CN110600009A - Intelligent voice interaction operation platform and interaction method - Google Patents
Intelligent voice interaction operation platform and interaction method Download PDFInfo
- Publication number
- CN110600009A CN110600009A CN201910914201.5A CN201910914201A CN110600009A CN 110600009 A CN110600009 A CN 110600009A CN 201910914201 A CN201910914201 A CN 201910914201A CN 110600009 A CN110600009 A CN 110600009A
- Authority
- CN
- China
- Prior art keywords
- voice
- awakening
- voice recognition
- operation platform
- library
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000002452 interceptive effect Effects 0.000 claims abstract description 62
- 230000003213 activating effect Effects 0.000 claims abstract description 9
- 210000001503 joint Anatomy 0.000 claims abstract description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000013475 authorization Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 6
- 241001672694 Citrus reticulata Species 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- G10L15/08—Speech classification or search
-
- 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
- G10L15/26—Speech to text systems
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses an intelligent voice interaction operation platform and an interaction method, wherein the intelligent voice interaction operation platform comprises a voice awakening recognition module, a voice recognition module and an interaction operation platform, wherein the voice awakening recognition module is used for acquiring awakening voice signals, recognizing and judging a voice recognition library corresponding to awakening words and activating the corresponding voice recognition library; the voice recognition module is used for acquiring a user voice signal, extracting signal characteristic information, comparing the signal characteristic information according to a corresponding voice recognition library and outputting a voice recognition result; the interactive operation platform is used for providing a corresponding interface for a user, carrying out butt joint in different modes aiming at information of different scenes and different places, and realizing final control of voice interaction. According to the intelligent voice interaction operation platform and the interaction method, the overall control of the platform and the authorization of voice recognition can be realized through voice input, the safety and the convenience are higher than those of the existing platform, and the intelligent voice interaction operation platform and the intelligent voice interaction method can be widely popularized.
Description
Technical Field
The invention belongs to the field of voice recognition, and particularly relates to an intelligent voice interaction operation platform and an interaction method.
Background
Speech Recognition technology, also known as Automatic Speech Recognition (ASR), aims at converting the vocabulary content in human Speech into computer-readable input, such as keystrokes, binary codes or character sequences. The fields to which speech recognition technology relates include: signal processing, pattern recognition, probability and information theory, sound and hearing mechanisms, artificial intelligence, and the like. The machine learning field deep learning research is introduced into the speech recognition acoustic model training, and the acoustic model is used for recognizing the sound.
The conventional intelligent system integration platform is operated through a mouse or a keyboard, and is tedious and low in efficiency.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects in the prior art, the invention provides an intelligent voice interaction operation platform and an interaction method, the overall control of the platform and the authorization of voice recognition can be realized through voice input, the safety and the convenience are higher than those of the existing platform, and the intelligent voice interaction operation platform and the intelligent voice interaction method can be widely popularized.
The technical scheme is as follows: the invention relates to an intelligent voice interactive operation platform, which comprises:
the voice awakening recognition module is used for acquiring awakening voice signals, recognizing and judging a voice recognition library corresponding to the awakening words and activating the corresponding voice recognition library;
the voice recognition module is used for acquiring a user voice signal, extracting signal characteristic information, comparing the signal characteristic information according to a corresponding voice recognition library and outputting a voice recognition result;
and the interactive operation platform is used for providing a corresponding interface for a user, carrying out butt joint in different modes aiming at different scenes and different place information and realizing final control of voice interaction.
Furthermore, the voice recognition libraries are a plurality of voice recognition libraries corresponding to different languages, and each voice recognition library is provided with a corresponding awakening language.
Furthermore, the awakening words corresponding to each voice recognition library are the awakening words with unique identifiers.
Further, activating the corresponding voice recognition library refers to extracting signal characteristic information of the voice signal of the wake-up word, comparing the signal characteristic information with the voice recognition library of the wake-up word, and recognizing and judging the voice recognition library corresponding to the wake-up word according to the comparison of the signal characteristic information of the wake-up word with the voice recognition library of the wake-up word.
Further, the interactive operation platform comprises a mobile intelligent device application program and a WEB interface display program.
The invention also discloses an interaction method of the intelligent voice interaction operation platform, which comprises the following steps:
(1) a voice awakening step: a user speaks a corresponding awakening voice signal, a voice awakening recognition module acquires the awakening voice signal, a voice recognition library corresponding to the awakening voice is recognized and judged, and the corresponding voice recognition library is activated;
(2) a voice recognition step: the voice recognition module acquires a user voice signal, extracts signal characteristic information, compares the signal characteristic information according to a corresponding voice recognition library and outputs a voice recognition result;
(3) and a control feedback step: and according to the output voice recognition result, the interactive operation platform drives the corresponding interface to perform operation corresponding to the voice signal of the user, so that final control is realized.
Furthermore, in the voice awakening step, the voice recognition libraries are a plurality of voice recognition libraries corresponding to different languages, and each voice recognition library is provided with a corresponding awakening language.
Further, in the voice awakening step, the awakening words corresponding to each voice recognition library are the awakening words with unique identifiers.
Furthermore, in the voice recognition step, the signal characteristic information of the voice signal of the awakening language is extracted, the awakening language recognition library is compared, and the voice recognition library corresponding to the awakening language is recognized and judged according to the comparison of the awakening language signal characteristic information of the awakening language recognition library.
Further, the interactive operation platform comprises a mobile intelligent device application program and a WEB interface display program.
Has the advantages that: according to the intelligent voice interaction operation platform and the interaction method, the overall control of the platform and the authorization of voice recognition can be realized through voice input, the safety and the convenience are higher than those of the existing platform, and the intelligent voice interaction operation platform and the intelligent voice interaction method can be widely popularized.
Detailed Description
The invention will be further illustrated with reference to specific examples:
example 1
The invention relates to an intelligent voice interactive operation platform, which comprises:
the voice awakening recognition module is used for acquiring awakening voice signals, recognizing and judging a voice recognition library corresponding to the awakening words and activating the corresponding voice recognition library;
the voice recognition module is used for acquiring a user voice signal, extracting signal characteristic information, comparing the signal characteristic information according to a corresponding voice recognition library and outputting a voice recognition result;
and the interactive operation platform is used for providing a corresponding interface for a user, carrying out butt joint in different modes aiming at different scenes and different place information and realizing final control of voice interaction.
Preferably, the speech recognition libraries are a plurality of speech recognition libraries corresponding to different languages, and each speech recognition library is provided with a corresponding wake-up language.
Preferably, the wakeup words corresponding to each speech recognition library are uniquely identified wakeup words.
Preferably, activating the corresponding voice recognition library refers to extracting signal characteristic information of the wake-up language voice signal, comparing the signal characteristic information with the wake-up language recognition library, and recognizing and judging the voice recognition library corresponding to the wake-up language according to the comparison of the wake-up language signal characteristic information with the wake-up language recognition library.
Preferably, the interactive operation platform comprises a mobile intelligent device application program and a WEB interface display program.
The interaction method of the intelligent voice interaction operation platform comprises the following steps:
(1) a voice awakening step: a user speaks a corresponding awakening voice signal, a voice awakening recognition module acquires the awakening voice signal, a voice recognition library corresponding to the awakening voice is recognized and judged, and the corresponding voice recognition library is activated;
(2) a voice recognition step: the voice recognition module acquires a user voice signal, extracts signal characteristic information, compares the signal characteristic information according to a corresponding voice recognition library and outputs a voice recognition result;
(3) and a control feedback step: and according to the output voice recognition result, the interactive operation platform drives the corresponding interface to perform operation corresponding to the voice signal of the user, so that final control is realized.
Preferably, in the voice wake-up step, the voice recognition libraries are a plurality of voice recognition libraries corresponding to different languages, and each voice recognition library is provided with a corresponding wake-up language.
Preferably, in the voice wake-up step, the wake-up words corresponding to each voice recognition library are uniquely identified wake-up words.
Preferably, in the voice recognition step, the signal characteristic information of the wake-up language voice signal is extracted, the wake-up language recognition library is compared, and the voice recognition library corresponding to the wake-up language is recognized and judged according to the comparison of the wake-up language signal characteristic information of the wake-up language recognition library.
Preferably, the interactive operation platform comprises a mobile intelligent device application program and a WEB interface display program.
The voice interaction method of the embodiment aims to realize voice interaction aiming at different languages in the using process of the automatic interaction operation platform by identifying a plurality of different languages. In the use process of the interactive operation platform, the information contained in the voice signal of the user is obtained through the voice signal sent by the voice recognition user, and then the feedback of the corresponding voice recognition result is made. At present, most of voice recognition systems only aim at mandarin. The method only identifies and outputs a voice identification result according to the acquired voice content of the Mandarin, and feeds back and represents the voice content which cannot be identified for the language which cannot be identified.
As the interoperability platform is spread around the world, there may be a possibility that different users may use different languages. For example, some users use cantonese, some users use mandarin, some users use english, to such a situation, the traditional way is to set up a speech recognition system of multiple languages, through operating the operating system of the interactive operating platform, the switching of the speech recognition system can be performed, when the corresponding user uses the interactive operating platform, the speech recognition system can be correspondingly switched to realize the speech interaction with the interactive operating platform, and then the control of the interactive operating platform is realized.
However, for a user who is not good at using the interactive operation platform operation system, the manual operation of the interactive operation platform is not practical, and the situations of misoperation and the like are easy to occur. Moreover, manual operation of interactive operation platforms is often inconvenient. Therefore, different languages are automatically recognized through the voice interaction method, the operation system of the interactive operation platform does not need to be operated to switch the voice recognition system, and the intellectualization and automation of the interactive operation platform are further realized.
To realize automatic recognition of multiple different languages, a speech recognition library of multiple different languages needs to be established first. And correspondingly establishing a voice recognition library according to various languages required to be recognized by the interactive operation platform. It should be noted that, in order to avoid the sample size being too large, the interactive operation platform can be enabled to specifically identify human-computer voice interaction content that may occur in a usage scenario of the interactive operation platform. According to the voice interaction method, the voice content required for human-computer interaction under the use scene of the interactive operation platform is respectively obtained according to different languages, and the voice recognition libraries corresponding to the different languages are respectively established through learning and training. And voice content which does not belong to the platform use scene is not included in the voice recognition library. Therefore, on one hand, the storage of the characteristic information corresponding to the voice content is reduced, on the other hand, the voice recognition library can recognize the corresponding voice signal quickly, and the situation that a large amount of time is spent for recognizing and comparing the voice signal due to the fact that the voice recognition library compares the sample amount is too large is avoided. In the process of establishing each voice recognition library of different languages, a large amount of voice contents needed to be used for man-machine interaction under the use scene of an interactive operation platform need to be obtained, and the voice contents are converted into voltage signals or current signals; then, carrying out analog/digital conversion on the electric signal to obtain a digital signal; and carrying out high-frequency filtering or band-pass filtering on the digital signal to remove the non-voice interference signal.
The purpose of the filtering processing is to remove noise interference of direct current signals and non-voice signals, so that voice data input by a user is convenient for subsequent extraction of characteristic information. If the environmental noise of the input voice is large or other interference signals exist, the voice information is not easy to be identified, so that the voice data needs to be filtered, and the data which is more convenient for extracting the characteristics is obtained. And after filtering the electric signal, preprocessing the electric signal to obtain a second electric signal, and standardizing the second electric signal to obtain a preprocessed second electric signal. Wherein, the standardization treatment specifically comprises: pre-weighting the voice signal, framing the voice signal, and windowing the voice signal. After the preprocessing is completed, the characteristic information of the preprocessed second electric signal can be extracted.
The feature information of the preprocessed second electrical signal is extracted by a Linear Predictive Coding (LPC) method, a linear predictive cepstrum coefficient (LPC) method, and a Mel-scale Frequency cepstral coefficient (MFCC) method. And after the extraction of the characteristic information corresponding to each voice content is finished, the establishment of a corresponding voice recognition library is finished. The method for establishing the voice recognition library is a mature technology, and the fields related to the voice recognition technology comprise: signal processing, pattern recognition, probability theory and information theory, sound production mechanism and auditory mechanism, artificial intelligence, which are not described herein. By respectively extracting the feature information of different languages, the establishment of different speech recognition libraries can be correspondingly completed.
After the voice recognition libraries are established, a corresponding awakening language with a unique identifier needs to be set corresponding to each voice recognition library to be used as a 'key' for activating the corresponding voice recognition library. The awakening words can be set to be in the same language, for example, the awakening words are unified to be Mandarin awakening words, and different voice recognition libraries can be activated by setting voice contents representing different semantics and converting the voice contents into different computer characters. The wake-up language may also be set to have the same semantic meaning in different languages, for example, different reading methods in different languages are turned on, and corresponding voice signals are different, so that different voice recognition libraries can be activated. And identifying the awakening words by presetting an awakening word identification library, wherein the establishment of the awakening word identification library is similar to the establishment of the voice identification library. Since the voice signal also needs to be recognized, the wake-up speech recognition library also needs to extract feature information from the voice signal. Unlike the establishment of a speech recognition library, the feature samples of the wake-up speech recognition library need not be so large. When the awakening language recognition library is established, only the voice content of the awakening language corresponding to each voice recognition library is needed to be obtained, the voice content is converted into an electric signal according to the method, and the establishment of the awakening language recognition library is completed by processing the electric signal and extracting characteristic information.
Then, in the using process of the interactive operation platform, a user needs to send out a wakeup word first and activate a corresponding voice recognition library. And voice signals of the user awakening words are collected through a microphone, corresponding characteristic information is obtained through signal processing, and the corresponding characteristic information is compared with an awakening word recognition library to recognize and judge the voice recognition library corresponding to the awakening words. And if the voice recognition library corresponding to the awakening language can be recognized, activating the corresponding voice recognition library and starting the voice interaction between the user and the interactive operation platform. If the voice recognition library corresponding to the awakening language cannot be recognized, the awakening language is judged to be invalid, and the system feeds back a recognition result to prompt the user to send the awakening language again.
And after the corresponding voice recognition library is activated, the system starts to perform voice recognition, extracts the signal characteristic information by acquiring the voice signal sent by the user according to the signal processing method of the voice content, and then compares the signal characteristic information according to the corresponding voice recognition library which is activated in advance. And in the comparison process, extracting the signal characteristic information with the maximum similarity in the voice recognition library, and outputting computer character information of the voice content corresponding to the signal characteristic information as a voice recognition result by setting a similarity threshold value if the similarity of the signal characteristic information with the maximum similarity is greater than or equal to the set similarity threshold value. If the similarity of the signal characteristic information with the maximum similarity is smaller than the set similarity threshold, the voice recognition library is determined to have no content matched with the voice signal information, and the system feeds back a recognition result to prompt the user to repeat the voice content.
Therefore, the corresponding voice recognition library is activated through the awakening language, and the automatic interactive operation platform can recognize a plurality of different languages. It should be noted that, after the voice recognition library is activated, if no user voice signal is obtained within a set time period, it indicates that the user does not perform voice interaction with the automatic interactive operation platform within the time period, at this time, the corresponding activated voice recognition library enters a "sleep" state, and the system prompts the voice recognition library to be disconnected, and if the voice recognition library needs to be used, the system needs to be awakened again. On the other hand, in the voice recognition process, the feedback is mainly carried out aiming at the conversation content which is possibly generated by a man-machine under the use scene of the interactive operation platform, so that the voice recognition library can be simplified, and the voice signal information sent by the user can be conveniently and quickly recognized. For conversation contents possibly generated by a man-machine under the use scene not belonging to the interactive operation platform, if signal characteristic information with relatively high corresponding similarity possibly does not exist in the voice recognition library, voice recognition cannot be completed, and a recognition failure result can be fed back by the system to prompt a user to repeat the voice contents.
After the voice recognition is finished, aiming at the voice recognition result output by the recognition, the automatic interactive operation platform makes corresponding feedback according to different recognition results. And if the output voice recognition result is the definite control operation of the automatic interactive operation platform, the system outputs a control instruction of the corresponding operation to the automatic interactive operation platform to control the corresponding automatic instrument to execute the operation. And simultaneously feeding back the voice content corresponding to the executed operation by the system. It should be noted that the interactive scene library stores voice content for human-computer interaction according to the recognition result of the user voice signal in the interactive operation platform usage scene. The method and the device have the advantages that the voice interaction content which can occur between a user and the interactive operation platform under the use scene of the cooking platform is stored in a large amount. And feeding back the most appropriate replied voice content to the user by combining the attribute information of the interactive operation platform. Therefore, accurate and detailed man-machine voice interaction is realized.
According to the voice interaction method, the corresponding awakening words are set for different voice recognition libraries, the corresponding voice recognition libraries are activated according to the awakening words judged by recognition, voice recognition is carried out, corresponding feedback is made according to voice recognition results, voice interaction between a user and an interactive operation platform based on multiple different languages is achieved, and the user can conveniently operate the interactive operation platform. Different voice recognition libraries are activated by the help of the awakening words, so that the embarrassment that some users cannot operate the automatic interactive operation platform due to the fact that some users cannot have a certain language can be avoided when the automatic interactive operation platform is used at home. Especially for older users, the native language may be a local dialect, and the native language does not have other languages. Then the interactive operation platform will affect the use of the part of users if only mandarin is recognized. Different voice recognition libraries are activated through the awakening words, the problem of voice interaction between a user and the interactive operation platform is solved, the intelligent interactive operation platform is further intelligent and automatic, the audience area of the automatic interactive operation platform is wider while the user operation is controlled, and more people can use the operation platform conveniently.
According to the intelligent voice interaction operation platform and the interaction method, the overall control of the platform and the authorization of voice recognition can be realized through voice input, the safety and the convenience are higher than those of the existing platform, and the intelligent voice interaction operation platform and the intelligent voice interaction method can be widely popularized.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An intelligent voice interactive operation platform is characterized in that: the method comprises the following steps:
the voice awakening recognition module is used for acquiring awakening voice signals, recognizing and judging a voice recognition library corresponding to the awakening words and activating the corresponding voice recognition library;
the voice recognition module is used for acquiring a user voice signal, extracting signal characteristic information, comparing the signal characteristic information according to a corresponding voice recognition library and outputting a voice recognition result;
and the interactive operation platform is used for providing a corresponding interface for a user, carrying out butt joint in different modes aiming at different scenes and different place information and realizing final control of voice interaction.
2. The intelligent voice interaction operation platform of claim 1, wherein: the voice recognition libraries are a plurality of voice recognition libraries corresponding to different languages, and each voice recognition library is provided with a corresponding awakening language.
3. The intelligent voice interaction operation platform of claim 2, wherein: and the awakening words corresponding to each voice recognition library are the awakening words with unique identifiers.
4. The intelligent voice interaction operation platform of claim 1, wherein: and activating the corresponding voice recognition library refers to extracting signal characteristic information of the voice signal of the awakening language, comparing the signal characteristic information with the awakening language recognition library, and recognizing and judging the voice recognition library corresponding to the awakening language according to the comparison of the awakening language signal characteristic information with the awakening language recognition library.
5. The intelligent voice interaction operation platform of claim 1, wherein: the interactive operation platform comprises a mobile intelligent device application program and a WEB interface display program.
6. An interactive method of an intelligent voice interactive operation platform is characterized in that: the method comprises the following steps:
(1) a voice awakening step: a user speaks a corresponding awakening voice signal, a voice awakening recognition module acquires the awakening voice signal, a voice recognition library corresponding to the awakening voice is recognized and judged, and the corresponding voice recognition library is activated;
(2) a voice recognition step: the voice recognition module acquires a user voice signal, extracts signal characteristic information, compares the signal characteristic information according to a corresponding voice recognition library and outputs a voice recognition result;
(3) and a control feedback step: and according to the output voice recognition result, the interactive operation platform drives the corresponding interface to perform operation corresponding to the voice signal of the user, so that final control is realized.
7. The interactive method of the intelligent voice interactive operation platform according to claim 6, wherein: in the voice awakening step, the voice recognition libraries are a plurality of voice recognition libraries corresponding to different languages, and each voice recognition library is provided with a corresponding awakening language.
8. The interactive method of the intelligent voice interactive operation platform according to claim 7, wherein: in the voice awakening step, the awakening words corresponding to each voice recognition library are the awakening words with unique identifiers.
9. The interactive method of the intelligent voice interactive operation platform according to claim 6, wherein: in the voice recognition step, signal characteristic information of the awakening language voice signal is extracted, the awakening language recognition library is compared, and the voice recognition library corresponding to the awakening language is recognized and judged according to the awakening language recognition library compared with the awakening language signal characteristic information.
10. The interactive method of the intelligent voice interactive operation platform according to claim 6, wherein: the interactive operation platform comprises a mobile intelligent device application program and a WEB interface display program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910914201.5A CN110600009A (en) | 2019-09-26 | 2019-09-26 | Intelligent voice interaction operation platform and interaction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910914201.5A CN110600009A (en) | 2019-09-26 | 2019-09-26 | Intelligent voice interaction operation platform and interaction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110600009A true CN110600009A (en) | 2019-12-20 |
Family
ID=68863402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910914201.5A Pending CN110600009A (en) | 2019-09-26 | 2019-09-26 | Intelligent voice interaction operation platform and interaction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110600009A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109256132A (en) * | 2018-10-29 | 2019-01-22 | 华南农业大学 | A kind of message type information interaction system and method based on speech-sound intelligent identification |
| CN109461448A (en) * | 2018-12-11 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device |
| CN109767767A (en) * | 2019-01-25 | 2019-05-17 | 广州富港万嘉智能科技有限公司 | A kind of voice interactive method, system, electronic equipment and storage medium |
-
2019
- 2019-09-26 CN CN201910914201.5A patent/CN110600009A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109256132A (en) * | 2018-10-29 | 2019-01-22 | 华南农业大学 | A kind of message type information interaction system and method based on speech-sound intelligent identification |
| CN109461448A (en) * | 2018-12-11 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device |
| CN109767767A (en) * | 2019-01-25 | 2019-05-17 | 广州富港万嘉智能科技有限公司 | A kind of voice interactive method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI576825B (en) | A voice recognition system of a robot system ?????????????????????????????? and method thereof | |
| WO2017012511A1 (en) | Voice control method and device, and projector apparatus | |
| CN113327609B (en) | Method and apparatus for speech recognition | |
| CN110689877A (en) | Voice end point detection method and device | |
| CN108766441A (en) | A kind of sound control method and device based on offline Application on Voiceprint Recognition and speech recognition | |
| CN104575504A (en) | Method for personalized television voice wake-up by voiceprint and voice identification | |
| CN105261356A (en) | Voice recognition system and method | |
| CN105788596A (en) | Speech recognition television control method and system | |
| CN108595406B (en) | User state reminding method and device, electronic equipment and storage medium | |
| CN112420044A (en) | Voice recognition method, voice recognition device and electronic equipment | |
| CN105700359A (en) | Method and system for controlling smart home through speech recognition | |
| CN109074809B (en) | Information processing apparatus, information processing method, and computer-readable storage medium | |
| CN113593565B (en) | Intelligent home device management and control method and system | |
| CN110223672B (en) | Offline multi-language voice recognition method | |
| CN111179903A (en) | Voice recognition method and device, storage medium and electric appliance | |
| CN109767767A (en) | A kind of voice interactive method, system, electronic equipment and storage medium | |
| CN114708869A (en) | Voice interaction method and device and electric appliance | |
| CN111477226B (en) | Control method, intelligent device and storage medium | |
| CN112309396A (en) | AI virtual robot state dynamic setting system | |
| CN112420053A (en) | Intelligent interactive man-machine conversation system | |
| CN110674482B (en) | Multi-scene application computer | |
| CN110600009A (en) | Intelligent voice interaction operation platform and interaction method | |
| CN111161735A (en) | Voice editing method and device | |
| CN113992468A (en) | Smart home voice control method | |
| CN114121022A (en) | Voice wake-up method and device, electronic equipment and storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191220 |
|
| WD01 | Invention patent application deemed withdrawn after publication |