CN113823269A - A method for automatic storage of power grid dispatch commands based on speech recognition - Google Patents
A method for automatic storage of power grid dispatch commands based on speech recognition Download PDFInfo
- Publication number
- CN113823269A CN113823269A CN202111044322.2A CN202111044322A CN113823269A CN 113823269 A CN113823269 A CN 113823269A CN 202111044322 A CN202111044322 A CN 202111044322A CN 113823269 A CN113823269 A CN 113823269A
- Authority
- CN
- China
- Prior art keywords
- phoneme
- command
- module
- phoneme label
- matching
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000009432 framing Methods 0.000 claims description 3
- 241000274965 Cyrestis thyodamas Species 0.000 claims 1
- 238000003672 processing method Methods 0.000 claims 1
- 238000004891 communication Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000012549 training 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
- G10L15/02—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
- G10L15/16—Speech classification or search using artificial neural networks
-
- 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
- G10L2015/025—Phonemes, fenemes or fenones being the recognition units
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)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了一种基于语音识别电网调度命令自动保存的方法，包括以下步骤：特征提取模块提取语音特征信号，并进行综合处理，将综合处理结果发送至神经网络模块；神经网络模块接收特征提取模块发送的综合处理结果，并进行识别，将识别结果发送至命令匹配模块；命令匹配模块接收神经网络模块发送的识别结果，并进行匹配，将匹配结果发送至调度命令记录模块；调度命令记录模块接收命令匹配模块发送的匹配结果，并进行保存。实现了自动将调度命令进行保存，减少调度人员手动记录调度命令的工作量。
The invention discloses a method for automatically saving power grid scheduling commands based on voice recognition, comprising the following steps: a feature extraction module extracts voice feature signals, performs comprehensive processing, and sends the comprehensive processing results to a neural network module; the neural network module receives feature extraction The comprehensive processing results sent by the module are identified, and the identification results are sent to the command matching module; the command matching module receives the identification results sent by the neural network module, performs matching, and sends the matching results to the scheduling command recording module; the scheduling command recording module Receive the matching result sent by the command matching module and save it. It realizes the automatic saving of scheduling commands, and reduces the workload of manual recording of scheduling commands by the scheduling personnel.
Description
Technical Field
The invention belongs to the technical field of voice recognition, and particularly relates to a method for automatically storing a power grid dispatching command based on voice recognition.
Background
With the continuous development of the application of the power industry in recent years, the complexity of the power grid structure is increasing day by day, and the power dispatching communication center is used as a neural center for the operation, management and control of the power grid, so that the power dispatching communication center bears an important responsibility for guaranteeing the safe operation of the power grid and is also a key factor for influencing the smooth operation of the power grid and the efficient optimal configuration of resources. However, although each link in the power system tends to be more and more intelligent and digital, the automation level and reliability thereof have been greatly improved, people still play an indispensable role in the power system. Because the existing power grid surpasses the traditional power grid in the aspects of equipment quantity, complexity and the like, the workload, the working complexity and the working pressure of dispatchers are increased gradually, and even dispatchers with good training and rich experience are likely to enter a fatigue state, so careless mistakes occur in the middle links with complicated processes. At present, telephone is often adopted for communication in the power grid dispatching work, manual recording is needed to be carried out in a log system after oral notification, and the telephone communication content is recorded and stored. The accuracy of the telephone information is affected due to the compact time of receiving and making telephone calls, the unsatisfactory field communication environment, dialect accents of dispatchers and field personnel and the like.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method for automatically storing a power grid dispatching command based on voice recognition, which realizes the automatic recognition of the dispatching command and the storage.
In order to achieve the purpose, the invention adopts the following technical scheme:
s101, a feature extraction module extracts voice feature signals, performs comprehensive processing, and sends a comprehensive processing result to a neural network module;
s102, the neural network module receives the comprehensive processing result sent by the feature extraction module, identifies the comprehensive processing result and sends the identification result to the command matching module;
s103, receiving the identification result sent by the neural network module by the command matching module, matching and sending the matching result to the scheduling command recording module;
s104, the scheduling command recording module receives and stores the matching result sent by the command matching module;
and S101 to S104, the command matching module matches the recognition result with the scheduling command phoneme label library and sends the matching result to the scheduling command recording module for storage.
Further, the feature extraction module performs comprehensive processing on the voice feature signal, and the comprehensive processing mode includes: pre-emphasis, framing, windowing and fast fourier transform; the feature extraction module carries out comprehensive processing on the voice feature signals to generate speech and speech pattern signals, and sends the speech and speech pattern signals to the neural network module.
Further, the neural network module receives the comprehensive processing result sent by the feature extraction module, and the neural network module identifies the language map.
Further, the neural network module identifies a first phoneme in the speech graph as a first phoneme label, a second phoneme as a second phoneme label, and a third phoneme as a third phoneme label … …; the neural network module identifies the first combination of phonemes as a first phoneme label sequence, the neural network module identifies the second combination of phonemes as a second phoneme label sequence, and the neural network module identifies the third combination of phonemes as a third phoneme label sequence … … the neural network module identifies the nth combination of phonemes as an nth phoneme label sequence.
Further, the first phoneme combination comprises a first phoneme, a second phoneme, a fourth phoneme and a fifth phoneme; the second phoneme combination comprises a second phoneme, a third phoneme, a fourth phoneme, a fifth phoneme and a sixth phoneme; the third phoneme combination comprises a fourth phoneme, a fifth phoneme and a sixth phoneme; the Nth phoneme comprises a first phoneme, a second phoneme and a third phoneme … … Nth phoneme; the first phoneme label sequence comprises a first phoneme label, a second phoneme label, a fourth phoneme label and a fifth phoneme label; the second phoneme label sequence comprises a second phoneme label, a third phoneme label, a fourth phoneme label, a fifth phoneme label and a sixth phoneme label; the third phoneme label sequence comprises a fourth phoneme label, a fifth phoneme label and a sixth phoneme label; the sequence of nth phoneme tags includes a first phoneme tag, a second phoneme tag, and a third phoneme tag … … nth phoneme tag.
Further, the command matching module adopts a dynamic time warping algorithm for matching.
Further, the command matching module matches the first phoneme label, the second phoneme label and the third phoneme label … … with the scheduling command phoneme label library.
Further, the scheduling command phoneme label library includes a scheduling command first phoneme label, a scheduling command second phoneme label, a scheduling command third phoneme label … … scheduling command nth phoneme label.
Further, the first phoneme label is successfully matched with the first phoneme label of the scheduling command, the command matching module sends the matching result of the first phoneme label of the scheduling command to the scheduling command recording module, the second phoneme label is successfully matched with the second phoneme label of the scheduling command, the command matching module sends the matching result of the second phoneme label of the scheduling command to the scheduling command recording module, the third phoneme label is successfully matched with the third phoneme label of the scheduling command, the command matching module sends the matching result of the third phoneme label of the scheduling command to the scheduling command recording module … …, the nth phoneme label is successfully matched with the nth phoneme label of the scheduling command, and the command matching module sends the matching result of the nth phoneme label of the scheduling command to the scheduling command recording module.
Further, the command matching module matches the first phoneme label sequence, the second phoneme label sequence, the third phoneme label sequence … … the nth phoneme label sequence with the scheduling command phoneme label library.
Further, the scheduling command phoneme label library further includes a scheduling command first phoneme label sequence, a scheduling command second phoneme label sequence, a scheduling command third phoneme label sequence … … scheduling command nth phoneme label sequence.
Further, the first phoneme label sequence is successfully matched with the first phoneme label sequence of the scheduling command, the command matching module sends a matching result of the first phoneme label sequence of the scheduling command to the scheduling command recording module, the second phoneme label sequence is successfully matched with the second phoneme label sequence of the scheduling command, the command matching module sends a matching result of the second phoneme label sequence of the scheduling command to the scheduling command recording module, the third phoneme label sequence is successfully matched with a third phoneme label sequence of the scheduling command, the command matching module sends the matching result of the third phoneme label sequence of the scheduling command to the scheduling command recording module … …, the nth phoneme label sequence is successfully matched with the nth phoneme label sequence of the scheduling command, and the command matching module sends the matching result of the nth phoneme label sequence of the scheduling command to the scheduling command recording module.
Further, the scheduling command recording module receives the matching result sent by the command matching module, and stores the scheduling command first phoneme label matching result, the scheduling command second phoneme label matching result, the scheduling command third phoneme label matching result … … and the scheduling command Nth phoneme label matching result; and the scheduling command recording module stores the matching result of the scheduling command first phoneme label sequence, the matching result of the scheduling command second phoneme label sequence and the matching result of the scheduling command third phoneme label sequence … ….
The invention has the beneficial effects that: a method for automatically storing a power grid dispatching command based on voice recognition is characterized in that a neural network module receives and recognizes a comprehensive processing result sent by a feature extraction module, the neural network module sends the recognition result to a command matching module, the command matching module matches the recognition result with a dispatching command phoneme label library and sends the matching result to a dispatching command recording module for storage, and the workload of dispatching personnel for manually recording the dispatching command is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic step diagram of a method for automatically saving a power grid dispatching command based on voice recognition according to the present invention.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The first embodiment is as follows:
s101, a feature extraction module extracts voice feature signals, performs comprehensive processing, and sends a comprehensive processing result to a neural network module;
the feature extraction module extracts the voice feature signal, the feature extraction module carries out comprehensive processing on the voice feature signal, and the comprehensive processing mode comprises the following steps: pre-emphasis, framing, windowing and fast fourier transform; the feature extraction module carries out comprehensive processing on the voice feature signals to generate speech and speech pattern signals, and sends the speech and speech pattern signals to the neural network module.
S102, the neural network module receives the comprehensive processing result sent by the feature extraction module, identifies the comprehensive processing result and sends the identification result to the command matching module;
the neural network module receives the comprehensive processing result sent by the feature extraction module, the neural network module identifies the speech pattern, the neural network module identifies a first phoneme in the speech pattern as a first phoneme label, a second phoneme in the speech pattern as a second phoneme label, and a third phoneme in the speech pattern as a third phoneme label … …; the neural network module recognizes the first phoneme combination as a first phoneme label sequence, the neural network module recognizes the second phoneme combination as a second phoneme label sequence, and the neural network module recognizes the third phoneme combination as a third phoneme label sequence … … the neural network module recognizes the nth phoneme combination as an nth phoneme label sequence; the first phoneme combination comprises a first phoneme, a second phoneme, a fourth phoneme and a fifth phoneme; the second phoneme combination comprises a second phoneme, a third phoneme, a fourth phoneme, a fifth phoneme and a sixth phoneme; the third phoneme combination comprises a fourth phoneme, a fifth phoneme and a sixth phoneme; the Nth phoneme comprises a first phoneme, a second phoneme and a third phoneme … … Nth phoneme; the first phoneme label sequence comprises a first phoneme label, a second phoneme label, a fourth phoneme label and a fifth phoneme label; the second phoneme label sequence comprises a second phoneme label, a third phoneme label, a fourth phoneme label, a fifth phoneme label and a sixth phoneme label; the third phoneme label sequence comprises a fourth phoneme label, a fifth phoneme label and a sixth phoneme label; the nth phoneme label sequence includes a first phoneme label, a second phoneme label, a third phoneme label … … nth phoneme label; and the neural network module sends the identification result to the command matching module.
S103, receiving the identification result sent by the neural network module by the command matching module, matching and sending the matching result to the scheduling command recording module;
the command matching module receives the recognition result sent by the neural network module, and the command matching module adopts a dynamic time warping algorithm for matching; the command matching module matches the first phoneme label, the second phoneme label and the third phoneme label … … with the scheduling command phoneme label library; scheduling command phoneme label library includes scheduling command first phoneme label, scheduling command second phoneme label, scheduling command third phoneme label … … scheduling command nth phoneme label; the first phoneme label is successfully matched with a first phoneme label of a scheduling command, the command matching module sends a matching result of the first phoneme label of the scheduling command to the scheduling command recording module, the second phoneme label is successfully matched with a second phoneme label of the scheduling command, the command matching module sends a matching result of the second phoneme label of the scheduling command to the scheduling command recording module, the third phoneme label is successfully matched with a third phoneme label of the scheduling command, the command matching module sends the matching result of the third phoneme label of the scheduling command to the scheduling command recording module … …, the Nth phoneme label is successfully matched with the Nth phoneme label of the scheduling command, and the command matching module sends the matching result of the Nth phoneme label of the scheduling command to the scheduling command recording module; the command matching module matches the first phoneme label sequence, the second phoneme label sequence and the third phoneme label sequence … … with a scheduling command phoneme label library; scheduling command phoneme label library further comprises a scheduling command first phoneme label sequence, a scheduling command second phoneme label sequence, a scheduling command third phoneme label sequence … … scheduling command Nth phoneme label sequence; the first phoneme label sequence is successfully matched with the first phoneme label sequence of the scheduling command, the command matching module sends a matching result of the first phoneme label sequence of the scheduling command to the scheduling command recording module, the second phoneme label sequence is successfully matched with the second phoneme label sequence of the scheduling command, the command matching module sends a matching result of the second phoneme label sequence of the scheduling command to the scheduling command recording module, the third phoneme label sequence is successfully matched with the third phoneme label sequence of the scheduling command, the command matching module sends a matching result of the third phoneme label sequence of the scheduling command to the scheduling command recording module … …, the Nth phoneme label sequence is successfully matched with the Nth phoneme label sequence of the scheduling command, and the command matching module sends a matching sequence result of the Nth phoneme label of the scheduling command to the scheduling command recording module.
S104, the scheduling command recording module receives and stores the matching result sent by the command matching module;
the scheduling command recording module receives the matching result sent by the command matching module, and stores a scheduling command first phoneme label matching result, a scheduling command second phoneme label matching result and a scheduling command third phoneme label matching result … …; and the scheduling command recording module stores the matching result of the scheduling command first phoneme label sequence, the matching result of the scheduling command second phoneme label sequence and the matching result of the scheduling command third phoneme label sequence … ….
In the description of the present invention, it should be noted that the terms "first", "second", "third", "fourth", "fifth", "sixth" and "nth" are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
The above description is for the purpose of illustrating embodiments of the invention and is not intended to limit the invention, and it will be apparent to those skilled in the art that any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention shall fall within the protection scope of the invention.
Claims (8)
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111044322.2A CN113823269A (en) | 2021-09-07 | 2021-09-07 | A method for automatic storage of power grid dispatch commands based on speech recognition |
| PCT/CN2022/115880 WO2023036014A1 (en) | 2021-09-07 | 2022-08-30 | Method for automatically saving power grid scheduling command on basis of voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111044322.2A CN113823269A (en) | 2021-09-07 | 2021-09-07 | A method for automatic storage of power grid dispatch commands based on speech recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113823269A true CN113823269A (en) | 2021-12-21 |
Family
ID=78922133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111044322.2A Pending CN113823269A (en) | 2021-09-07 | 2021-09-07 | A method for automatic storage of power grid dispatch commands based on speech recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113823269A (en) |
| WO (1) | WO2023036014A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023036014A1 (en) * | 2021-09-07 | 2023-03-16 | 广西电网有限责任公司贺州供电局 | Method for automatically saving power grid scheduling command on basis of voice recognition |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6177098A (en) * | 1984-09-06 | 1986-04-19 | ブリテイシユ・テレコミユニケーシヨンズ パブリツク・リミテツド・カンパニ | Audio information classification method and device |
| CN103077714A (en) * | 2013-01-29 | 2013-05-01 | 华为终端有限公司 | Information identification method and apparatus |
| WO2017154116A1 (en) * | 2016-03-08 | 2017-09-14 | 日本電気株式会社 | Power control device, power control system, power control method, and program |
| CN108805417A (en) * | 2018-05-22 | 2018-11-13 | 国网山东省电力公司济南供电公司 | A kind of implementation method and power scheduling instruction system of power scheduling instruction |
| CN109448707A (en) * | 2018-12-18 | 2019-03-08 | 北京嘉楠捷思信息技术有限公司 | Speech recognition method and device, device and medium |
| CN110473531A (en) * | 2019-09-05 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Audio recognition method, device, electronic equipment, system and storage medium |
| CN110807574A (en) * | 2019-10-09 | 2020-02-18 | 广州供电局有限公司 | Intelligent power dispatching method, device and system |
| CN112530434A (en) * | 2020-12-21 | 2021-03-19 | 云南电网有限责任公司玉溪供电局 | Automatic intelligent robot on duty scheduling system of power station |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107644638B (en) * | 2017-10-17 | 2019-01-04 | 北京智能管家科技有限公司 | Audio recognition method, device, terminal and computer readable storage medium |
| CN111402862B (en) * | 2020-02-28 | 2023-06-20 | 出门问问创新科技有限公司 | Speech recognition method, device, storage medium and equipment |
| CN111429915A (en) * | 2020-03-31 | 2020-07-17 | 国家电网有限公司华东分部 | A dispatch system and dispatch method based on speech recognition |
| CN111640453B (en) * | 2020-05-13 | 2023-06-16 | 广州国音智能科技有限公司 | Spectrogram matching method, device, equipment and computer-readable storage medium |
| CN112735410B (en) * | 2020-12-25 | 2024-06-07 | 中国人民解放军63892部队 | Automatic voice interactive force model control method and system |
| CN113096417A (en) * | 2021-04-06 | 2021-07-09 | 昭通亮风台信息科技有限公司 | Traffic signal lamp remote regulation and control method and system based on unmanned aerial vehicle and computer readable storage medium |
| CN113823269A (en) * | 2021-09-07 | 2021-12-21 | 广西电网有限责任公司贺州供电局 | A method for automatic storage of power grid dispatch commands based on speech recognition |
-
2021
- 2021-09-07 CN CN202111044322.2A patent/CN113823269A/en active Pending
-
2022
- 2022-08-30 WO PCT/CN2022/115880 patent/WO2023036014A1/en not_active Ceased
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6177098A (en) * | 1984-09-06 | 1986-04-19 | ブリテイシユ・テレコミユニケーシヨンズ パブリツク・リミテツド・カンパニ | Audio information classification method and device |
| CN103077714A (en) * | 2013-01-29 | 2013-05-01 | 华为终端有限公司 | Information identification method and apparatus |
| WO2017154116A1 (en) * | 2016-03-08 | 2017-09-14 | 日本電気株式会社 | Power control device, power control system, power control method, and program |
| CN108805417A (en) * | 2018-05-22 | 2018-11-13 | 国网山东省电力公司济南供电公司 | A kind of implementation method and power scheduling instruction system of power scheduling instruction |
| CN109448707A (en) * | 2018-12-18 | 2019-03-08 | 北京嘉楠捷思信息技术有限公司 | Speech recognition method and device, device and medium |
| CN110473531A (en) * | 2019-09-05 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Audio recognition method, device, electronic equipment, system and storage medium |
| CN110807574A (en) * | 2019-10-09 | 2020-02-18 | 广州供电局有限公司 | Intelligent power dispatching method, device and system |
| CN112530434A (en) * | 2020-12-21 | 2021-03-19 | 云南电网有限责任公司玉溪供电局 | Automatic intelligent robot on duty scheduling system of power station |
Non-Patent Citations (2)
| Title |
|---|
| 刘琨;金文标;: "基于脉冲耦合神经网络的孤立词语音识别研究", 重庆邮电大学学报(自然科学版), no. 02 * |
| 陈龙;杜江;伍仕红;宋弦;姚刚;: "基于指令执行时间预测的优化调度指挥网络交互系统", 电工技术, no. 07 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023036014A1 (en) * | 2021-09-07 | 2023-03-16 | 广西电网有限责任公司贺州供电局 | Method for automatically saving power grid scheduling command on basis of voice recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023036014A1 (en) | 2023-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10950241B2 (en) | Diarization using linguistic labeling with segmented and clustered diarized textual transcripts | |
| CN108766441B (en) | Voice control method and device based on offline voiceprint recognition and voice recognition | |
| CN113468296B (en) | Model self-iteration intelligent customer service quality inspection system and method with configurable business logic | |
| CN111312219B (en) | Telephone recording labeling method, system, storage medium and electronic equipment | |
| WO2021135534A1 (en) | Speech recognition-based dialogue management method, apparatus, device and medium | |
| CA2564760C (en) | Speech analysis using statistical learning | |
| CN112270922B (en) | Automatic filling method and device for scheduling log | |
| CN103811000A (en) | Voice recognition system and voice recognition method | |
| CN113948079B (en) | Human-computer interaction method for distribution network dispatching based on artificial intelligence speech recognition | |
| CN117713377A (en) | Dispatching automation main station intelligent voice joint debugging system | |
| CN111210821A (en) | Intelligent voice recognition system based on internet application | |
| CN113823269A (en) | A method for automatic storage of power grid dispatch commands based on speech recognition | |
| CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
| CN112530434A (en) | Automatic intelligent robot on duty scheduling system of power station | |
| CN114512123A (en) | Training method and device for VAD model, and voice endpoint detection method and device | |
| CN118609552A (en) | Power grid fault information extraction and processing method and system based on speech recognition | |
| CN114121022A (en) | Voice wake-up method and device, electronic equipment and storage medium | |
| CN111223489B (en) | Specific keyword identification method and system based on Attention mechanism | |
| CN115985315A (en) | Speaker labeling method, device, electronic equipment and storage medium | |
| CN114945058A (en) | Electric power inquiry system and method based on virtual agent | |
| CN114582328A (en) | Voice labeling system, method, terminal and storage medium | |
| CN112509582A (en) | Quality inspection method, system, equipment and storage medium for voice call | |
| CN114446307A (en) | Model training method, speech transcription method, system, device and storage medium | |
| CN110716523A (en) | Pump station intelligent decision system and method based on voice recognition | |
| CN110349576A (en) | Power system operation instruction executing method, apparatus and system based on speech recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211221 |
|
| RJ01 | Rejection of invention patent application after publication |