CN110459227A - Voiceprint registration method based on smart television - Google Patents
Voiceprint registration method based on smart television Download PDFInfo
- Publication number
- CN110459227A CN110459227A CN201910808446.XA CN201910808446A CN110459227A CN 110459227 A CN110459227 A CN 110459227A CN 201910808446 A CN201910808446 A CN 201910808446A CN 110459227 A CN110459227 A CN 110459227A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- user
- vocal print
- recognition
- smart television
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- 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
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/10—Network architectures or network communication protocols for network security for controlling access to devices or network resources
Abstract
The voiceprint registration method based on smart television that the invention discloses a kind of, comprising the following steps: user's vocal print is identified;If the Application on Voiceprint Recognition of user fails, the vocal print of recognition failures is registered automatically;If the Application on Voiceprint Recognition success of user, reports the successful voiceprint of identification.Present invention realization voiceprint registration zero gate sill and raising Application on Voiceprint Recognition rate, keep the voice print database of acquisition more complete, recommend the resource for more meeting its demand to user, can give user more intelligent experience, improve the competitiveness of product in market.
Description
Technical field
The present invention relates to field of artificial intelligence, especially a kind of voiceprint registration method based on smart television.
Background technique
Have benefited from the development of the information technologies such as cloud computing, big data, Internet of Things, deep learning in recent years, biological characteristic is known
Other technology seizes rapidly interconnection market.Vocal print is exactly a kind of biological behavior characteristic.Intelligent television end acquires voice print database
It is accustomed to doing recommendation business to user according to user behavior, but the threshold height of voiceprint registration at present, user is needed actively to go to record
Sound registration, subscriber usage and vocal print acquisition rate be not high.In addition, Application on Voiceprint Recognition cannot be guaranteed accurate, identification very at present
The case where will appear recognition failures in the process.
Summary of the invention
To solve problems of the prior art, the object of the present invention is to provide a kind of, and the vocal print based on smart television is infused
Volume method, the present invention realizes voiceprint registration zero gate sill and improves Application on Voiceprint Recognition rate, keeps the voice print database of acquisition more complete, pushes away to user
The resource for more meeting its demand is recommended, can give user more intelligent experience, improve the competitiveness of product in market.
To achieve the above object, the technical solution adopted by the present invention is that: a kind of voiceprint registration method based on smart television,
The following steps are included:
Step 1 identifies user's vocal print;
If step 2 fails to the Application on Voiceprint Recognition of user in step 1, the vocal print of recognition failures is registered automatically;
If step 3, the Application on Voiceprint Recognition success to user in step 1, report the successful voiceprint of identification.
As a preferred embodiment, the step 1 is specific as follows:
When user wakes up smart television voice by waking up word far field, the recording data for waking up word to user carries out vocal print knowledge
Not, and recognition result is returned.
As another preferred embodiment, the step 2 is specific as follows:
The recognition result returned to step 1 judges, has indicated the vocal print if returning to vocal print ID and vocal print gender
Registration, if only return vocal print gender if indicate the Application on Voiceprint Recognition failure or it is unregistered, if recognition failures by the vocal print automatically into
Row registration.
As another preferred embodiment, the step 3 is specific as follows:
After waking up smart television speech recognition success every time, the voiceprint that will acquire carries out data acquisition, and
It is reported to semanteme and matchmakes to provide and recommend.
The beneficial effects of the present invention are:
The present invention is when user using voice when being interacted, and without actively being registered, zero gate sill, recognition failures can be certainly
Dynamic registration, improves Application on Voiceprint Recognition rate, acquires more full voice print database, recommends the resource for more meeting its demand to user, gives user
Bring more intelligent experience.
Detailed description of the invention
Fig. 1 is the flow diagram of the embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described in detail with reference to the accompanying drawing.
Embodiment
As shown in Figure 1, a kind of voiceprint registration method based on smart television, comprising the following steps:
Step 1 identifies user's vocal print: when user wakes up TV speech by waking up word far field, waking up to user
The recording data of word carries out Application on Voiceprint Recognition, and returns to recognition result.
Step 2, recognition failures are registered automatically: the recognition result of the return of obtaining step 1 is simultaneously judged, if returned
Vocal print ID and vocal print gender then indicate registered, indicate recognition failures if only returning to vocal print gender;Recognition failures are then by the sound
Line is registered automatically.Specifically, the voice print database upper limit that every TV can be registered is 10, the vocal print of all registrations is saved in
Locally, it is emptied when factory reset.
Step 3 reports voiceprint: is waken up after identifying successfully every time, the voiceprint that will acquire carries out data and adopts
Collection, and be reported to semanteme and matchmake to provide and recommend.
In user using being registered automatically for it in smart television voice process, also can when user's registration crosses but recognition failures
Automatic registration vocal print, the voice print database of zero gate sill, acquisition is more complete, and the resource of recommendation is properer;One user possesses multiple vocal prints,
Improve discrimination, for a period of time from the point of view of, the corresponding behavioral data of these vocal prints ID should be it is similar, because of the behavior of user
Habit is metastable, so the user is identified as any one vocal print ID, is influenced less on business such as recommendations.
A specific embodiment of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.
Claims (4)
1. a kind of voiceprint registration method based on smart television, which comprises the following steps:
Step 1 identifies user's vocal print;
If step 2 fails to the Application on Voiceprint Recognition of user in step 1, the vocal print of recognition failures is registered automatically;
If step 3, the Application on Voiceprint Recognition success to user in step 1, report the successful voiceprint of identification.
2. the voiceprint registration method according to claim 1 based on smart television, which is characterized in that the step 1 is specific
It is as follows:
When user wakes up smart television voice by waking up word far field, the recording data for waking up word to user carries out Application on Voiceprint Recognition,
And return to recognition result.
3. the voiceprint registration method according to claim 2 based on smart television, which is characterized in that the step 2 is specific
It is as follows:
The recognition result returned to step 1 judges, indicates that the vocal print is registered if returning to vocal print ID and vocal print gender,
Application on Voiceprint Recognition failure or unregistered is indicated if only returning to vocal print gender, if recognition failures infuse the vocal print automatically
Volume.
4. the voiceprint registration method according to claim 1 or 3 based on smart television, which is characterized in that step 3 tool
Body is as follows:
After waking up smart television speech recognition success every time, the voiceprint that will acquire carries out data acquisition, and reports
It matchmakes to provide to semanteme and recommend.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910808446.XA CN110459227A (en) | 2019-08-29 | 2019-08-29 | Voiceprint registration method based on smart television |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910808446.XA CN110459227A (en) | 2019-08-29 | 2019-08-29 | Voiceprint registration method based on smart television |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110459227A true CN110459227A (en) | 2019-11-15 |
Family
ID=68489921
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910808446.XA Pending CN110459227A (en) | 2019-08-29 | 2019-08-29 | Voiceprint registration method based on smart television |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110459227A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104575504A (en) * | 2014-12-24 | 2015-04-29 | 上海师范大学 | Method for personalized television voice wake-up by voiceprint and voice identification |
CN107492379A (en) * | 2017-06-30 | 2017-12-19 | 百度在线网络技术(北京)有限公司 | A kind of voice-print creation and register method and device |
CN107623614A (en) * | 2017-09-19 | 2018-01-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN108182395A (en) * | 2017-12-25 | 2018-06-19 | 北京华捷艾米科技有限公司 | User registering method and device |
CN108766446A (en) * | 2018-04-18 | 2018-11-06 | 上海问之信息科技有限公司 | Method for recognizing sound-groove, device, storage medium and speaker |
CN109246473A (en) * | 2018-09-13 | 2019-01-18 | 苏州思必驰信息科技有限公司 | The voice interactive method and terminal system of individualized video barrage based on Application on Voiceprint Recognition |
-
2019
- 2019-08-29 CN CN201910808446.XA patent/CN110459227A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104575504A (en) * | 2014-12-24 | 2015-04-29 | 上海师范大学 | Method for personalized television voice wake-up by voiceprint and voice identification |
CN107492379A (en) * | 2017-06-30 | 2017-12-19 | 百度在线网络技术(北京)有限公司 | A kind of voice-print creation and register method and device |
CN107623614A (en) * | 2017-09-19 | 2018-01-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN108182395A (en) * | 2017-12-25 | 2018-06-19 | 北京华捷艾米科技有限公司 | User registering method and device |
CN108766446A (en) * | 2018-04-18 | 2018-11-06 | 上海问之信息科技有限公司 | Method for recognizing sound-groove, device, storage medium and speaker |
CN109246473A (en) * | 2018-09-13 | 2019-01-18 | 苏州思必驰信息科技有限公司 | The voice interactive method and terminal system of individualized video barrage based on Application on Voiceprint Recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109582793B (en) | Model training method, customer service system, data labeling system and readable storage medium | |
CN108351986B (en) | Learning system, learning apparatus, training data generating method, and computer readable medium | |
CN110363194B (en) | NLP-based intelligent examination paper reading method, device, equipment and storage medium | |
WO2018036555A1 (en) | Session processing method and apparatus | |
KR102276728B1 (en) | Multimodal content analysis system and method | |
CN101071418B (en) | Chat method and system | |
CN109241251A (en) | A kind of session interaction method | |
CN109637547B (en) | Audio data labeling method and device, electronic equipment and storage medium | |
CN112287089B (en) | Classification model training and automatic question-answering method and device for automatic question-answering system | |
CN111984821A (en) | Method and device for determining dynamic cover of video, storage medium and electronic equipment | |
CN111709242B (en) | Chinese punctuation mark adding method based on named entity recognition | |
CN103198828A (en) | Method and system of construction of voice corpus | |
US11816609B2 (en) | Intelligent task completion detection at a computing device | |
WO2024000867A1 (en) | Emotion recognition method and apparatus, device, and storage medium | |
CN110210540B (en) | Cross-social media user identity recognition method and system based on attention mechanism | |
CN105809557A (en) | Method and device for mining genders of users in social network | |
CN110580516A (en) | interaction method and device based on intelligent robot | |
CN107704869B (en) | Corpus data sampling method and model training method | |
CN111611350A (en) | Response method and device based on health knowledge and electronic equipment | |
CN116127065A (en) | Simple and easy-to-use incremental learning text classification method and system | |
CN110459227A (en) | Voiceprint registration method based on smart television | |
CN109583423A (en) | A kind of method, apparatus and associated component of Handwritten Digit Recognition | |
CN109739968A (en) | A kind of data processing method and device | |
CN109240718B (en) | Intelligent character construction and analysis system and working method thereof | |
CN116681128A (en) | Neural network model training method and device with noisy multi-label data |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191115 |