command word preset by the system is awakened, the system performs corresponding operation. E.g., the command word "increase volume" wakes up, the system will perform an operation to increase volume. After the operation is performed, the system will resume acquiring signals.
Beta version formed by the inventor in the process of implementing the invention:
and (4) awakening the scheme of + voiceprint, uploading the voice to the cloud after the voice awakening is successful, confirming the voiceprint, and judging whether the sound source is from the registrant or not. The disadvantages are as follows: networking is required (voiceprints need to be run in the cloud); the advantages are that: the scheme is easy to realize.
And splicing the bone conduction signals with an air conduction signal training model, and directly training the model. The disadvantages are as follows: the existing method is difficult to train due to the lack of labeled bone conduction data. The advantages are that: the calculation is smaller than the current scheme of the bone conduction signal VAD + air conduction awakening. This scheme is tried later on.
The inventor finds that deeper effects are achieved in the process of implementing the invention:
this scheme has integrateed bone conduction microphone signal and air conduction microphone signal, has realized that only oneself can awaken up, the function that other people can't awaken up, very big promotion user experience.
Referring to fig. 4, a block diagram of a voice wake-up apparatus for a bone conduction headset according to an embodiment of the present invention is shown.
As shown in fig. 4, the voice wake-up apparatus 400 for bone conduction headset includes an acquisition program module 410, a determination program module 420, an input determination program module 430, and a wake-up program module 440.
Wherein, the obtaining program module 410 is configured to obtain the bone conduction signal and the air conduction voice signal; a determining program module 420 configured to send the bone conduction signal to a bone conduction signal VAD, and determine whether the bone conduction signal VAD is triggered; an input determining program module 430, configured to input the air conduction voice signal to a voice wake-up engine if the VAD is triggered, and determine whether the air conduction voice signal includes a wake-up word; a wake-up program module 440 configured to wake up the bone conduction headset if the wake-up word is included.
It should be understood that the modules depicted in fig. 4 correspond to various steps in the methods described with reference to fig. 1 and 2. Thus, the operations and features described above for the method and the corresponding technical effects are also applicable to the modules in fig. 4, and are not described again here.
It should be noted that the modules in the embodiments of the present disclosure are not intended to limit the aspects of the present disclosure, and for example, the acquisition program module may be described as a module for acquiring a bone conduction signal and an air conduction voice signal. In addition, the related functional modules may also be implemented by a hardware processor, for example, the acquiring program module may also be implemented by a processor, which is not described herein again.
In other embodiments, the present invention also provides a bone conduction headset comprising: a bone conduction signal processing unit, a speech signal processing unit and a processor capable of performing the method of any one of claims 1-7.
In other embodiments, an embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores computer-executable instructions, where the computer-executable instructions may perform a voice wake-up method for a bone conduction headset in any of the above method embodiments;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
acquiring a bone conduction signal and an air conduction voice signal;
sending the bone conduction signal into a bone conduction signal VAD, and judging whether the bone conduction signal VAD is triggered;
if the bone conduction signal VAD is triggered, inputting the air conduction voice signal into a voice awakening engine, and judging whether the air conduction voice signal contains awakening words or not;
and if the bone conduction earphone contains the awakening word, awakening the bone conduction earphone.
The non-volatile computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a voice wake-up apparatus for a bone conduction headset, and the like. Further, the non-volatile computer-readable storage medium may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the non-transitory computer readable storage medium optionally includes memory remotely located from the processor, which may be connected over a network to a voice wake-up unit for a bone conduction headset. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Embodiments of the present invention also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform any of the above voice wake-up methods for a bone conduction headset.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 5, the electronic device includes: one or more processors 510 and memory 520, with one processor 510 being an example in fig. 5. The apparatus for a voice wake-up method of a bone conduction headset may further include: an input device 530 and an output device 540. The processor 510, the memory 520, the input device 530, and the output device 540 may be connected by a bus or other means, and the bus connection is exemplified in fig. 5. The memory 520 is a non-volatile computer-readable storage medium as described above. The processor 510 executes various functional applications of the server and data processing by executing the nonvolatile software programs, instructions and modules stored in the memory 520, namely, implements the voice wake-up method for the bone conduction headset of the above-described method embodiments. The input device 530 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the communication compensation device. The output device 540 may include a display device such as a display screen.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
As an embodiment, the electronic device is applied to a voice wake-up apparatus for a bone conduction headset, and is used for a client, and includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
acquiring a bone conduction signal and an air conduction voice signal;
sending the bone conduction signal into a bone conduction signal VAD, and judging whether the bone conduction signal VAD is triggered;
if the bone conduction signal VAD is triggered, inputting the air conduction voice signal into a voice awakening engine, and judging whether the air conduction voice signal contains awakening words or not;
and if the bone conduction earphone contains the awakening word, awakening the bone conduction earphone.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A voice wake-up method for a bone conduction headset, comprising:
acquiring a bone conduction signal and an air conduction voice signal;
sending the bone conduction signal into a bone conduction signal VAD, and judging whether the bone conduction signal VAD is triggered;
if the bone conduction signal VAD is triggered, inputting the air conduction voice signal into a voice awakening engine, and judging whether the air conduction voice signal contains awakening words or not;
and if the bone conduction earphone contains the awakening word, awakening the bone conduction earphone.
2. The method according to claim 1, wherein after the determining whether the VAD is triggered, the method further comprises:
if the bone conduction signal VAD is not triggered, the bone conduction signal and the air conduction voice signal are acquired again.
3. The method of claim 1, wherein after the determining whether a wake word is included in the air conduction speech signal, the method further comprises:
and if the air conduction voice signal does not contain a wake-up word, reacquiring the bone conduction signal and the air conduction voice signal.
4. The method of claim 1, wherein after waking up the bone conduction headset if the wake-up word is included, the method further comprises:
and recognizing the air conduction voice signal and executing the operation corresponding to the air conduction voice signal.
5. The method according to claim 1, wherein after determining whether the air conduction speech signal includes a wake up word if the VAD is triggered, the method further comprises:
if the voice guide voice signal contains the awakening word, matching the voiceprint of the air guide voice signal with a preset voiceprint, and judging whether the voiceprint of the air guide voice signal is consistent with the preset voiceprint or not;
and if the signals are consistent, awakening the bone conduction earphone.
6. The method of claim 4, wherein after the determining whether the voiceprint of the air conduction speech signal is consistent with a preset voiceprint, the method further comprises:
and if the voiceprint of the air conduction voice signal is inconsistent with the preset voiceprint, judging that the bone conduction earphone does not meet the awakening condition, and reacquiring the bone conduction signal and the air conduction voice signal.
7. The method according to any one of claims 1-6, wherein the bone conduction signal features and the air conduction signal features are capable of being stitched to train a unified model, while a unified wake-up engine capable of detecting bone conduction signals and determining whether it is a wake-up word.
8. A voice wake-up apparatus for a bone conduction headset, comprising:
an acquisition program module configured to acquire a bone conduction signal and an air conduction voice signal;
a judging program module configured to send the bone conduction signal to a bone conduction signal VAD and judge whether the bone conduction signal VAD is triggered;
an input judgment program module configured to input the air conduction voice signal to a voice wake-up engine if the VAD is triggered, and judge whether the air conduction voice signal includes a wake-up word;
and the awakening program module is configured to awaken the bone conduction earphone if the awakening program module contains an awakening word.
9. A bone conduction headset, comprising:
a bone conduction signal processing unit, a speech signal processing unit and a processor capable of performing the method of any one of claims 1-7.
10. A non-volatile storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111423091.6A CN114143651A (en) | 2021-11-26 | 2021-11-26 | Voice wake-up method and device for bone conduction headset |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111423091.6A CN114143651A (en) | 2021-11-26 | 2021-11-26 | Voice wake-up method and device for bone conduction headset |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114143651A true CN114143651A (en) | 2022-03-04 |
Family
ID=80388384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111423091.6A Pending CN114143651A (en) | 2021-11-26 | 2021-11-26 | Voice wake-up method and device for bone conduction headset |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114143651A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106714023A (en) * | 2016-12-27 | 2017-05-24 | 广东小天才科技有限公司 | Voice wake-up method and system based on bone conduction earphone, and bone conduction earphone |
| US20190066671A1 (en) * | 2017-08-22 | 2019-02-28 | Baidu Online Network Technology (Beijing) Co., Ltd. | Far-field speech awaking method, device and terminal device |
| CN111028838A (en) * | 2019-12-17 | 2020-04-17 | 苏州思必驰信息科技有限公司 | Voice wake-up method, device and computer readable storage medium |
| CN111432303A (en) * | 2020-03-19 | 2020-07-17 | 清华大学 | Monaural headset, intelligent electronic device, method, and computer-readable medium |
| CN112951243A (en) * | 2021-02-07 | 2021-06-11 | 深圳市汇顶科技股份有限公司 | Voice awakening method, device, chip, electronic equipment and storage medium |
-
2021
- 2021-11-26 CN CN202111423091.6A patent/CN114143651A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106714023A (en) * | 2016-12-27 | 2017-05-24 | 广东小天才科技有限公司 | Voice wake-up method and system based on bone conduction earphone, and bone conduction earphone |
| US20190066671A1 (en) * | 2017-08-22 | 2019-02-28 | Baidu Online Network Technology (Beijing) Co., Ltd. | Far-field speech awaking method, device and terminal device |
| CN111028838A (en) * | 2019-12-17 | 2020-04-17 | 苏州思必驰信息科技有限公司 | Voice wake-up method, device and computer readable storage medium |
| CN111432303A (en) * | 2020-03-19 | 2020-07-17 | 清华大学 | Monaural headset, intelligent electronic device, method, and computer-readable medium |
| CN112951243A (en) * | 2021-02-07 | 2021-06-11 | 深圳市汇顶科技股份有限公司 | Voice awakening method, device, chip, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108701458B (en) | Speech recognition | |
| EP3614383A1 (en) | Audio data processing method and apparatus, and storage medium | |
| CN110890093A (en) | Intelligent device awakening method and device based on artificial intelligence | |
| CN105575395A (en) | Voice wake-up method and apparatus, terminal, and processing method thereof | |
| CN110910887B (en) | Voice wake-up method and device | |
| CN110570840B (en) | Intelligent device awakening method and device based on artificial intelligence | |
| CN109844857B (en) | Portable audio device with voice capability | |
| JP2016526178A (en) | Method and apparatus for detecting target keywords | |
| KR20160005050A (en) | Adaptive audio frame processing for keyword detection | |
| CN103269405A (en) | Method and device for hinting friendlily | |
| CN110263131B (en) | Reply information generation method, device and storage medium | |
| WO2017151406A1 (en) | Conversational software agent | |
| CN107731241B (en) | Method, apparatus and storage medium for processing audio signal | |
| CN109885162B (en) | Vibration method and mobile terminal | |
| EP4191579A1 (en) | Electronic device and speech recognition method therefor, and medium | |
| CN111755002B (en) | Speech recognition device, electronic apparatus, and speech recognition method | |
| CN107146605B (en) | Voice recognition method and device and electronic equipment | |
| CN111522592A (en) | Intelligent terminal awakening method and device based on artificial intelligence | |
| WO2020057624A1 (en) | Voice recognition method and apparatus | |
| CN110830368A (en) | Instant messaging message sending method and electronic equipment | |
| CN115150501A (en) | Voice interaction method and electronic equipment | |
| CN112150583A (en) | Spoken language pronunciation evaluation method and terminal equipment | |
| WO2023006033A1 (en) | Speech interaction method, electronic device, and medium | |
| CN114143651A (en) | Voice wake-up method and device for bone conduction headset | |
| CN117099099A (en) | Device finder using voice authentication |
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 |