CN110782895A - Man-machine voice system based on artificial intelligence - Google Patents
Man-machine voice system based on artificial intelligence Download PDFInfo
- Publication number
- CN110782895A CN110782895A CN201911067373.XA CN201911067373A CN110782895A CN 110782895 A CN110782895 A CN 110782895A CN 201911067373 A CN201911067373 A CN 201911067373A CN 110782895 A CN110782895 A CN 110782895A
- Authority
- CN
- China
- Prior art keywords
- module
- electrically connected
- sentence
- voice
- searching
- 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- Withdrawn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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000006243 chemical reaction Methods 0.000 claims abstract description 16
- 241000282414 Homo sapiens Species 0.000 description 5
- 239000002131 composite material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008451 emotion Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Images
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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L13/00—Speech synthesis; Text to speech 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
- G10L13/0335—Pitch control
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/04—Details of speech synthesis systems, e.g. synthesiser structure or memory management
- G10L13/047—Architecture of speech synthesisers
-
- 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
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
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)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a man-machine voice system based on artificial intelligence, which comprises a receiving unit, the receiving unit is electrically connected with a splitting module which splits the received conversation into sentences, the unpacking module is electrically connected with a tone analysis module, a context analysis module and a sentence pattern analysis module, the intonation analysis module, the context analysis module and the sentence pattern analysis module are electrically connected with a sentence combination module, the sentence combination module is electrically connected with a voice conversion module which is electrically connected with a controller, the controller is electrically connected with a processing unit, a character database, a character searching module, a character combination module and a character conversion module, the character database is electrically connected with the character searching module, and the character searching module is electrically connected with the character combination module. The invention can enhance the analysis of the tone, the context and the sentence pattern of the voice and enhance the understanding of the voice content.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a man-machine voice system based on artificial intelligence.
Background
Artificial intelligence is a new technical science for researching and developing theories, methods, techniques and application systems for simulating, extending and expanding human intelligence, which is also called intelligent machinery and machine intelligence and refers to the intelligence expressed by machines manufactured by human beings. Artificial intelligence generally refers to techniques for presenting human intelligence through ordinary computer programs. Through the progress of medicine, neuroscience, robotics, statistics and the like.
In the field of artificial intelligence, human power is saved by carrying out human-computer conversation to liberate people, and the human-computer conversation is often used in occasions of customer service, but the existing human-computer voice system only simply converts human language into characters to understand the superficial literal meaning when carrying out human-computer conversation, does not understand the context, intonation and language expression of the speech of people, and under different contexts, intonation and language expressions, even if the voices with the same content are different, the meanings of the conversant cannot be fully understood when carrying out human-computer conversation, and the situation of understanding errors is easily caused.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a man-machine voice system based on artificial intelligence.
In order to achieve the purpose, the invention adopts the following technical scheme:
a man-machine voice system based on artificial intelligence is designed, comprising a receiving unit, wherein the receiving unit is electrically connected with a splitting module, the splitting module splits received conversation into sentences, the unpacking module is electrically connected with a tone analysis module, a context analysis module and a sentence pattern analysis module, the tone analysis module, the context analysis module and the sentence pattern analysis module are electrically connected with a sentence combination module, the sentence combination module recovers the split conversation into sentences, the sentence combination module is electrically connected with a voice conversion module, the voice conversion module converts voice into characters, the voice conversion module is electrically connected with a controller, the controller is electrically connected with a processing unit, a character database, a character searching module, a character combination module and a character conversion module, the character database is electrically connected with the character searching module and searches for the characters through the character searching module, the word searching module is electrically connected with a word combination module, the word combination module is used for combining words and sentences of the words searched by the word searching module, the word combination module is electrically connected with the voice output unit, and the controller is electrically connected with the intonation analyzing module, the context analyzing module, the sentence pattern analyzing module and the sentence combination module.
Preferably, the receiving unit includes a voice receiving module, the voice receiving module is electrically connected to a storage module, the storage module is electrically connected to a voice recognition module, the voice is stored through the storage module, and the voice recognition module recognizes the type of the language.
Preferably, the speech recognition module includes microprocessor, microprocessor and split module electric connection, microprocessor electric connection has language searching module, language database, language searching module and language database electric connection, and language searching module looks for the pronunciation received, language database electric connection has the input module.
Preferably, the recording module is a recording pen or a recorder.
Preferably, the voice output unit comprises a microcontroller, and the microcontroller is electrically connected with a volume adjusting module, a tone adjusting module and an audio adjusting module.
Preferably, the processing unit includes a sentence database, the sentence database is electrically connected with a sentence searching module, the sentence searching module is electrically connected with a comparison module, the comparison module is electrically connected with a semantic understanding module, the comparison module, the sentence searching module, the sentence database and the controller are electrically connected, an input sentence is searched in the sentence database through the sentence searching module, the comparison module is used for comparing and finding out a sentence close to the input sentence, and then the sentence is interpreted by the semantic understanding module.
Preferably, the sentence searching module comprises a keyword searching module and a keyword sentence searching module.
The man-machine voice system based on artificial intelligence provided by the invention has the beneficial effects that: the dialect analysis module, the context analysis module and the sentence pattern analysis module are used for analyzing the dialect, the speaking context and the speaking sentence pattern of the speaker, so that the meaning of the dialog person to be expressed is fully analyzed and understood, the corresponding question and answer are made, meanwhile, the voice is output through the voice output unit, the emotion of the language output is increased, and the comfort level of the dialog is facilitated.
Drawings
FIG. 1 is a block diagram of a human-computer speech system based on artificial intelligence according to the present invention;
FIG. 2 is a block diagram of a human-machine speech system receiving unit based on artificial intelligence according to the present invention;
FIG. 3 is a block diagram of a human-machine speech system speech output unit based on artificial intelligence according to the present invention;
FIG. 4 is a block diagram of a processing unit of an artificial intelligence based human-machine speech system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1-4, a man-machine voice system based on artificial intelligence comprises a receiving unit, wherein the receiving unit is electrically connected with a splitting module, the splitting module splits a received conversation into sentences, the splitting module is electrically connected with a tone analysis module, a context analysis module and a sentence pattern analysis module, a paragraph of the conversation is split into sentences through the splitting module so as to analyze each sentence, even if voices with the same content have different meanings under different contexts, tones and languages, the tone analysis module is convenient to analyze the tones of the conversation so as to be beneficial to judging the emotion of the conversation, the context of the conversation is analyzed through the context analysis module so as to be beneficial to understanding the content of the conversation, and the tone analysis module is matched with the sentence pattern analysis module so as to analyze the sentence patterns, it is useful to understand the potential meaning of the speech content.
Intonation analysis module, context analysis module, sentence pattern analysis module electric connection have sentence composite module, and sentence composite module restores the split sentence dialogue, sentence composite module electric connection has the speech conversion module, and the speech conversion module converts speech into characters, speech conversion module electric connection has the controller, makes up the split sentence dialogue through sentence composite module to resume the content of dialogue, be convenient for convert the characters to it through the speech conversion module, thereby carry out the understanding of literal meaning to it.
The controller is electrically connected with the processing unit, the character database, the character searching module, the character combination module and the character conversion module, the character database is electrically connected with the character searching module, characters are searched by the character searching module, the character searching module is electrically connected with the character combination module, the character combination module is used for combining characters searched by the character searching module into sentences, the character combination module is electrically connected with the voice output unit, the controller is electrically connected with the tone analysis module, the context analysis module, the sentence analysis module and the sentence combination module, input voice is converted into characters, the processing unit processes and understands the characters, then the character searching module searches in the character database, the character combination module is used for combining the characters to combine the characters into a sentence of characters or a section of document character, then the text conversion module converts the text into voice, and the voice is output by the voice output unit.
The receiving unit comprises a voice receiving module, the voice receiving module is electrically connected with a storage module, the storage module is electrically connected with a voice recognition module, voice is stored through the storage module, the voice recognition module recognizes the type of language, the voice is received through the voice receiving module, then the storage module stores the voice, the voice recognition module recognizes the voice, and the type of language spoken by an interlocutor is judged.
The speech recognition module comprises a microprocessor, the microprocessor is electrically connected with the splitting module, the microprocessor is electrically connected with a language searching module and a language database, the language searching module is electrically connected with the language database, the language searching module searches the received speech, the language database is electrically connected with a recording module, the recording module is specifically a recording pen or a recorder, the language searching module searches the received speech in the language database for the language matched with the speech, so that the language type spoken by the speaker is judged, the variety of conversational languages is increased, the voice recognition module is convenient for people with different languages to use, and the design of the recording module is convenient for updating the language of the language database.
The pronunciation output unit includes microcontroller, microcontroller electric connection has volume control module, tone adjusting module, audio frequency adjusting module, be convenient for adjust the language volume of output through volume control module, the design of tone adjusting module is convenient for adjust the tone of output pronunciation, the emotion of output pronunciation has been increased, the design of tone adjusting module, be convenient for adjust the tone of output module, be favorable to increasing the comfort level when conversing, through audio frequency adjusting module, be convenient for adjust the frequency of output pronunciation, prevent the condition of high frequency and low frequency, cause the condition of dazzling or husky.
The processing unit comprises a sentence database, the sentence database is electrically connected with a sentence searching module, the sentence searching module is electrically connected with a comparison module, the comparison module is electrically connected with a semantic understanding module, the comparison module, the sentence searching module and the sentence database are electrically connected with a controller, an input sentence is searched in the sentence database through the sentence searching module, the comparison module is used for comparing and searching out a sentence which is close to the input sentence, then the sentence is interpreted by the semantic understanding module, the sentence searching module comprises a keyword searching module and a key sentence searching module, the same and close sentences are searched in the sentence database through the sentence searching module, then the sentences with high similarity are selected through comparison by the comparison module, and then the sentences are understood by the semantic understanding module, therefore, the surface meaning of the characters is understood, and the keywords searching module and the key sentence searching module are convenient for searching sentences similar to the sentences, so that the searching speed is accelerated.
When in work: the speech is received by the receiving unit and judged by the language, the paragraph of the dialogue is split into sentences by the splitting module, the intonation of the speaker is conveniently analyzed by the tone analysis module, the context of the dialogue is analyzed by the context analysis module and is matched with the sentence analysis module at the same time, the sentence patterns are analyzed, the comprehension of the speech content is facilitated, the words are combined by the word combination module and are combined into a sentence of words or a section of file words, the sentence of words is converted into the speech by the word conversion module and is output by the speech output unit, the output linguistic quantity is adjusted by the volume adjustment module, the tone of the output speech is adjusted by the design of the tone adjustment module, the tone of the output speech is adjusted by the tone adjustment module, the tone color of the output module is adjusted by the tone color adjustment module, so that the emotion of the output language is increased, and the cold machine language is avoided, the comfort of the conversation is increased.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (7)
1. A man-machine voice system based on artificial intelligence comprises a receiving unit and is characterized in that the receiving unit is electrically connected with a splitting module which splits received conversation into sentences, the unpacking module is electrically connected with a tone analysis module, a context analysis module and a sentence pattern analysis module which are electrically connected with a sentence combination module which restores the split conversation into sentences, the sentence combination module is electrically connected with a voice conversion module which converts voice into characters, the voice conversion module is electrically connected with a controller which is electrically connected with a processing unit, a character database, a character searching module, a character combination module and a character conversion module, and the character database is electrically connected with the character searching module, the words are searched through the word searching module, the word searching module is electrically connected with the word combination module, the words searched by the word searching module are combined into words and sentences through the word combination module, the word combination module is electrically connected with the voice output unit, and the controller is electrically connected with the tone analysis module, the context analysis module, the sentence pattern analysis module and the sentence combination module.
2. The human-computer voice system based on artificial intelligence of claim 1, wherein the receiving unit comprises a voice receiving module electrically connected with a storage module, the storage module is electrically connected with a voice recognition module, the voice is stored through the storage module, and the voice recognition module recognizes the type of the language.
3. The human-computer voice system based on artificial intelligence of claim 2, wherein the voice recognition module comprises a microprocessor, the microprocessor is electrically connected with the splitting module, the microprocessor is electrically connected with a language searching module and a language database, the language searching module is electrically connected with the language database, the language searching module searches the received voice, and the language database is electrically connected with the entering module.
4. The human-computer voice system based on artificial intelligence of claim 3, wherein the recording module is a recording pen or a recorder.
5. The human-computer voice system based on artificial intelligence of claim 1, wherein the voice output unit comprises a microcontroller, and the microcontroller is electrically connected with a volume adjusting module, a tone adjusting module, and an audio adjusting module.
6. The human-computer voice system based on artificial intelligence of claim 1, wherein the processing unit comprises a sentence database, the sentence database is electrically connected with a sentence searching module, the sentence searching module is electrically connected with a comparison module, the comparison module is electrically connected with a semantic understanding module, the comparison module, the sentence searching module and the sentence database are electrically connected with a controller, an input sentence is searched in the sentence database through the sentence searching module, the comparison module is used for comparing and finding out a sentence close to the input sentence, and the sentence is interpreted by the semantic understanding module.
7. The human-computer voice system based on artificial intelligence of claim 6, wherein the sentence searching module comprises a keyword searching module and a keyword sentence searching module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911067373.XA CN110782895A (en) | 2019-11-04 | 2019-11-04 | Man-machine voice system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911067373.XA CN110782895A (en) | 2019-11-04 | 2019-11-04 | Man-machine voice system based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110782895A true CN110782895A (en) | 2020-02-11 |
Family
ID=69389158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911067373.XA Withdrawn CN110782895A (en) | 2019-11-04 | 2019-11-04 | Man-machine voice system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110782895A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111754977A (en) * | 2020-06-16 | 2020-10-09 | 普强信息技术(北京)有限公司 | Voice real-time synthesis system based on Internet |
-
2019
- 2019-11-04 CN CN201911067373.XA patent/CN110782895A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111754977A (en) * | 2020-06-16 | 2020-10-09 | 普强信息技术(北京)有限公司 | Voice real-time synthesis system based on Internet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10108606B2 (en) | Automatic interpretation system and method for generating synthetic sound having characteristics similar to those of original speaker's voice | |
US10140973B1 (en) | Text-to-speech processing using previously speech processed data | |
Echols | A role for stress in early speech segmentation | |
US10672391B2 (en) | Improving automatic speech recognition of multilingual named entities | |
US8352260B2 (en) | Multimodal unification of articulation for device interfacing | |
CN106486121B (en) | Voice optimization method and device applied to intelligent robot | |
CN110689877A (en) | Voice end point detection method and device | |
DE69922971D1 (en) | NETWORK-INTERACTIVE USER INTERFACE USING LANGUAGE RECOGNITION AND PROCESSING NATURAL LANGUAGE | |
Yu | Research on speech recognition technology and its application | |
KR20030085075A (en) | Speech-to-Speech Generation System and Method | |
CA2718564A1 (en) | Systems and methods of improving automated speech recognition accuracy using statistical analysis of search terms | |
EP0767950B1 (en) | Method and device for adapting a speech recognition equipment for dialectal variations in a language | |
CN114330371A (en) | Session intention identification method and device based on prompt learning and electronic equipment | |
CN110852075A (en) | Voice transcription method and device for automatically adding punctuation marks and readable storage medium | |
CN111933116B (en) | Speech recognition model training method, system, mobile terminal and storage medium | |
CN110782895A (en) | Man-machine voice system based on artificial intelligence | |
Price et al. | Combining linguistic with statistical methods in modeling prosody | |
CN111949778A (en) | Intelligent voice conversation method and device based on user emotion and electronic equipment | |
JP2004271895A (en) | Multilingual speech recognition system and pronunciation learning system | |
CN115019787A (en) | Interactive homophonic and heteronym word disambiguation method, system, electronic equipment and storage medium | |
Chakraborty et al. | Spontaneous speech emotion recognition using prior knowledge | |
KR20050101695A (en) | A system for statistical speech recognition using recognition results, and method thereof | |
CN113053358A (en) | Voice recognition customer service system for regional dialects | |
Abudubiyaz et al. | The acoustical and language modeling issues on Uyghur speech recognition | |
CN113515952B (en) | Combined modeling method, system and equipment for Mongolian dialogue model |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200211 |