CN213904931U - Sound off-line speech recognition control device - Google Patents
Sound off-line speech recognition control device Download PDFInfo
- Publication number
- CN213904931U CN213904931U CN202020856198.4U CN202020856198U CN213904931U CN 213904931 U CN213904931 U CN 213904931U CN 202020856198 U CN202020856198 U CN 202020856198U CN 213904931 U CN213904931 U CN 213904931U
- Authority
- CN
- China
- Prior art keywords
- voice
- audio
- audio signal
- digital audio
- signal
- 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
Images
Landscapes
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
The utility model provides a stereo set off-line speech recognition controlling means, include: the voice pickup device is arranged on the front panel of the sound box and is used for acquiring a voice instruction signal from a user; the audio feedback circuit is connected with an output circuit of a sound source module of the sound box and is used for collecting audio signals which are being played; the coding and decoding unit is electrically connected with the voice pickup and the audio feedback circuit and is used for converting the voice instruction signal into a first digital audio signal and converting the audio signal into a second digital audio signal; the voice recognition control unit is electrically connected with the coding and decoding unit and used for filtering audio bottom noise in the first digital audio signal according to the second digital audio signal and recognizing a control instruction corresponding to the voice instruction signal from the filtered first digital audio signal, so that the audio bottom noise can be filtered by utilizing audio feedback, the recognition rate is improved, the control distance is longer, the sensitivity is higher, and the application scene is wider.
Description
Technical Field
The utility model relates to a stereo set field, in particular to stereo set off-line speech recognition controlling means.
Background
The existing off-line speech recognition technology is that a main controller directly samples a signal of a front microphone of a sound box, stops outputting audio after receiving a wake-up command, receives command speech to be executed in a quite environment, and performs off-line recognition to achieve a high command recognition rate. The existing off-line voice recognition technology can not recognize voice instructions under the condition of continuous audio output, the recognition rate is low, the distance is short, and the voice recognition needs to be carried out in the environment below a certain noise decibel.
Disclosure of Invention
The utility model provides a stereo set off-line speech recognition controlling means to solve at least one above-mentioned technical problem.
In order to solve the above problem, as an aspect of the present invention, there is provided a sound system off-line speech recognition control apparatus, including: the voice pickup device is arranged on the front panel of the sound box and is used for acquiring a voice instruction signal from a user; the audio feedback circuit is connected with an output circuit of a sound source module of the sound box and is used for collecting audio signals which are being played; the coding and decoding unit is electrically connected with the voice pickup and the audio feedback circuit and is used for converting the voice instruction signal into a first digital audio signal and converting the audio signal into a second digital audio signal; the voice recognition control unit is electrically connected with the coding and decoding unit and is used for filtering audio noise in the first digital audio signal according to the second digital audio signal and recognizing a control instruction corresponding to the voice instruction signal from the filtered first digital audio signal.
Preferably, the sound offline voice recognition control device further comprises a power supply for supplying power.
Since the technical scheme is used, the utility model discloses usable audio frequency feedback realizes that the audio frequency end is made an uproar and is filtered, can be under the condition of the normal output of audio frequency off-line recognition voice command, solved the sound source under the condition of big decibel output, other off-line voice recognition units can't filter out former sound source part, snatch voice command's problem from the centre, improved the recognition rate, control distance is farther, and sensitivity is higher, makes the application scene more extensive.
Drawings
Fig. 1 schematically shows a structural view of the present invention.
Detailed Description
The embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
The utility model discloses an aspect provides a stereo set off-line speech recognition controlling means, include: the voice pickup device is arranged on the front panel of the sound box and is used for acquiring a voice instruction signal from a user; the audio feedback circuit is connected with an output circuit of a sound source module of the sound box and is used for collecting audio signals which are being played; the coding and decoding unit is electrically connected with the voice pickup and the audio feedback circuit and is used for converting the voice instruction signal into a first digital audio signal and converting the audio signal into a second digital audio signal; the voice recognition control unit is electrically connected with the coding and decoding unit and is used for filtering audio noise in the first digital audio signal according to the second digital audio signal and recognizing a control instruction corresponding to the voice instruction signal from the filtered first digital audio signal. The filtering of the audio noise floor in the first digital audio signal according to the second digital audio signal and the identification of the control instruction corresponding to the voice instruction signal from the first digital audio signal belong to the technologies known in the prior art, and can be implemented in any corresponding manner in the prior art, which is not described herein again.
Preferably, the sound offline voice recognition control device further comprises a power supply for supplying power.
In the technical scheme, only one microphone voice pickup device is needed and is arranged on the front panel of the sound box to obtain the voice command signal. The voice recognition control unit collects voice instruction signals and audio feedback signals at the same time, filters audio background noise through a processing algorithm, captures required voice instruction signals from the audio background noise, and decodes the voice instruction signals through an instruction decoding algorithm to obtain digital instructions and response audio signals; the digital instruction can output and control the peripheral circuit to realize uninterrupted audio playing and voice recognition control, and the response audio signal is connected to the output circuit of the sound source module through the response output circuit.
Since the technical scheme is used, the utility model discloses usable audio frequency feedback realizes that the audio frequency end is made an uproar and is filtered, can be under the condition of the normal output of audio frequency off-line recognition voice command, solved the sound source under the condition of big decibel output, other off-line voice recognition units can't filter out former sound source part, snatch voice command's problem from the centre, improved the recognition rate, control distance is farther, and sensitivity is higher, makes the application scene more extensive.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. An audio offline speech recognition control device, comprising:
the voice pickup device is arranged on the front panel of the sound box and is used for acquiring a voice instruction signal from a user;
the audio feedback circuit is connected with an output circuit of a sound source module of the sound box and is used for collecting audio signals which are being played;
the coding and decoding unit is electrically connected with the voice pickup and the audio feedback circuit and is used for converting the voice instruction signal into a first digital audio signal and converting the audio signal into a second digital audio signal;
the voice recognition control unit is electrically connected with the coding and decoding unit and is used for filtering audio noise in the first digital audio signal according to the second digital audio signal and recognizing a control instruction corresponding to the voice instruction signal from the filtered first digital audio signal.
2. The audio offline voice recognition control device of claim 1, further comprising a power supply for supplying power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020856198.4U CN213904931U (en) | 2020-05-20 | 2020-05-20 | Sound off-line speech recognition control device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020856198.4U CN213904931U (en) | 2020-05-20 | 2020-05-20 | Sound off-line speech recognition control device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN213904931U true CN213904931U (en) | 2021-08-06 |
Family
ID=77095916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020856198.4U Active CN213904931U (en) | 2020-05-20 | 2020-05-20 | Sound off-line speech recognition control device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN213904931U (en) |
-
2020
- 2020-05-20 CN CN202020856198.4U patent/CN213904931U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108028982A (en) | Electronic equipment and its audio-frequency processing method | |
| CN106766086A (en) | The air-conditioning that a kind of active abates the noise | |
| CN101247672A (en) | Speaker apparatus, speaker driving apparatus and control method thereof | |
| CN102915732A (en) | Method and device for identifying voice commands restraining background broadcasts | |
| KR20170044689A (en) | Voice wake-up method and device | |
| CN105427866A (en) | Voice processing method and device, and pickup circuit | |
| CN111128167A (en) | Far-field voice awakening method and device, electronic product and storage medium | |
| EP1920633B1 (en) | Hearing aid with increased acoustic bandwidth | |
| CN110366067B (en) | Far field voice module echo cancellation circuit and device | |
| CN105383376A (en) | Pedestrian sound warning device, based on environmental sound feedback, of new energy vehicle | |
| CN213904931U (en) | Sound off-line speech recognition control device | |
| CN214381356U (en) | Pickup equipment | |
| CN102932710A (en) | Method and device for bass compensation | |
| CN207150781U (en) | A kind of active noise reduction earphone of pluggable earphone line | |
| CN103179295A (en) | Mobile terminal capable of removing echo and echo removing method thereof | |
| CN109361367B (en) | Frequency conversion automatic gain control device suitable for intelligent power amplifier chip | |
| CN209784987U (en) | system for controlling output volume and intelligent household appliance | |
| CN205113134U (en) | New energy automobile pedestrian sound warning device based on environment sound feedback | |
| CN200967732Y (en) | Unmanned hand truck with voice warning device | |
| CN103744335B (en) | A kind of embedded digital sound-effect processing equipment | |
| CN110248287A (en) | A kind of audio frequency processing circuit | |
| CN207968840U (en) | A kind of circular audio devices of 3D | |
| CN105681976A (en) | Inaudible sound wave based microphone anti-howling method and system | |
| CN217135696U (en) | Small simply-controlled sound amplification system | |
| CN206283664U (en) | A kind of multifunction speech card for intelligent robot system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |