@inproceedings{f0cbf9d709454110858c456f918167aa,
title = "Chinese Dialect Speech Recognition Based on End-to-end Machine Learning",
abstract = "With the development of End-to-end neural network, End-to-end speech recognition has achieved comparable performance with traditional speech recognition methods. The End-to-end speech recognition model only needs the speech features of the input and the text information of the output. This paper takes advantage of the End-to-end method and uses the dataset provided by the Oriental Language Recognition Challenge to build a Chinese dialect recognition system for Sichuanese, Hokkien, Shanghainese and Cantonese. Dialect data belongs to low-resource languages. In this paper, in view of the lack of dialect data resources, a method of adding unrelated languages for joint training and adding Chinese language model for joint decoding is proposed for dialect speech recognition. The model has a relative improvement of 12% in Character Error Rate compared with the Baseline systerm.",
keywords = "Attention mechanism, Connectionist Temporal Classification, End-to-end, Speech Recognition, dialect",
author = "Fengrun Zhang and Xiang Xie and Xinyue Quan",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Machine Learning, Control, and Robotics, MLCR 2022 ; Conference date: 29-10-2022 Through 31-10-2022",
year = "2022",
doi = "10.1109/MLCR57210.2022.00012",
language = "English",
series = "Proceedings - 2022 International Conference on Machine Learning, Control, and Robotics, MLCR 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "14--18",
booktitle = "Proceedings - 2022 International Conference on Machine Learning, Control, and Robotics, MLCR 2022",
address = "United States",
}