Adapting End-to-End Speech Recognition for Readable Subtitles

Danni Liu, Jan Niehues, Gerasimos Spanakis


Abstract
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time. Therefore, this work focuses on ASR with output compression, a task challenging for supervised approaches due to the scarcity of training data. We first investigate a cascaded system, where an unsupervised compression model is used to post-edit the transcribed speech. We then compare several methods of end-to-end speech recognition under output length constraints. The experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities. Furthermore, the best performance in terms of WER and ROUGE scores is achieved by explicitly modeling the length constraints within the end-to-end ASR system.
Anthology ID:
2020.iwslt-1.30
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Marcello Federico, Alex Waibel, Kevin Knight, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Dekai Wu, Joseph Mariani, Francois Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
247–256
Language:
URL:
https://aclanthology.org/2020.iwslt-1.30
DOI:
10.18653/v1/2020.iwslt-1.30
Bibkey:
Cite (ACL):
Danni Liu, Jan Niehues, and Gerasimos Spanakis. 2020. Adapting End-to-End Speech Recognition for Readable Subtitles. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 247–256, Online. Association for Computational Linguistics.
Cite (Informal):
Adapting End-to-End Speech Recognition for Readable Subtitles (Liu et al., IWSLT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwslt-1.30.pdf
Video:
 http://slideslive.com/38929588
Code
 quanpn90/NMTGMinor