Developing speech recognition systems for corpus indexing under the IARPA Babel program
Lists
Only you see this
Abstract
Automatic speech recognition is a core component of many applications, including keyword search. In this paper we describe experiments on acoustic modeling, language modeling, and decoding for keyword search on a Cantonese conversational telephony corpus collected as part of the IARPA Babel program. We show that acoustic modeling techniques such as the bootstrapped-and-restructured model and deep neural network acoustic model significantly outperform a state-of-the-art baseline GMM/HMM model, in terms of both recognition performance and keyword search performance, with improvements of up to 11% relative character error rate reduction and 31% relative maximum term weighted value improvement. We show that while an interpolated Model M and neural network LM improve recognition performance, they do not improve keyword search results; however, the advanced LM does reduce the size of the keyword search index. Finally, we show that a simple form of automatically adapted keyword search performs 16% better than a preindexed search system, indicating that out-of-vocabulary search is still a challenge.
BibTeX
@inproceedings{cui2013developing,
author = {Jia Cui and Xiaodong Cui and Bhuvana Ramabhadran and Janice Kim and Brian Kingsbury and Jonathan Mamou and Lidia Mangu and Michael Picheny and Tara N. Sainath and Abhinav Sethy},
title = {{Developing speech recognition systems for corpus indexing under the IARPA Babel program}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2013},
url = {https://openreview.net/forum?id=IkJo4OxI_B7},
}Loading related content...