CN114257684A - Voice processing method, system and device and electronic equipment - Google Patents
Voice processing method, system and device and electronic equipment Download PDFInfo
- Publication number
- CN114257684A CN114257684A CN202111555026.9A CN202111555026A CN114257684A CN 114257684 A CN114257684 A CN 114257684A CN 202111555026 A CN202111555026 A CN 202111555026A CN 114257684 A CN114257684 A CN 114257684A
- Authority
- CN
- China
- Prior art keywords
- preset
- current
- voice
- strategy
- placement state
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims description 30
- 230000005484 gravity Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 230000003321 amplification Effects 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Environmental & Geological Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a voice processing method, a system, a device and electronic equipment, wherein in the scheme, before the received voice is identified, the placement state of the electronic equipment is determined, then different strategies are set according to different placement states of the electronic equipment, and then different processing is carried out on the voice received by the electronic equipment based on the strategies, so that the processed voice reaches the preset standard. In the application, the factor of the state of the electronic equipment is taken into consideration, and the received voice is processed differently according to different placing states, so that the received voice all reaches the preset standard, the problem that the voice recognition is inaccurate due to different placing states of the electronic equipment can be avoided, and the accuracy of the electronic equipment for the voice recognition are improved.
Description
Technical Field
The present invention relates to the field of intelligent devices, and in particular, to a method, a system, an apparatus, and an electronic device for processing speech.
Background
Along with the improvement of daily life quality, electronic equipment is gradually popularized, the intellectualization of electronic equipment is also gradually improved, and a plurality of electronic equipment have a voice recognition function. The core of the voice recognition function lies in the accuracy and the correct rate of voice recognition, and how the electronic devices are placed (for example, horizontally placed or vertically placed or buckled) is related to the accuracy and the correct rate of voice recognition, specifically, when the electronic devices are placed in different states, the received definition degrees of the same voice are different, and for some placement states which are not beneficial to receiving voice, the definition of the voice received by the electronic devices may be poor, and the accuracy and the correct rate of voice recognition may be influenced. Therefore, it is an urgent need to solve the above-mentioned problems by those skilled in the art to provide a speech processing method to improve the accuracy and precision of speech recognition of electronic devices.
Disclosure of Invention
The invention aims to provide a voice processing method, a system, a device and electronic equipment, which take the prevention state of the electronic equipment into account, carry out different processing on received voice aiming at different placing states so as to ensure that the received voice reaches the preset standard, can avoid inaccurate voice recognition caused by different placing states of the electronic equipment, and improve the accuracy and the correct rate of the electronic equipment for the voice recognition.
In order to solve the above technical problem, the present invention provides a speech processing method, including:
determining a current placement state of the electronic device;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy;
and processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard.
Preferably, a microphone is arranged in the electronic equipment;
after determining the current placement state of the electronic device, the method further comprises:
determining the current direction of the microphone according to the relative position between the microphone and the electronic equipment and the current placement state;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy, wherein the method comprises the following steps:
and determining a current strategy according to the current direction and the corresponding relation between the preset direction and the preset strategy.
Preferably, the preset strategy is a preset compensation strategy;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy, wherein the method comprises the following steps:
determining a current compensation strategy according to the current placement state and the corresponding relation between the preset placement state and the preset compensation strategy;
processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard, wherein the processing comprises the following steps:
and compensating the voice received by the electronic equipment by using the current compensation strategy so as to enable the compensated voice to reach a preset standard.
Preferably, the current compensation strategy is a corresponding relation between a preset frequency band and a preset compensation amount;
compensating the voice received by the electronic equipment by using the current compensation strategy so as to enable the compensated voice to reach a preset standard, wherein the method comprises the following steps:
determining each frequency segment of the voice received by the electronic equipment;
determining compensation quantity corresponding to each frequency segment of the voice according to the corresponding relation between the preset frequency segment and the preset compensation quantity;
and compensating the corresponding frequency band according to the determined compensation amount so as to enable the compensated voice to reach a preset standard.
Preferably, a gravity sensor is arranged in the electronic equipment;
determining a current placement state of the electronic device, comprising:
and determining the current placement state of the electronic equipment according to the current output parameters of the gravity sensor.
Preferably, after determining the current placement state of the electronic device, the method further includes:
judging whether the current placement state is a preset state or not;
if yes, directly identifying the received voice;
if not, the step of determining the current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy is carried out.
Preferably, before determining the current placement state of the electronic device, the method further includes:
judging whether a preset voice is recognized or not, wherein the preset voice comprises preset words or preset characters;
and if so, entering a step of determining the current placement state of the electronic equipment.
In order to solve the above technical problem, the present invention further provides a speech recognition system, including:
a state determination unit for determining a current placement state of the electronic device;
the strategy determining unit is used for determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy;
and the voice processing unit is used for processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard.
In order to solve the above technical problem, the present invention further provides a speech recognition apparatus, including:
a memory for executing a computer program;
a processor for implementing the steps of the speech processing method described above when executing the computer program.
In order to solve the technical problem, the invention also provides electronic equipment comprising the voice recognition device.
The application provides a voice processing method, in the scheme, before received voice is recognized, the placing state of electronic equipment is determined, different strategies are set according to different placing states of the electronic equipment, then different processing is carried out on the voice received by the electronic equipment based on the strategies, and the processed voice reaches a preset standard. In the application, the factor of the state of the electronic equipment is taken into consideration, and the received voice is processed differently according to different placing states, so that the received voice all reaches the preset standard, the problem that the voice recognition is inaccurate due to different placing states of the electronic equipment can be avoided, and the accuracy of the electronic equipment for the voice recognition are improved.
The application also provides a voice processing system, a voice processing device and electronic equipment, and the voice processing system, the voice processing device and the electronic equipment have the same beneficial effects as the voice processing method described above.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed in the prior art and the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of a speech processing method according to the present invention;
FIG. 2 is a schematic diagram of an electronic device according to the present invention in a vertical position;
fig. 3 is a schematic view of an electronic device according to the present invention disposed horizontally and upwardly;
fig. 4 is a schematic view of an electronic device according to the present invention being locked horizontally;
FIG. 5 is a graph of FR curves for three placement states provided by the present invention;
FIG. 6 is a block diagram of a speech recognition system according to the present invention;
fig. 7 is a block diagram of a speech recognition apparatus according to the present invention.
Detailed Description
The core of the invention is to provide a voice processing method, a system, a device and electronic equipment, which take the prevention state of the electronic equipment into account, carry out different processing on the received voice aiming at different placing states, so that the received voice reaches the preset standard, can avoid the inaccurate voice recognition caused by the different placing states of the electronic equipment, and improve the accuracy and the correct rate of the voice recognition by the electronic equipment.
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, fig. 1 is a schematic flow chart of a speech processing method according to the present invention, the method including:
s11: determining a current placement state of the electronic device;
for solving the influence of the placing state of the electronic equipment on the voice recognition, the design idea of the application is as follows: aiming at different placement states of the electronic equipment, different processing modes are set for the received voice so that the received voice can reach a standard based on the corresponding processing modes, and therefore a voice recognition system in the electronic equipment can recognize the received voice based on the standard voice, and the electronic equipment acts based on the recognized voice.
Based on this, the present application needs to first acquire the current placement state of the electronic device at the beginning of the scheme, so as to set different processing modes for the voice based on the current placement state.
It should be noted that, the electronic device in the present application may be but is not limited to an intelligent remote controller, and the placement state of the electronic device may be but is not limited to three states including a vertical placement state, a horizontal upward placement state, a horizontal downward placement state, and the like, and may also include other placement states, which is not limited herein.
Of course, the electronic device is not limited to the smart remote controller, and the above is only a single embodiment listed in the present application, and other implementations are also possible.
S12: determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy;
specifically, the corresponding relationship between the preset placement state and the preset policy is pre-established, and the step of establishing the corresponding relationship may be performed only once at the beginning or may be performed once when the user needs to adjust the corresponding relationship, and does not need to be repeatedly performed.
After the current placement state of the electronic equipment is determined, a corresponding preset strategy is determined according to the relation, so that the received voice is processed based on the preset strategy. The preset strategy may be different processing modes for the voice, such as different filtering modes, filtering degrees, amplification factors, amplification strategies, and the like corresponding to different placement states.
S13: and processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard.
After the current strategy corresponding to the current placement state is determined, the determined current strategy is used for processing the voice received by the electronic equipment, so that the processed voice reaches a preset standard. The processing method may include, but is not limited to, amplification processing, filtering processing, or other forms of speech processing, which is determined according to the actual situation.
Therefore, in the scheme of the application, the factor of the state prevention of the electronic equipment is taken into consideration, the received voice is processed differently according to different placing states, so that the received voice reaches the preset standard, the problem that the voice recognition is inaccurate due to different placing states of the electronic equipment can be avoided, the accuracy and the correctness of the voice recognition by the electronic equipment are improved, and the voice recognition effect is improved.
On the basis of the above-described embodiment:
as a preferred embodiment, a microphone is provided in the electronic device;
after determining the current placement state of the electronic device, the method further comprises:
determining the current direction of the microphone according to the relative position between the microphone and the electronic equipment and the current placement state;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy, wherein the method comprises the following steps:
and determining the current strategy according to the current direction and the corresponding relation between the preset direction and the preset strategy.
Specifically, the main reasons for considering that different placement states of the electronic device may affect the effect of the voice recognition are: when the electronic device is placed in different states, the microphones in the electronic device are oriented differently, and the received voices are also different in intelligibility. For example, when the electronic device is placed on a desktop in a buckled manner, the microphone is oriented downward, a gap exists between the microphone and the desktop, and when the microphone receives voice, sound waves may vibrate in the gap between the microphone and the desktop, thereby affecting the accuracy and precision of voice recognition.
Based on this, the corresponding relationship in the present application is specifically a corresponding relationship between a preset direction and a preset policy, after the current placement state of the electronic device is determined, the current direction of the microphone is determined according to the relative positions of the electronic device and the microphone and the current placement state of the electronic device, and then the current policy is specifically determined based on the current direction of the microphone, so as to perform adaptive processing on the voice received by the electronic device.
By the mode in the embodiment, different strategies can be determined for the received voice according to different orientations of the microphone, so that different processing is performed on the voice to enable the voice to reach the preset standard.
As a preferred embodiment, the preset strategy is a preset compensation strategy;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy, wherein the method comprises the following steps:
determining a current compensation strategy according to the current placement state and the corresponding relation between the preset placement state and the preset compensation strategy;
the method for processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach the preset standard comprises the following steps:
and compensating the voice received by the electronic equipment by using the current compensation strategy so as to enable the compensated voice to reach a preset standard.
Specifically, considering that the clarity of the obtained voices is different when the placement states of the electronic devices are different, for example, please refer to fig. 2, fig. 3, fig. 4, and fig. 5, fig. 2 is a schematic diagram of a vertical placement of an electronic device provided by the present invention, fig. 3 is a schematic diagram of an upward horizontal placement of an electronic device provided by the present invention, fig. 4 is a schematic diagram of an upward horizontal placement of an electronic device provided by the present invention, and fig. 5 is an FR curve graph in three placement states provided by the present invention. It is assumed that the surface of the microphone receiving the speech is parallel to the front of the electronic device. It is assumed that the voice received by the electronic device suspended on the wall is in a normal state, and as can be seen from fig. 5, the sound intensity received by the electronic device in the state different from the state of being suspended on the wall and being placed is lower than the sound intensity received in the normal state. That is, the received sound intensity is weak.
Therefore, the preset strategy in the present application is a preset compensation strategy, and mainly compensates voices received in different placing states to different degrees, specifically but not limited to, compensates for volume so that the voices reach a preset standard.
It should be noted that the preset criterion may be, but is not limited to, a certain range around the curve a in fig. 5. In addition, the compensation strategy may be, but is not limited to, gain compensation, for example, if the placement state corresponding to the curve a is taken as a normal state, then the gain is a1 in the normal state; in the placed state corresponding to the curve B, the corresponding gain is B1; the gain corresponding to the curve C in the placed state is C1, where C1 is greater than B1 and greater than a1, the gain compensation corresponding to the curve B is Δ B — B1-a1, and the gain compensation corresponding to the curve C is Δ C — C1-a 1. Of course, filtering compensation and the like are also possible, and the application is not limited herein.
To sum up, through the mode in this application, can carry out the compensation of different degrees to the pronunciation that electronic equipment under the different states of placing received to make it reach preset standard, improve speech recognition's the degree of accuracy and correct rate.
As a preferred embodiment, the current compensation strategy is a corresponding relationship between a preset frequency band and a preset compensation amount;
using the current compensation strategy to compensate the voice received by the electronic device, so that the compensated voice reaches a preset standard, including:
determining each frequency segment of the voice received by the electronic equipment;
determining compensation amount corresponding to each frequency segment of the voice according to the corresponding relation between the preset frequency segment and the preset compensation amount;
and compensating the corresponding frequency band according to the determined compensation amount so as to enable the compensated voice to reach a preset standard.
Specifically, as can be seen from fig. 5, in different placement states of the electronic device, the intensities of the voices received by the microphone are different, and the difference between the voice intensity of each frequency band and the corresponding voice intensity in the normal state is different, that is, the different placement states have different influences on different frequency bands of the voices.
In order to improve the speech intelligibility as much as possible, in this embodiment, when compensating the speech, it is required to determine each frequency segment of the speech received by the electronic device, then determine a corresponding compensation amount for each frequency segment, and compensate each frequency segment respectively, so that the compensated speech reaches a preset standard.
For example, as can be seen from fig. 5, since the influence of the sound in the high frequency band is large and the influence of the sound in the low frequency band is small, when compensating the received speech, the sound in the high frequency band is processed with a small compensation amount and the sound in the low frequency band is processed with a small compensation amount.
In summary, in the embodiment, different frequency segments of the speech are considered respectively, and different compensations are performed on the different frequency segments, so that the processed speech reaches a preset standard, thereby avoiding the occurrence of a frequency drop phenomenon and further improving the accuracy of speech recognition.
As a preferred embodiment, a gravity sensor is arranged in the electronic device;
determining a current placement state of the electronic device, comprising:
and determining the current placement state of the electronic equipment through the current output parameters of the gravity sensor.
Specifically, the electronic device is provided with a gravity sensor, and the placement state of the electronic device may be determined by acquiring an output parameter of the gravity sensor, but is not limited to this.
Wherein, gravity sensor can perceive the change of acceleration force, and acceleration force is exactly as the object in the acceleration process on the object the power, for example rock, fall, rise, various removal changes such as decline can both be turned into the signal of telecommunication output by gravity sensor, then through the computational analysis back to the signal of telecommunication, just can confirm electronic equipment's current state of placing.
In the embodiment, the function of determining the placement state of the electronic equipment can be realized, and the realization mode is simple and reliable.
As a preferred embodiment, after determining the current placement state of the electronic device, the method further includes:
judging whether the current placement state is a preset state or not;
if yes, directly identifying the received voice;
if not, the step of determining the current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy is carried out.
As can be seen from fig. 5, assuming that the curve a is a default normal state, after determining the current placement state of the electronic device, it is further determined whether the current placement state is the default normal state, that is, a preset state, and if so, the voice is directly recognized without any processing. Otherwise, entering the step of determining the current strategy.
Through the method and the device, the steps of identifying the voice can be simplified, and the power consumption of the electronic equipment is reduced.
As a preferred embodiment, before determining the current placement state of the electronic device, the method further includes:
judging whether a preset voice is recognized or not, wherein the preset voice comprises preset words or preset characters;
and if so, entering a step of determining the current placement state of the electronic equipment.
In addition, the step of determining the current placement state of the electronic device is only entered when speech recognition is performed. Otherwise, this step is not entered. The method for judging whether the voice recognition is performed is as follows: and judging whether the preset voice is recognized or not, if so, judging that the voice recognition time is the voice recognition time, and if not, judging that the voice recognition time is not the voice recognition time.
The preset speech may be, but not limited to, a preset word or a preset word, and specifically, an implementation manner of the preset word or the preset word is not limited herein.
Therefore, the method does not need to repeatedly execute the step of determining the current placement state of the electronic equipment, and therefore power consumption of the electronic equipment can be reduced.
Referring to fig. 6, fig. 6 is a block diagram of a speech recognition system provided in the present invention, the system includes:
a state determination unit 61 for determining a current placement state of the electronic device;
a policy determining unit 62, configured to determine a current policy according to the current placement state and a preset placement state-preset policy correspondence;
and the voice processing unit 63 is configured to process the voice received by the electronic device using the current policy, so that the processed voice meets a preset standard.
For the introduction of the speech recognition system, please refer to the above embodiments, which are not described herein again.
Referring to fig. 7, fig. 7 is a block diagram of a speech recognition apparatus provided in the present invention, the apparatus includes:
a memory 71 for executing a computer program;
the processor 72 is configured to implement the steps of the above-described speech processing method when executing the computer program.
For the introduction of the voice recognition apparatus, please refer to the above embodiments, which are not described herein again.
An electronic device comprises the voice recognition device.
For solving the above technical problem, the present application further provides an electronic device, where the electronic device may be, but not limited to, an intelligent remote controller, and may also be other intelligent devices with a voice recognition function, and for the introduction of the electronic device, please refer to the above embodiments, which is not described herein again.
It is to be noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of speech processing, comprising:
determining a current placement state of the electronic device;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy;
and processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard.
2. The speech processing method of claim 1, wherein a microphone is provided in the electronic device;
after determining the current placement state of the electronic device, the method further comprises:
determining the current direction of the microphone according to the relative position between the microphone and the electronic equipment and the current placement state;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy, wherein the method comprises the following steps:
and determining a current strategy according to the current direction and the corresponding relation between the preset direction and the preset strategy.
3. The speech processing method according to claim 1, wherein the predetermined strategy is a predetermined compensation strategy;
determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy, wherein the method comprises the following steps:
determining a current compensation strategy according to the current placement state and the corresponding relation between the preset placement state and the preset compensation strategy;
processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard, wherein the processing comprises the following steps:
and compensating the voice received by the electronic equipment by using the current compensation strategy so as to enable the compensated voice to reach a preset standard.
4. The speech processing method according to claim 3, wherein the current compensation strategy is a preset frequency segment-preset compensation amount correspondence;
compensating the voice received by the electronic equipment by using the current compensation strategy so as to enable the compensated voice to reach a preset standard, wherein the method comprises the following steps:
determining each frequency segment of the voice received by the electronic equipment;
determining compensation quantity corresponding to each frequency segment of the voice according to the corresponding relation between the preset frequency segment and the preset compensation quantity;
and compensating the corresponding frequency band according to the determined compensation amount so as to enable the compensated voice to reach a preset standard.
5. The speech processing method according to claim 1, wherein a gravity sensor is provided in the electronic device;
determining a current placement state of the electronic device, comprising:
and determining the current placement state of the electronic equipment according to the current output parameters of the gravity sensor.
6. The speech processing method of any one of claims 1-5, wherein after determining the current placement state of the electronic device, further comprising:
judging whether the current placement state is a preset state or not;
if yes, directly identifying the received voice;
if not, the step of determining the current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy is carried out.
7. The speech processing method of any one of claims 1-5, wherein prior to determining the current placement state of the electronic device, further comprising:
judging whether a preset voice is recognized or not, wherein the preset voice comprises preset words or preset characters;
and if so, entering a step of determining the current placement state of the electronic equipment.
8. A speech recognition system, comprising:
a state determination unit for determining a current placement state of the electronic device;
the strategy determining unit is used for determining a current strategy according to the current placement state and the corresponding relation between the preset placement state and the preset strategy;
and the voice processing unit is used for processing the voice received by the electronic equipment by using the current strategy so as to enable the processed voice to reach a preset standard.
9. A speech recognition apparatus, comprising:
a memory for executing a computer program;
a processor for implementing the steps of the speech processing method according to any of claims 1-7 when executing the computer program.
10. An electronic device, characterized in that it comprises a speech recognition arrangement according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111555026.9A CN114257684A (en) | 2021-12-17 | 2021-12-17 | Voice processing method, system and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111555026.9A CN114257684A (en) | 2021-12-17 | 2021-12-17 | Voice processing method, system and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114257684A true CN114257684A (en) | 2022-03-29 |
Family
ID=80795690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111555026.9A Pending CN114257684A (en) | 2021-12-17 | 2021-12-17 | Voice processing method, system and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114257684A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172421A1 (en) * | 2011-08-10 | 2014-06-19 | Goertek Inc. | Speech enhancing method, device for communication earphone and noise reducing communication earphone |
| CN109272989A (en) * | 2018-08-29 | 2019-01-25 | 北京京东尚科信息技术有限公司 | Voice awakening method, device and computer readable storage medium |
| CN110164446A (en) * | 2018-06-28 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Voice signal recognition methods and device, computer equipment and electronic equipment |
| CN112992169A (en) * | 2019-12-12 | 2021-06-18 | 华为技术有限公司 | Voice signal acquisition method and device, electronic equipment and storage medium |
| WO2021180085A1 (en) * | 2020-03-11 | 2021-09-16 | 华为技术有限公司 | Sound pickup method and apparatus and electronic device |
-
2021
- 2021-12-17 CN CN202111555026.9A patent/CN114257684A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172421A1 (en) * | 2011-08-10 | 2014-06-19 | Goertek Inc. | Speech enhancing method, device for communication earphone and noise reducing communication earphone |
| CN110164446A (en) * | 2018-06-28 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Voice signal recognition methods and device, computer equipment and electronic equipment |
| CN109272989A (en) * | 2018-08-29 | 2019-01-25 | 北京京东尚科信息技术有限公司 | Voice awakening method, device and computer readable storage medium |
| CN112992169A (en) * | 2019-12-12 | 2021-06-18 | 华为技术有限公司 | Voice signal acquisition method and device, electronic equipment and storage medium |
| WO2021180085A1 (en) * | 2020-03-11 | 2021-09-16 | 华为技术有限公司 | Sound pickup method and apparatus and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2704141B1 (en) | Enhancement of a voice signal in a noisy environment | |
| EP2492912B1 (en) | Sound processing apparatus, sound processing method and hearing aid | |
| JP2654503B2 (en) | Wireless terminal | |
| US20200227071A1 (en) | Analysing speech signals | |
| US5970441A (en) | Detection of periodicity information from an audio signal | |
| US20080008311A1 (en) | Methods and apparatus for improving voice quality in an environment with noise | |
| US9536536B2 (en) | Adaptive equalization system | |
| EP1607939B1 (en) | Speech signal compression device, speech signal compression method, and program | |
| EP3905718B1 (en) | Sound pickup device and sound pickup method | |
| CN101909099A (en) | Portable radio communication equipment and control method thereof | |
| US20240062770A1 (en) | Enhanced de-esser for in-car communications systems | |
| CN104867499A (en) | Frequency-band-divided wiener filtering and de-noising method used for hearing aid and system thereof | |
| EP3823315B1 (en) | Sound pickup device, sound pickup method, and sound pickup program | |
| US20160295320A1 (en) | Audio capturing enhancement method and audio capturing system using the same | |
| JP5903921B2 (en) | Noise reduction device, voice input device, wireless communication device, noise reduction method, and noise reduction program | |
| US20020019733A1 (en) | System and method for enhancing the intelligibility of received speech in a noise environment | |
| CN110914901A (en) | Verbal signal leveling | |
| CN103813251A (en) | Hearing-aid denoising device and method allowable for adjusting denoising degree | |
| CN115641866A (en) | Signal processing method and device, computer readable storage medium and terminal | |
| CN114257684A (en) | Voice processing method, system and device and electronic equipment | |
| EP2660814B1 (en) | Adaptive equalization system | |
| CN102860047A (en) | Hearing aid and hearing aid control method | |
| WO2020228473A1 (en) | Method and system for speaker loudness control | |
| JP2000250568A (en) | Voice section detecting device | |
| US9294848B2 (en) | Adaptation of a classification of an audio signal in a hearing aid |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220329 |