Speech Recognition Model Inspired on Large Language Model for Smart Grid Dispatching

被引:0
|
作者
Na, Qionglan [1 ]
Yang, Yixi [2 ]
Su, Dan [1 ]
Li, Xin [1 ]
Wang, Yifei [1 ]
Chen, Zhongtao [1 ]
机构
[1] State Grid Jibei Informat & Telecommun Co, Beijing 100053, Peoples R China
[2] State Grid Informat & Telecommun Branch, Beijing 100761, Peoples R China
来源
PROCEEDINGS OF 2024 INTERNATIONAL CONFERENCE ON POWER ELECTRONICS AND ARTIFICIAL INTELLIGENCE, PEAI 2024 | 2024年
关键词
Grid; Speech recognition; Smart grid; Deep learning; FUTURE; CELLS;
D O I
10.1145/3674225.3674303
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years, large language models have gained popularity across various domains, with particular attention given to the impressive performance of their core component, the Transformer. This paper aims to enhance the accuracy of intelligent power grid dispatch speech recognition by leveraging deep learning techniques, specifically CNN and Transformer architectures. The proposed approach involves the creation of a specialized corpus tailored specifically for power dispatch speech recognition, focusing on power dispatch-specific terminology and regional grid dispatch language. The acoustic model training utilizes deep neural networks as the fundamental framework. Inspired by the success of Transformers in large language models, we incorporate Transformers as the language model to further enhance prediction performance. The practical results highlight the superiority of the Transformer-based power dispatch speech recognition compared to traditional speech recognition frameworks. With an impressive accuracy in power dispatch speech recognition, the developed system based on this approach has been successfully deployed and validated in a regional grid control center, affirming its feasibility and effectiveness.
引用
收藏
页码:439 / 442
页数:4
相关论文
共 50 条
  • [41] A unified language model architecture for web-based speech recognition grammars
    Holland, Wesley
    May, Daniel
    Baca, Julie
    Lazarou, Georgios
    Picone, Joseph
    2006 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, VOLS 1 AND 2, 2006, : 294 - +
  • [42] An End-to-End Chinese Speech Recognition Algorithm Integrating Language Model
    Lü, Kun-Ru
    Wu, Chun-Guo
    Liang, Yan-Chun
    Yuan, Yu-Ping
    Ren, Zhi-Min
    Zhou, You
    Shi, Xiao-Hu
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2021, 49 (11): : 2177 - 2185
  • [43] Dialogue speech recognition by combining hierarchical topic classification and language model switching
    Lane, IR
    Kawahara, T
    Matsui, T
    Nakamura, S
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2005, E88D (03): : 446 - 454
  • [44] Dynamic out-of-vocabulary word registration to language model for speech recognition
    Norihide Kitaoka
    Bohan Chen
    Yuya Obashi
    EURASIP Journal on Audio, Speech, and Music Processing, 2021
  • [45] PLSA ENHANCED WITH A LONG-DISTANCE BIGRAM LANGUAGE MODEL FOR SPEECH RECOGNITION
    Haidar, Md. Akmal
    O'Shaughnessy, Douglas
    2013 PROCEEDINGS OF THE 21ST EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2013,
  • [46] A Research on Construction of 30 Bus Large-scale Smart Grid Model
    Kainose, Sho
    Nagasaka, Ken
    2015 INTERNATIONAL CONFERENCE ON ADVANCED MECHATRONIC SYSTEMS (ICAMECHS), 2015, : 295 - 300
  • [47] RECURRENT NEURAL NETWORK LANGUAGE MODEL WITH STRUCTURED WORD EMBEDDINGS FOR SPEECH RECOGNITION
    He, Tianxing
    Xiang, Xu
    Qian, Yanmin
    Yu, Kai
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 5396 - 5400
  • [48] Model for Smart Appliances toward Smart Grid into Smart City
    Lazaroiu, George Cristian
    Roscia, Mariacristina
    2016 IEEE INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY RESEARCH AND APPLICATIONS (ICRERA), 2016, : 622 - 627
  • [49] Brownian traffic model for SMART GRID
    Fonseca, L. A.
    Sanchez, J. F.
    2014 IEEE CENTRAL AMERICA AND PANAMA CONVENTION (CONCAPAN XXXIV), 2014,
  • [50] A COMPARISON OF TECHNIQUES FOR LANGUAGE MODEL INTEGRATION IN ENCODER-DECODER SPEECH RECOGNITION
    Toshniwal, Shubham
    Kannan, Anjuli
    Chiu, Chung-Cheng
    Wu, Yonghui
    Sainath, Tara N.
    Livescu, Karen
    2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 369 - 375