Word-Error Correction of Continuous Speech Recognition Based on Normalized Relevance Distance

Fusayasu, Yohei; Tanaka, Katsuyuki; Takiguchi, Tetsuya; Ariki, Yasuo

Word-Error Correction of Continuous Speech Recognition Based on Normalized Relevance Distance

Yohei Fusayasu, Katsuyuki Tanaka, Tetsuya Takiguchi, Yasuo Ariki

Download BibTeX Cite

Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1257-1261.

Abstract

In spite of the recent advancements being made in speech recognition, recognition errors are unavoidable in continuous speech recognition. In this paper, we focus on a word-error correction system for continuous speech recognition using confusion networks.Conventional N-gram correction is widely used; however, the performance degrades due to the fact that the N-gram approach cannot measure information between long distance words. In order to improve the performance of the N-gram model, we employ Normalized Relevance Distance (NRD) as a measure for semantic similarity between words. NRD can identify not only co-occurrence but also the correlation of importance of the terms in documents. Even if the words are located far from each other, NRD can estimate the semantic similarity between the words. The effectiveness of our method was evaluated in continuous speech recognition tasks for multiple test speakers. Experimental results show that our error-correction method is the most effective approach as compared to the methods using other features.

Yohei Fusayasu, Katsuyuki Tanaka, Tetsuya Takiguchi, and Yasuo Ariki. 2015. Word-Error Correction of Continuous Speech Recognition Based on Normalized Relevance Distance. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15. IJCAI, 1257–1261. https://ijcai.org/proceedings/2015/181

@inproceedings{ijcai2015p181,
  title     = {Word-Error Correction of Continuous Speech Recognition Based on Normalized Relevance Distance},
  author    = {Fusayasu, Yohei and Tanaka, Katsuyuki and Takiguchi, Tetsuya and Ariki, Yasuo},
  booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-15}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Qiang Yang and Michael Wooldridge},
  pages     = {1257--1261},
  year      = {2015},
  month     = {7},
  note      = {Main Track},
  url       = {https://ijcai.org/proceedings/2015/181},
}

TY  - CPAPER
TI  - Word-Error Correction of Continuous Speech Recognition Based on Normalized Relevance Distance
AU  - Fusayasu, Yohei
AU  - Tanaka, Katsuyuki
AU  - Takiguchi, Tetsuya
AU  - Ariki, Yasuo
T2  - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2015
SP  - 1257
EP  - 1261
UR  - https://ijcai.org/proceedings/2015/181
ER  -