Cycle-consistency Training for End-to-end Speech Recognition

Takaaki Hori, Ramon Astudillo, Tomoki Hayashi, Yu Zhang, Shinji Watanabe, Jonathan Le Roux

研究成果: Conference contribution

40 被引用数 (Scopus)

抄録

This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR systems, it still requires a large amount of paired data, i.e., speech utterances and their transcriptions. Cycle-consistency losses have been recently proposed as a way to mitigate the problem of limited paired data. These approaches compose a reverse operation with a given transformation, e.g., text-to-speech (TTS) with ASR, to build a loss that only requires unsupervised data, speech in this example. Applying cycle consistency to ASR models is not trivial since fundamental information, such as speaker traits, are lost in the intermediate text bottleneck. To solve this problem, this work presents a loss that is based on the speech encoder state sequence instead of the raw speech signal. This is achieved by training a Text-To-Encoder model and defining a loss based on the encoder reconstruction error. Experimental results on the LibriSpeech corpus show that the proposed cycle-consistency training reduced the word error rate by 14.7% from an initial model trained with 100-hour paired data, using an additional 360 hours of audio data without transcriptions. We also investigate the use of text-only data mainly for language modeling to further improve the performance in the unpaired data training scenario.

本文言語English
ホスト出版物のタイトル2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ6271-6275
ページ数5
ISBN(電子版)9781479981311
DOI
出版ステータスPublished - 2019 5月
外部発表はい
イベント44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
継続期間: 2019 5月 122019 5月 17

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2019-May
ISSN(印刷版)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
国/地域United Kingdom
CityBrighton
Period19/5/1219/5/17

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Cycle-consistency Training for End-to-end Speech Recognition」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