CN116665674A - Internet intelligent recruitment publishing method based on voice and pre-training model - Google Patents
Internet intelligent recruitment publishing method based on voice and pre-training model Download PDFInfo
- Publication number
- CN116665674A CN116665674A CN202310651942.5A CN202310651942A CN116665674A CN 116665674 A CN116665674 A CN 116665674A CN 202310651942 A CN202310651942 A CN 202310651942A CN 116665674 A CN116665674 A CN 116665674A
- Authority
- CN
- China
- Prior art keywords
- recruitment
- voice
- information
- training model
- recruitment information
- 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
- 230000007115 recruitment Effects 0.000 title claims abstract description 131
- 238000012549 training Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000013598 vector Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000011282 treatment Methods 0.000 claims description 4
- 239000000969 carrier Substances 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001915 proofreading effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012795 verification 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
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses an Internet intelligent recruitment publishing method based on a voice and pre-training model, which comprises the following steps: s1, voice input, wherein a user provides recruitment information in a voice input mode, the recruitment information comprises position description and position requirements, S2, voice recognition is adopted, voice input recruitment information in S1 is converted into text data by adopting a voice recognition technology, S3, text data are processed, cleaned and analyzed, S4, the text data obtained in S3 are analyzed and understood by utilizing a pre-training model, S5, recruitment information is automatically generated based on a result obtained after analysis and understanding, and the recruitment information is published on the Internet; the recruitment information acquisition method and the recruitment information acquisition system improve the recruitment release efficiency through a voice input mode, improve the recruitment information quality by utilizing the semantic understanding and generating capacity of the pre-training model, combine voice input, voice recognition and the pre-training model, and improve user experience.
Description
Technical Field
The invention relates to a recruitment release method, in particular to an Internet intelligent recruitment release method based on a voice and pre-training model, and belongs to the field of Internet recruitment release.
Background
With the rapid development of the internet and the mature application of artificial intelligence technology, the recruitment industry is continuously exploring and utilizing new technology to improve the efficiency and accuracy of recruitment release. The conventional recruitment publishing method generally needs to manually write and edit recruitment information, which is time-consuming and is easy to cause inaccurate information. However, the recent rise of natural language processing and pre-training models provides new possibilities for solving these problems.
Natural language processing (NaturalLanguageProcessing, NLP) technology is one of the important research directions in the field of artificial intelligence, aimed at enabling computers to understand, process and generate human language. By utilizing the NLP technology, the computer can automatically process and analyze recruitment information, and the accuracy and reliability of the information are improved.
The pre-training model is a model which is trained based on a large-scale data set, and can automatically understand and generate texts by learning semantic and grammar rules of a large amount of text data. Recently, with the development of deep learning technology, pre-training models such as BERT (BidirectionalEncoderRepresentationsfrom Transformers) and GPT (generative pre-trainedsformer) have achieved remarkable results in the field of natural language processing. The models can learn rich language knowledge and context understanding capability through pre-training, and a powerful tool is provided for automatic recruitment release processing.
However, the current recruitment release method still has some problems, such as low information accuracy, large labor investment, low release efficiency, etc. Therefore, an internet intelligent recruitment release method based on voice and a pre-training model is needed to overcome the limitation of the traditional method and improve the efficiency and accuracy of recruitment release.
The Internet intelligent recruitment publishing method based on the voice and the pre-training model combines the voice input with the natural language processing technology, and automatically converts the voice into text data through the voice input and the recognition. And then, analyzing and understanding the text data by utilizing the pre-training model, and automatically generating accurate and complete recruitment information. The method not only improves the use experience and convenience of the user, but also greatly saves the time and the workload of manually writing and editing recruitment information, and improves the efficiency and the accuracy of recruitment release. Therefore, the Internet intelligent recruitment release method based on the voice and the pre-training model has important application value and innovation significance.
Disclosure of Invention
In order to solve the defects of the technology, the invention provides an Internet intelligent recruitment issuing method based on voice and a pre-training model
In order to solve the technical problems, the technical scheme adopted by the invention is that the method comprises the following steps:
s1, voice input, wherein a user provides recruitment information through a voice input mode,
the recruitment information comprises job descriptions and job requirements;
s2, voice recognition, namely converting recruitment information input by voice in the S1 into text data by adopting a voice recognition technology;
s3, processing the text, and processing and cleaning the text data;
s4, analyzing and understanding the text data obtained in the S3 by utilizing a pre-training model;
s5, recruitment information is automatically generated based on the result obtained after analysis and understanding, and the recruitment information is issued on the Internet.
Further, the voice input is implemented in a configuration form using a smart phone and a smart sound as carriers.
Further, speech recognition techniques, i.e. analyzing and converting speech information in a decoded audio signal into readable text data.
Further, the voice recognition technology comprises:
preprocessing, reducing interference, improving voice signal quality,
the method comprises removing noise and adjusting volume;
feature extraction, namely converting a voice signal into a feature vector;
an acoustic model modeling feature vectors of a speech signal using speech data;
a language model that corrects, complements, and predicts a next possible word or phrase for the text data based on the context information;
and decoding, and determining the most probable recognition result by utilizing a search algorithm.
Further, the text processing of S3 further includes removing redundant information and punctuation marks, and extracting and classifying keywords.
Further, the pre-training model extracts recruitment post information when analyzing and understanding the text data, wherein the recruitment post information at least comprises work types, salaries and places.
Further, the pre-training model is introduced into corpus training to learn language modes and language structures, and is characterized by comprising the following steps:
firstly, converting a text into a basic unit processed by an adaptive language model, and expressing the basic unit in a numeric form, wherein the numeric form is to convert the basic unit into an embedded vector;
secondly, resolving the meaning of each basic unit in the context, including performing attention operations and/or convolution operations on other basic units in the context, thereby capturing specific meaning and semantic relationships;
and finally, extracting the characteristics of the information extraction task.
Further, in S5, recruitment information is automatically generated based on the result obtained after analysis and understanding, specific content of the recruitment information is generated according to a predefined recruitment information template, the recruitment information template at least includes title, responsibility description, skill requirement, work place and salary treatment of the recruitment position, and the extracted key information is filled in the corresponding position of the recruitment information template, so that complete recruitment information is formed.
Further, the recruitment information is published to the recruitment channel, and the compliance of the presentation effect of the recruitment information is ensured in a mode of automatic typesetting and formatting function provision.
The invention discloses an Internet intelligent recruitment release method based on a voice and pre-training model, which has three technical effects:
1. the recruitment publishing efficiency is improved, the user can rapidly and accurately provide recruitment information through a voice input mode, and the complexity and time consumption of a traditional manual input mode are avoided. Meanwhile, the application of the pre-training model can automatically generate recruitment information, so that the workload of manual editing and proofreading is reduced, and the recruitment release efficiency is greatly improved;
2. the quality of recruitment information is improved, the semantic understanding and generating capacity of the pre-training model is utilized, the recruitment information can be accurately analyzed and processed by the system, key information is extracted from the recruitment information, and accurate and complete recruitment information is generated. The technical effect of the method improves the quality and accuracy of recruitment information and reduces errors and incompleteness in the information release process;
3. the user experience is improved, and the user can participate in the recruitment release process more intuitively and conveniently by the voice input mode, so that complicated keyboard input is not needed. In addition, the recruitment information generated automatically can be customized individually according to the user requirements, so that the satisfaction degree and the participation degree of the user are improved, and the user experience is further improved.
Drawings
FIG. 1 is a schematic diagram of an alternative architecture of the present invention.
FIG. 2 is a schematic diagram of an alternative flow scheme of the present invention.
FIG. 3 is an alternative structural schematic of the present invention.
FIG. 4 is a schematic diagram of an alternative speech input of the present invention.
Fig. 5 is a schematic diagram of an alternative issue acknowledgement of the present invention.
Detailed Description
The invention will be described in further detail with reference to the drawings and the detailed description.
The Internet intelligent recruitment publishing method based on the voice and the pre-training model comprises the following steps:
s1, voice input, wherein a user provides recruitment information through a voice input mode,
the recruitment information comprises job descriptions and job requirements;
s2, voice recognition, namely converting recruitment information input by voice in the S1 into text data by adopting a voice recognition technology;
s3, processing the text, and processing and cleaning the text data;
s4, analyzing and understanding the text data obtained in the S3 by utilizing a pre-training model;
s5, recruitment information is automatically generated based on the result obtained after analysis and understanding, and the recruitment information is issued on the Internet.
Preferably, the voice input is implemented in a configuration mode that a smart phone and a smart sound are used as carriers, specifically, a user is connected to a recruitment release system through the Internet, voice input options are selected on a recruitment information release page, then the user uses a microphone device or other voice input devices to provide recruitment information in a voice mode, so that the limitation of a traditional manual input mode is overcome by utilizing voice input, convenience and use experience of the user are improved, and the recruitment release process is more intelligent and efficient.
Speech recognition techniques, i.e. analyzing and converting speech information in a decoded audio signal into readable text data, include:
preprocessing, which aims at reducing interference and improving voice signal quality, wherein the preprocessing comprises noise removal and volume adjustment; feature extraction, which converts a voice signal into a feature vector so as to be understood and processed by a computer; an acoustic model modeling feature vectors of a speech signal using speech data; a language model that corrects, complements, and predicts the next possible word or phrase based on the context information, the prediction being calculated based on the impact rules and the probability model; and decoding, and determining the most probable recognition result by utilizing a search algorithm.
The text processing of S3 also comprises removing redundant information and punctuation marks, and extracting and classifying keywords.
And when the text data is analyzed and understood, the pre-training model extracts recruitment post information, wherein the recruitment post information at least comprises work seeds, salaries and places.
Preferably, the pre-training model is used for training a corpus, so as to learn a language mode and a language structure, and is characterized by comprising the following steps:
firstly, converting a text into a basic unit processed by an adaptive language model, and expressing the basic unit in a numeric form, wherein the numeric form converts the basic unit into an embedded vector, and the vector has a high latitude, and is continuously optimized in the training process so that similar basic units are closer in a vector space;
secondly, resolving the meaning of each basic unit in the context, including performing attention operations and/or convolution operations on other basic units in the context, thereby capturing specific meaning and semantic relationships;
finally, the information extraction task is subjected to feature extraction, and the process is designed to find a specific mode in a vector space or to classify and cluster by utilizing a pre-training model.
Needless to say, the pre-training model can help the front-end system to better understand the language content and the context, and accuracy and integrity of recruitment information are improved, so that texts are processed more effectively.
And S5, automatically generating recruitment information based on the result obtained after analysis and understanding, generating specific content of the recruitment information according to a predefined recruitment information template, wherein the recruitment information template at least comprises titles, responsibility descriptions, skill requirements, work places and salary treatments of the recruitment positions, and filling the extracted key information into corresponding positions of the recruitment information template so as to form complete recruitment information, thereby reducing editing burden of a user and improving consistency and accuracy of the information.
On the basis, the recruitment information is released to the recruitment channel, and the display effect compliance of the recruitment information is ensured in an automatic typesetting and formatting function providing mode, so that the intelligent and automatic release of the recruitment information is realized, manual copying and pasting to different recruitment websites or recruitment platforms are not needed, and the labor time cost is saved.
The present invention will be described in further detail with reference to examples.
Example 1
As shown in fig. 1, a user issues APP input voice to intelligent recruitment, the APP is parsed into text by integrating voice to text SDK, then the text is interacted with cloud service to obtain structured recruitment information, and the structured recruitment information is issued to an internet recruitment platform after confirmation.
Example two
As shown in fig. 2, after accessing the internet recruitment platform and logging in the personal account, the user selects a voice input option, presses a recording key, provides recruitment information through a microphone device, and if recording fails, the user can initiate a recording request again;
the voice recognition technology intervenes in converting the voice input of the user into recruitment information in a text form, and if the text conversion fails, the user can reinitiate recording and convert the text request;
using a pre-training model, for example: chatgpt, analyzing and understanding text content, extracting key information, for example: job title, job site, job experience requirements and payroll treatment, in the process, if the pre-training model cannot identify and extract the corresponding key information, the voice release request can be reinitiated;
based on the processing result of the pre-training model, the Internet recruitment platform automatically generates recruitment information, and in the process, if part of important key information, such as a work place, is lost after structuring, a user can be prompted to supplement part of the key information by voice;
then, the user checks the automatically generated recruitment information in the system, confirms the accuracy of the information, can modify the information according to the needs, and finally confirms the release of the recruitment information, and if the user cancels the release, the process is terminated;
the Internet recruitment platform automatically distributes the recruitment information which passes the verification to the Internet recruitment platform for the staff to browse and apply, and before the recruitment information is refused by the Internet recruitment platform, the user can be contacted to reissue the recruitment post.
According to the Internet intelligent recruitment release method based on the voice and the pre-training model, the efficiency of recruitment release is improved through a voice input mode, the quality of recruitment information is improved through semantic understanding and generating capacity of the pre-training model, the voice input, the voice recognition and the pre-training model are combined, and user experience is improved.
The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above examples, but is also intended to be limited to the following claims.
Claims (9)
1. The Internet intelligent recruitment publishing method based on the voice and the pre-training model is characterized by comprising the following steps of:
s1, voice input, wherein a user provides recruitment information through a voice input mode,
the recruitment information comprises job descriptions and job requirements;
s2, voice recognition, namely converting recruitment information input by voice in the S1 into text data by adopting a voice recognition technology;
s3, processing the text data, and cleaning the text data;
s4, analyzing and understanding the text data obtained in the S3 by utilizing a pre-training model;
s5, recruitment information is automatically generated based on the result obtained after analysis and understanding, and the recruitment information is issued on the Internet.
2. The internet intelligent recruitment publishing method based on the voice and the pre-training model of claim 1, wherein the method comprises the following steps: the voice input is implemented in a configuration form taking a smart phone and a smart sound as carriers.
3. The internet intelligent recruitment publishing method based on the voice and the pre-training model of claim 1, wherein the method comprises the following steps: the speech recognition technique, i.e. analyzing the speech information in the decoded audio signal and converting it into readable text data.
4. The internet intelligent recruitment distribution method based on the voice and the pre-training model of claim 3, wherein the voice recognition technology comprises:
preprocessing, reducing interference, improving voice signal quality,
the method comprises removing noise and adjusting volume;
feature extraction, namely converting a voice signal into a feature vector;
an acoustic model modeling feature vectors of a speech signal using speech data;
a language model that corrects, complements, and predicts a next possible word or phrase for the text data based on the context information;
and decoding, and determining the most probable recognition result by utilizing a search algorithm.
5. The internet intelligent recruitment publishing method based on the voice and the pre-training model of claim 1, wherein the method comprises the following steps: the text processing of S3 also comprises removing redundant information and punctuation marks, and extracting and classifying keywords.
6. The internet intelligent recruitment publishing method based on the voice and the pre-training model of claim 1, wherein the method comprises the following steps: and when the text data is analyzed and understood, the pre-training model extracts recruitment post information, wherein the recruitment post information at least comprises work types, salaries and places.
7. The internet intelligent recruitment publishing method based on voice and pre-training model according to claim 4 or 6, wherein the pre-training model introduces corpus training to learn language patterns and language structures, comprising the following steps:
firstly, converting text into basic units which are suitable for the language model processing, and expressing the basic units in a numerical form, wherein the numerical form is used for converting the basic units into embedded vectors;
secondly, resolving the meaning of each basic unit in the context, including performing attention operations and/or convolution operations on other basic units in the context, thereby capturing specific meaning and semantic relationships;
and finally, extracting the characteristics of the information extraction task.
8. The internet intelligent recruitment publishing method based on the voice and the pre-training model according to claim 1, wherein the recruitment information is automatically generated based on the result obtained after analysis and understanding in S5, which is characterized in that: and generating specific content of the recruitment information according to a predefined recruitment information template, wherein the recruitment information template at least comprises a title, a responsibility description, a skill requirement, a work place and a salary treatment of the recruitment position, and filling the extracted key information into the corresponding position of the recruitment information template so as to form complete recruitment information.
9. The internet intelligent recruitment publishing method based on the voice and the pre-training model of claim 8, wherein the method comprises the steps of: and publishing the recruitment information to a recruitment channel, and implementing a mode of automatic typesetting and formatting function providing to ensure that the presentation effect of the recruitment information is compliant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310651942.5A CN116665674A (en) | 2023-06-05 | 2023-06-05 | Internet intelligent recruitment publishing method based on voice and pre-training model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310651942.5A CN116665674A (en) | 2023-06-05 | 2023-06-05 | Internet intelligent recruitment publishing method based on voice and pre-training model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116665674A true CN116665674A (en) | 2023-08-29 |
Family
ID=87727497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310651942.5A Pending CN116665674A (en) | 2023-06-05 | 2023-06-05 | Internet intelligent recruitment publishing method based on voice and pre-training model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665674A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117495321A (en) * | 2023-11-03 | 2024-02-02 | 北京探也智能科技有限公司 | Self-help recruitment method and device based on large model |
-
2023
- 2023-06-05 CN CN202310651942.5A patent/CN116665674A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117495321A (en) * | 2023-11-03 | 2024-02-02 | 北京探也智能科技有限公司 | Self-help recruitment method and device based on large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717031B (en) | Intelligent conference summary generation method and system | |
| WO2019085779A1 (en) | Machine processing and text correction method and device, computing equipment and storage media | |
| CN114116994A (en) | Welcome robot dialogue method | |
| WO2021179910A1 (en) | Text voice front-end conversion method and apparatus, and device and storage medium | |
| CN111341305A (en) | Audio data labeling method, device and system | |
| CN109377981B (en) | Phoneme alignment method and device | |
| CN112466279B (en) | Automatic correction method and device for spoken English pronunciation | |
| JP6875819B2 (en) | Acoustic model input data normalization device and method, and voice recognition device | |
| CN115019776A (en) | Voice recognition model, training method thereof, voice recognition method and device | |
| CN110717341A (en) | Method and device for constructing old-Chinese bilingual corpus with Thai as pivot | |
| CN116665674A (en) | Internet intelligent recruitment publishing method based on voice and pre-training model | |
| CN114330371A (en) | Session intention identification method and device based on prompt learning and electronic equipment | |
| CN114120985A (en) | Pacifying interaction method, system and equipment of intelligent voice terminal and storage medium | |
| CN105869622B (en) | Chinese hot word detection method and device | |
| CN107424612A (en) | Processing method, device and machine readable media | |
| Bangalore et al. | Balancing data-driven and rule-based approaches in the context of a multimodal conversational system | |
| CN111339757A (en) | Error correction method for voice recognition result in collection scene | |
| CN115019787A (en) | Interactive homophonic and heteronym word disambiguation method, system, electronic equipment and storage medium | |
| CN111128181B (en) | Recitation question evaluating method, recitation question evaluating device and recitation question evaluating equipment | |
| Jing et al. | Acquisition of English Corpus Machine Translation Based on Speech Recognition Technology | |
| CN113362801A (en) | Audio synthesis method, system, device and storage medium based on Mel spectrum alignment | |
| CN116386637B (en) | Radar flight command voice instruction generation method and system | |
| CN113593584B (en) | Electronic product voice control system for restraining response time delay | |
| Tao | An intelligent voice interaction model based on mobile teaching environment | |
| CN110085212A (en) | A kind of audio recognition method for CNC program controller |
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 |