Research on Scheduling Speech Intelligent Recognition Based on Language Model

Du Fan, Zhang Min, Shan Zuzhi, Yang Zaihe

Integrated Circuits and Embedded Systems ›› 2022, Vol. 22 ›› Issue (2) : 55-59.

Integrated Circuits and Embedded Systems ›› 2022, Vol. 22 ›› Issue (2) : 55-59.
TECHNOLOGY REVIEW

Research on Scheduling Speech Intelligent Recognition Based on Language Model

  • Du Fan, Zhang Min, Shan Zuzhi, Yang Zaihe
Author information +
History +

Abstract

Aiming at the problem of poor accuracy of word graph generated by single pass decoding word graph generation algorithm in the process of scheduling speech recognition, a scheduling speech intelligent recognition method based on language model is studied.A scheduling speech intelligent recognition model composed of training process and recognition process is constructed.In the training process, the model extracts the speech vector sequence of speech data to construct the phonological sub model, and uses the language sub model to train the text data to construct the speech word map.In the recognition process, the phonological sub model, speech word map and pronunciation dictionary are decoded and searched to obtain the optimal word sequence.Scheduling speech intelligent recognition is completed based on the optimal word sequence.The test results show that the word graph generated by the research method has high accuracy and can accurately recognize the scheduling speech.

Key words

language model / speech recognition / speech decoding / word map generation

Cite this article

Download Citations
Du Fan, Zhang Min, Shan Zuzhi, Yang Zaihe. Research on Scheduling Speech Intelligent Recognition Based on Language Model[J]. Integrated Circuits and Embedded Systems. 2022, 22(2): 55-59

References

[1] 蔡新雷, 齐颖.基于人工智能的电网调度操作智能防误系统建设及实践[J].电力大数据, 2020, 23(4):1623.
[2] 李舟军, 范宇, 吴贤杰.面向自然语言处理的预训练技术研究综述[J].计算机科学, 2020, 47(3):162173.
[3] 窦建中, 罗深增, 金勇, 等.基于深度神经网络的电力调度语音识别研究及应用[J].湖北电力, 2019, 43(3):1622.
[4] 于重重, 陈运兵, 孙沁瑶, 等.基于动态BLSTM和CTC的濒危语言语音识别研究[J].计算机应用研究, 2019, 36(11):33343337.
[5] 鄢发齐, 王春明, 窦建中, 等.基于隐马尔可夫模型的电力调度语音识别研究[J].武汉大学学报(工学版), 2018, 51(10):920923.
[6] 姜芃旭, 傅洪亮, 陶华伟, 等.一种基于卷积神经网络特征表征的语音情感识别方法[J].电子器件, 2019, 42(4):9981001.
[7] 侯勇, 王铮, 舒乔晔, 等.一种防范电网调度员语音失误的语音辅助系统[J].微型电脑应用, 2019, 35(12):1922.
[8] 龙艳花, 茅红伟, 叶宏.电视剧语音识别中的半监督自动语音分割算法[J].数据采集与处理, 2019, 34(2):281287.
[9] 张佳宁, 严冬梅, 王勇.基于word2vec的语音识别后文本纠错[J].计算机工程与设计, 2020, 407(11):243248.
[10] 杨维, 张才俊, 马永波.一种语音识别中核心词快速模型优化方法[J].电子技术应用, 2019, 45(2):911.
[11] 朱向前.基于混合注意力机制和CTC语音识别模型技术研究[J].电视技术, 2019, 529(22):811, 22.
[12] 张瑞珍, 韩跃平, 张晓通.基于深度LSTM的端到端的语音识别[J].中北大学学报(自然科学版), 2020, 191(3):5862.
[13] 彭其渊, 胡雨欣, 鲁工圆.基于预警文本信息的调度命令智能生成模型[J].同济大学学报(自然科学版), 2020, 48(9):9299, 127.
[14] 杨德举, 马良荔, 谭琳珊, 等.基于门控卷积网络与CTC的端到端语音识别[J].计算机工程与设计, 2020, 405(9):258262.
[15] 缪裕青, 邹巍, 刘同来, 等.基于参数迁移和卷积循环神经网络的语音情感识别[J].计算机工程与应用, 2019, 929(10):140145, 203.

Accesses

Citation

Detail

Sections
Recommended

/