CN105812517A - Receiver unit having voice recognition function - Google Patents
Receiver unit having voice recognition function Download PDFInfo
- Publication number
- CN105812517A CN105812517A CN201410844752.6A CN201410844752A CN105812517A CN 105812517 A CN105812517 A CN 105812517A CN 201410844752 A CN201410844752 A CN 201410844752A CN 105812517 A CN105812517 A CN 105812517A
- Authority
- CN
- China
- Prior art keywords
- voice
- unit
- converting
- module
- speed
- 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.)
- Withdrawn
Links
Abstract
The invention discloses a receiver unit having the voice recognition function. The receiver unit comprises a voice input module, an audio frequency processing module, a voice recognition module and a storage module. The voice input module is used for receiving voices in the surrounding environment. The storage module is used for storing predetermined effective voice patterns. The voice recognition module is used for recognizing the types of a received voice based on predetermined effective voice patterns. If the received voice is recognized by the voice recognition module as the effective voice, the voice is not filtered. If the received voice is recognized by the voice recognition module as the noise, the voice is filtered out. The receiver unit has the voice recognition function and received voices are subjected to the basic filtering treatment. Meanwhile, the speed range, the vocabulary accumulative total and the like for effective voices are preset. In this way, the influence caused by the frequency sweeping approach can be avoided. For example, the conditions that effective voices are filtered out, the filtering effect is unsatisfactory and the like, are avoided. The voice receiving quality is improved.
Description
Technical field
The present invention relates to voice processing technology field, be specifically related to a kind of receiver unit with speech identifying function.
Background technology
Environment it is typically due to noisy, it is impossible to catch the sound of phone when people receive calls out of doors, and universal along with mobile phone, important way as interpersonal communication, much important thing is all passed on by mobile phone, therefore possesses the receiver unit of noise filter function, by extensive concern.
The application for a patent for invention of application number 201320611465.1, disclose a kind of receiver with filtering noise function, including receiver's housing (1), and the tone-entering hole (2) on receiver's housing (1) two ends and go out acoustic aperture (3) respectively, noise filter (4) and speaker (5) it is provided with in described receiver's housing (1), described noise filter (4) is placed in the positive lower end of tone-entering hole (2), it is serially connected in internal sound signal processing apparatus loop, described speaker (5) is in the positive lower end going out acoustic aperture (3), it is serially connected in out in signal processor loop.
This novel advantage is to be provided with noise filter in receiver, it is possible to decrease the interference of ambient noise, it addition, be additionally provided with speaker in receiver, is prevented effectively from that the other side's sound is too small and the problem that affects exchange, it is ensured that the normal communication of both sides' phone.
But, noise filter is the equal of a wave filter, by artificially arranging a noise threshold, the sound frequency of reception and this noise threshold is compared, lower than sound frequency be filtered.And somebody itself speaks, the frequency of sound is just relatively low, it is easy to is near this noise threshold, and is filtered, then even if useful voice reception people still cannot hear.If what this noise threshold arranged is too low, the effect of filtering noise can not had again.
The application for a patent for invention of application number 201020137352.9, discloses a kind of device for filtering noise of handset, including being arranged on microphone and the cymoscope on receiver, for detecting the acoustic signals of the other side;The wave filter being connected with cymoscope, for filtering the sound of other signal;Be arranged on the sound absorber on receiver, acoustic absorption its be connected with cymoscope by trigger, be used for sponging the noise signal of surrounding;The microphone being connected with trigger.
The invention has the beneficial effects as follows: by filtering and detection, filtered the noise being not belonging to both call sides acoustical signal, shielded the noise of surrounding, it is possible to caught the sound of the other side.
But, the filtering principle of wave filter is all to be filtered out by all sound in certain frequency band, then the sound for being natively in filtered bands will be filtered, affects communication effect.
Summary of the invention
The technical problem to be solved in the present invention is: in order to solve the problems referred to above, a kind of receiver unit with speech identifying function of special offer.
The technical solution adopted in the present invention is:
A kind of receiver unit with speech identifying function, including: voice input module, audio processing modules, sound identification module and memory module;
Wherein, described voice input module is for receiving the voice in surrounding;
Described memory module is used for storing default effective speech pattern;
Described sound identification module is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
Further, the described following at least one information presetting the efficient voice that effective speech pattern includes pre-setting: frequency band range, frequent word finder, signal rate.
Further, described sound identification module includes filter unit, language and characters unit, test the speed unit;
Wherein, described filter unit is for being filtered described voice processing;
Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;
Further, unit is tested the speed described in for detecting the speed of described voice.
Described audio processing modules includes A/D converting unit and D/A converting unit;
Wherein, described A/D converting unit is used for converting speech into digital signal;
Described D/A converting unit is for converting digital signals into voice respectively.
A kind of telephone receiver, described telephone receiver includes: voice input module, audio processing modules, sound identification module and memory module;Wherein, described voice input module is for receiving the voice in surrounding;Described memory module is used for storing default effective speech pattern;Described sound identification module is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
Further, the described following at least one information presetting the efficient voice that effective speech pattern includes pre-setting: frequency band range, frequent word finder, signal rate.
Further, described sound identification module includes filter unit, language and characters unit, test the speed unit;Wherein, described filter unit is for being filtered described voice processing;Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;The described unit that tests the speed is for detecting the speed of described voice.
Further, described audio processing modules includes A/D converting unit and D/A converting unit;Wherein, described A/D converting unit is used for converting speech into digital signal;Described D/A converting unit is for converting digital signals into voice respectively.
A kind of microphone, described telephone receiver includes: voice input module, audio processing modules, sound identification module and memory module;Wherein, described voice input module is for receiving the voice in surrounding;Described memory module is used for storing default effective speech pattern;Described sound identification module is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
Further, the described following at least one information presetting the efficient voice that effective speech pattern includes pre-setting: frequency band range, frequent word finder, signal rate.
Further, described sound identification module includes filter unit, language and characters unit, test the speed unit;Wherein, described filter unit is for being filtered described voice processing;Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;The described unit that tests the speed is for detecting the speed of described voice.
Further, described audio processing modules includes A/D converting unit and D/A converting unit;Wherein, described A/D converting unit is used for converting speech into digital signal;Described D/A converting unit is for converting digital signals into voice respectively.
The present invention and application number are the application for a patent for invention of 201320611465.1, and the application for a patent for invention that application number is 201020137352.9 compares, have the beneficial effect that the present invention possesses speech identifying function, voice for receiving can carry out most basic Filtering Processing, can also be pre-set some and think that the speed range of efficient voice, vocabulary add up, avoid the impact that frequency single solution for diverse problems brings, such as efficient voice is filtered, filter effect is undesirable, improves the quality of phonetic incepting.
Accompanying drawing explanation
Fig. 1 is the structural representation that the present invention has the receiver unit of speech identifying function;
Fig. 2 is the structural representation of telephone receiver of the present invention;
Fig. 3 is the structural representation of microphone of the present invention.
Detailed description of the invention
Shown in reference to the accompanying drawings, by detailed description of the invention, the present invention is further described.
Embodiment 1:
As it is shown in figure 1, a kind of receiver unit 5 with speech identifying function, including: voice input module 1, audio processing modules 2, sound identification module 3 and memory module 4, wherein, described voice input module 1 is for receiving the voice in surrounding;Described memory module 4 is used for storing default effective speech pattern;Described sound identification module 3 is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
The present invention possesses speech identifying function, voice for receiving can carry out most basic Filtering Processing, can also be pre-set some and think that the speed range of efficient voice, vocabulary add up, avoid the impact that frequency single solution for diverse problems brings, such as efficient voice is filtered, filter effect is undesirable, improves the quality of phonetic incepting.
Embodiment 2:
On the basis of embodiment 1, preset the following at least one information of the efficient voice that effective speech pattern includes pre-setting described in the present embodiment: frequency band range, frequent word finder, signal rate.
Embodiment 3:
On the basis of embodiment 2, sound identification module described in the present embodiment includes filter unit, language and characters unit, test the speed unit;Wherein, described filter unit is for being filtered described voice processing;Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;The described unit that tests the speed is for detecting the speed of described voice.
The voice received can be identified by the sound identification module of the present invention in many ways, it is to avoid only relies on and distinguishes, by means of speech frequency, the situation that efficient voice that noise there will be is filtered.
Embodiment 4:
On the basis of embodiment 1, audio processing modules described in the present embodiment includes A/D converting unit and D/A converting unit;Wherein, described A/D converting unit is used for converting speech into digital signal;Described D/A converting unit is for converting digital signals into voice respectively.
Voice is carried out analog digital conversion by the present invention, it is possible to achieve more accurate Audio Processing.
Embodiment 5:
As in figure 2 it is shown, a kind of telephone receiver 6, described telephone receiver 6 includes the arbitrary shown receiver unit 5 with speech identifying function of embodiment 1 ~ embodiment 4.
The receiver unit with speech identifying function is applied on telephone receiver, and this telephone receiver goes for base receiver, earpiece, it is also possible to suitable in arbitrary equipment possessing function of radio receiver such as panel computer receiver.Most basic Filtering Processing can be carried out for the voice received, can also be pre-set some and think that the speed range of efficient voice, vocabulary add up, avoid the impact that frequency single solution for diverse problems brings, such as efficient voice is filtered, filter effect is undesirable, improves the quality of phonetic incepting.
Embodiment 6:
As in figure 2 it is shown, a kind of microphone 7, described microphone 7 includes the arbitrary shown receiver unit 5 with speech identifying function of embodiment 1 ~ embodiment 4.
The receiver unit with speech identifying function is applied on microphone, most basic Filtering Processing can be carried out for the voice received, can also be pre-set some and think that the speed range of efficient voice, vocabulary add up, avoid the impact that frequency single solution for diverse problems brings, such as efficient voice is filtered, filter effect is undesirable, improves the quality of phonetic incepting.
Embodiment of above is merely to illustrate the present invention; and it is not limitation of the present invention; those of ordinary skill about technical field; without departing from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all equivalent technical schemes fall within scope of the invention, and the scope of patent protection of the present invention should be defined by the claims.
Claims (12)
1. a receiver unit with speech identifying function, it is characterised in that including: voice input module, audio processing modules, sound identification module and memory module;
Wherein, described voice input module is for receiving the voice in surrounding;
Described memory module is used for storing default effective speech pattern;
Described sound identification module is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
2. device according to claim 1, it is characterised in that the described following at least one information presetting the efficient voice that effective speech pattern includes pre-setting: frequency band range, frequent word finder, signal rate.
3. device according to claim 2, it is characterised in that described sound identification module includes filter unit, language and characters unit, test the speed unit;
Wherein, described filter unit is for being filtered described voice processing;
Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;
The described unit that tests the speed is for detecting the speed of described voice.
4. device according to claim 1, it is characterised in that described audio processing modules includes A/D converting unit and D/A converting unit;
Wherein, described A/D converting unit is used for converting speech into digital signal;
Described D/A converting unit is for converting digital signals into voice respectively.
5. a telephone receiver, it is characterised in that described telephone receiver includes: voice input module, audio processing modules, sound identification module and memory module;Wherein, described voice input module is for receiving the voice in surrounding;Described memory module is used for storing default effective speech pattern;Described sound identification module is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
6. telephone receiver according to claim 5, it is characterised in that the described following at least one information presetting the efficient voice that effective speech pattern includes pre-setting: frequency band range, frequent word finder, signal rate.
7. telephone receiver according to claim 6, it is characterised in that described sound identification module includes filter unit, language and characters unit, test the speed unit;Wherein, described filter unit is for being filtered described voice processing;Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;The described unit that tests the speed is for detecting the speed of described voice.
8. telephone receiver according to claim 5, it is characterised in that described audio processing modules includes A/D converting unit and D/A converting unit;Wherein, described A/D converting unit is used for converting speech into digital signal;Described D/A converting unit is for converting digital signals into voice respectively.
9. a microphone, it is characterised in that described telephone receiver includes: voice input module, audio processing modules, sound identification module and memory module;Wherein, described voice input module is for receiving the voice in surrounding;Described memory module is used for storing default effective speech pattern;Described sound identification module is not for according to the described type presetting the voice that effective speech pattern recognition receives, if recognition result is described voice is efficient voice, filtering, if recognition result is described voice is noise, filter.
10. microphone according to claim 9, it is characterised in that the described following at least one information presetting the efficient voice that effective speech pattern includes pre-setting: frequency band range, frequent word finder, signal rate.
11. microphone according to claim 10, it is characterised in that described sound identification module includes filter unit, language and characters unit, test the speed unit;Wherein, described filter unit is for being filtered described voice processing;Described language and characters unit for becoming word by described voice record, and adds up the frequency of occurrences of vocabulary in described word;The described unit that tests the speed is for detecting the speed of described voice.
12. microphone according to claim 10, it is characterised in that described audio processing modules includes A/D converting unit and D/A converting unit;Wherein, described A/D converting unit is used for converting speech into digital signal;Described D/A converting unit is for converting digital signals into voice respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410844752.6A CN105812517A (en) | 2014-12-31 | 2014-12-31 | Receiver unit having voice recognition function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410844752.6A CN105812517A (en) | 2014-12-31 | 2014-12-31 | Receiver unit having voice recognition function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105812517A true CN105812517A (en) | 2016-07-27 |
Family
ID=56421081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410844752.6A Withdrawn CN105812517A (en) | 2014-12-31 | 2014-12-31 | Receiver unit having voice recognition function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105812517A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108630202A (en) * | 2017-03-21 | 2018-10-09 | 株式会社东芝 | Speech recognition equipment, audio recognition method and speech recognition program |
-
2014
- 2014-12-31 CN CN201410844752.6A patent/CN105812517A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108630202A (en) * | 2017-03-21 | 2018-10-09 | 株式会社东芝 | Speech recognition equipment, audio recognition method and speech recognition program |
CN108630202B (en) * | 2017-03-21 | 2021-12-03 | 株式会社东芝 | Speech recognition apparatus, speech recognition method, and recording medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100588210C (en) | Wireless telephone and method for processing audio single in the wireless telephone | |
US8184816B2 (en) | Systems and methods for detecting wind noise using multiple audio sources | |
US10269369B2 (en) | System and method of noise reduction for a mobile device | |
CN104427068B (en) | A kind of audio communication method and device | |
CN105657110B (en) | Echo cancellation method and device for voice communication | |
US20120084080A1 (en) | Machine for Enabling and Disabling Noise Reduction (MEDNR) Based on a Threshold | |
US20060115095A1 (en) | Reverberation estimation and suppression system | |
CN203747885U (en) | Acoustic signal processing system having function of double-talk detection | |
US9842599B2 (en) | Voice processing apparatus and voice processing method | |
US7519347B2 (en) | Method and device for noise detection | |
CN109195042A (en) | The high-efficient noise-reducing earphone and noise reduction system of low-power consumption | |
EP2806424A1 (en) | Improved noise reduction | |
JP6833616B2 (en) | Echo suppression device, echo suppression method and echo suppression program | |
US20120226495A1 (en) | Device and method for filtering out noise from speech of caller | |
CN105744084A (en) | Mobile terminal and method for improving conversation tone quality thereof | |
CN103997561A (en) | Communication apparatus and voice processing method therefor | |
CN103514876A (en) | Method and device for eliminating noise and mobile terminal | |
CN103402038A (en) | Method and device for eliminating echo of receiver from opposite side in handfree state of mobile phone | |
CN108605191B (en) | Abnormal sound detection method and device | |
CN105812517A (en) | Receiver unit having voice recognition function | |
US8903107B2 (en) | Wideband noise reduction system and a method thereof | |
CN107370898B (en) | Ring tone playing method, terminal and storage medium thereof | |
US9847092B2 (en) | Methods and system for wideband signal processing in communication network | |
US8275141B2 (en) | Noise reduction system and noise reduction method | |
CN204539248U (en) | A kind of receiver unit with speech identifying function |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20160727 |
|
WW01 | Invention patent application withdrawn after publication |