A study on multilingual acoustic modeling for large vocabulary ASR
Lists
Only you see this
Abstract
We study key issues related to multilingual acoustic modeling for automatic speech recognition (ASR) through a series of large-scale ASR experiments. Our study explores shared structures embedded in a large collection of speech data spanning over a number of spoken languages in order to establish a common set of universal phone models that can be used for large vocabulary ASR of all the languages seen or unseen during training. Language-universal and language-adaptive models are compared with language-specific models, and the comparison results show that in many cases it is possible to build general-purpose language-universal and language-adaptive acoustic models that outperform language-specific ones if the set of shared units, the structure of shared states, and the shared acoustic-phonetic properties among different languages can be properly utilized. Specifically, our results demonstrate that when the context coverage is poor in language-specific training, we can use one tenth of the adaptation data to achieve equivalent performance in cross-lingual speech recognition.
BibTeX
@inproceedings{lin2009study,
author = {Hui Lin and Li Deng and Dong Yu and Yifan Gong and Alex Acero and Chin-Hui Lee},
title = {{A study on multilingual acoustic modeling for large vocabulary ASR}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2009},
doi = {10.1109/icassp.2009.4960588},
}Loading related content...