Presentation 2022-06-17
A Study of Speech Recognition Result Correction Using BERT for Speech Translation
Tadashi Ogura, Masakiyo Fujimoto, Peng Shen, Xugang Lu, Hisashi Kawai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Speech translation (ST) technology consists of automatic speech recognition (ASR) and machine translation technologies. Since ASR is the first module to be processed in ST, improving ASR performance is a critical factor in ST. However, it is difficult to solve this problem by pursuing only improvement of ASR performance, and error correction processing for ASR results is strongly required. Therefore, in this paper, we propose an error correction method for ASR results to improve ST performance using the state-of-the-art huge scale language model, BERT. The proposed method realizes context-aware error correction for ASR results, and successfully improves the accuracy of ST by reducing misunderstandings of “meaning" and "intention" of utterances.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) BERT / Spech Translation / Error Correction
Paper # SP2022-4
Date of Issue 2022-06-10 (SP)

Conference Information
Committee SP / IPSJ-MUS / IPSJ-SLP
Conference Date 2022/6/17(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tomoki Toda(Nagoya Univ.)
Vice Chair
Secretary (NTT) / (Univ. of Electro-Comm.)
Assistant Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Speech / Special Interest Group on Music and Computer / Special Interest Group on Spoken Language Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Speech Recognition Result Correction Using BERT for Speech Translation
Sub Title (in English)
Keyword(1) BERT
Keyword(2) Spech Translation
Keyword(3) Error Correction
1st Author's Name Tadashi Ogura
1st Author's Affiliation National Institute of Information and Communications Technology(NICT)
2nd Author's Name Masakiyo Fujimoto
2nd Author's Affiliation National Institute of Information and Communications Technology(NICT)
3rd Author's Name Peng Shen
3rd Author's Affiliation National Institute of Information and Communications Technology(NICT)
4th Author's Name Xugang Lu
4th Author's Affiliation National Institute of Information and Communications Technology(NICT)
5th Author's Name Hisashi Kawai
5th Author's Affiliation National Institute of Information and Communications Technology(NICT)
Date 2022-06-17
Paper # SP2022-4
Volume (vol) vol.122
Number (no) SP-81
Page pp.pp.10-13(SP),
#Pages 4
Date of Issue 2022-06-10 (SP)