A study on multilingual acoustic modeling for large vocabulary ASR

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 ...

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Hui Lin, Li Deng, Dong Yu, Yifan Gong, Alex Acero, Chin-Hui Lee
• Keywords: Automatic Speech Recognition, ICASSP 2009, Large Vocabulary Asr, Signal Processing, Speech Recognition