A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation

Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe

研究成果: Conference contribution

11 被引用数 (Scopus)

抄録

Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time applications, an increasing number of NAR models have been explored in different fields to mitigate the performance gap against AR models. In this work, we conduct a comparative study of various NAR modeling methods for end-to-end automatic speech recognition (ASR). Experiments are performed in the state-of-the-art setting using ESPnet. The results on various tasks provide interesting findings for developing an understanding of NAR ASR, such as the accuracy-speed trade-off and robustness against long-form utterances. We also show that the techniques can be combined for further improvement and applied to NAR end-to-end speech translation. All the implementations are publicly available to encourage further research in NAR speech processing.

本文言語English
ホスト出版物のタイトル2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ47-54
ページ数8
ISBN(電子版)9781665437394
DOI
出版ステータスPublished - 2021
外部発表はい
イベント2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Cartagena, Colombia
継続期間: 2021 12月 132021 12月 17

出版物シリーズ

名前2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings

Conference

Conference2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021
国/地域Colombia
CityCartagena
Period21/12/1321/12/17

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識
  • 信号処理
  • 言語学および言語

フィンガープリント

「A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル