The speech recognition systems of IOIT for IWSLT 2014

Quoc Bao Nguyen, Tat Thang Vu, Chi Mai Luong


Abstract
This paper describes the speech recognition systems of IOIT for IWSLT 2014 TED ASR track. This year, we focus on improving acoustic model for the systems using two main approaches of deep neural network which are hybrid and bottleneck feature systems. These two subsystems are combined using lattice Minimum Bayes-Risk decoding. On the 2013 evaluations set, which serves as a progress test set, we were able to reduce the word error rate of our transcription systems from 27.2% to 24.0%, a relative reduction of 11.7%.
Anthology ID:
2014.iwslt-evaluation.12
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Editors:
Marcello Federico, Sebastian Stüker, François Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
92–95
Language:
URL:
https://aclanthology.org/2014.iwslt-evaluation.12
DOI:
Bibkey:
Cite (ACL):
Quoc Bao Nguyen, Tat Thang Vu, and Chi Mai Luong. 2014. The speech recognition systems of IOIT for IWSLT 2014. In Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 92–95, Lake Tahoe, California.
Cite (Informal):
The speech recognition systems of IOIT for IWSLT 2014 (Nguyen et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-evaluation.12.pdf