Learning a language model from continuous speech

This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using acoustic model scores, and Bayesian techniques are used to robustly learn a language model from this noisy input. A novel sampling technique is devised that allows for the integrated learning of word boundaries and an n-gram language model with no prior linguistic knowledge. The proposed techniques were used to learn a language model directly from continuous, potentially large-vocabulary speech. This language model was able to significantly reduce the ASR phoneme error rate over a separate set of test data, and the proposed lattice processing and lexical acquisition techniques were found to be important factors in this improvement.

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsuya Kawahara
• Keywords: Acoustic Model Scores, INTERSPEECH 2010, Language Model, N-gram Language Model, Signal Processing