| Presentation # | 11 |
| Session: | ASR III (End-to-End) |
| Session Time: | Friday, December 21, 10:00 - 12:00 |
| Presentation Time: | Friday, December 21, 10:00 - 12:00 |
| Presentation: |
Poster
|
| Topic: |
Speech recognition and synthesis: |
| Paper Title: |
BACK-TRANSLATION-STYLE DATA AUGMENTATION FOR END-TO-END ASR |
| Authors: |
Tomoki Hayashi; Nagoya University | | |
| | Shinji Watanabe; Johns Hopkins University | | |
| | Yu Zhang; Google | | |
| | Tomoki Toda; Nagoya University | | |
| | Takaaki Hori; Mitsubishi Electric Research Laboratories | | |
| | Ramon Astudillo; INESC-ID-Lisboa | | |
| | Kazuya Takeda; Nagoya University | | |
| Abstract: |
In this paper we propose a novel data augmentation method for attention-based end-to-end automatic speech recognition (E2E-ASR), utilizing a large amount of text which is not paired with speech signals. Inspired by the back-translation technique proposed in the field of machine translation, we build a neural text-to-encoder model which predicts a sequence of hidden states extracted by a pre-trained E2E-ASR encoder from a sequence of characters. By using hidden states as a target instead of acoustic features, it is possible to achieve faster attention learning and reduce computational cost, thanks to sub-sampling in E2E-ASR encoder, also the use of the hidden states can avoid to model speaker dependencies unlike acoustic features. After training, the text-to-encoder model generates the hidden states from a large amount of unpaired text, then E2E-ASR decoder is re-trained using the generated hidden states as additional training data. Experimental evaluation using LibriSpeech dataset demonstrates that our proposed method achieves improvement of ASR performance and reduces the number of unknown words without the need for paired data. |