Location-Based End-to-End Speech Recognition with Multiple Language Models

Zhijie Lin, Kaiyang Lin, Shiling Chen, Linlin Li, Zhou Zhao

AAAI 2019 pp. 9975-9976

doi:10.1609/AAAI.V33I01.33019975 /aaai/2019/lin2019aaai-location/

Abstract

End-to-End deep learning approaches for Automatic Speech Recognition (ASR) has been a new trend. In those approaches, starting active in many areas, language model can be considered as an important and effective method for semantic error correction. Many existing systems use one language model. In this paper, however, multiple language models (LMs) are applied into decoding. One LM is used for selecting appropriate answers and others, considering both context and grammar, for further decision. Experiment on a general location-based dataset show the effectiveness of our method.

PDF AAAI Semantic Scholar

Cite

Text

Lin et al. "Location-Based End-to-End Speech Recognition with Multiple Language Models." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019975

Markdown

[Lin et al. "Location-Based End-to-End Speech Recognition with Multiple Language Models." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/lin2019aaai-location/) doi:10.1609/AAAI.V33I01.33019975

BibTeX

@inproceedings{lin2019aaai-location,
  title     = {{Location-Based End-to-End Speech Recognition with Multiple Language Models}},
  author    = {Lin, Zhijie and Lin, Kaiyang and Chen, Shiling and Li, Linlin and Zhao, Zhou},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9975-9976},
  doi       = {10.1609/AAAI.V33I01.33019975},
  url       = {https://mlanthology.org/aaai/2019/lin2019aaai-location/}
}