10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Noisy Speech Recognition by Using Output Combination of Discrete-Mixture HMMs and Continuous-Mixture HMMs

Tetsuo Kosaka, You Saito, Masaharu Kato

Yamagata University, Japan

This paper presents an output combination approach for noiserobust speech recognition. The aim of this work is to improve recognition performance for adverse conditions which contain both stationary and non-stationary noise. In the proposed method, both discrete-mixture HMMs (DMHMMs) and continuous-mixture HMMs (CMHMMs) are used as acoustic models. In the DMHMM, subvector quantization is used instead of vector quantization and each state has multiple mixture components. Our previous work showed that DMHMM system indicated better performance in low SNR and/or non-stationary noise conditions. In contrast, CMHMM system was better in the opposite conditions. Thus, we take a system combination approach of the two models to improve the performance in various kinds of noise conditions. The proposed method was evaluated on a LVCSR task with 5K word vocabulary. The results showed that the proposed method was effective in various kinds of noise conditions.

Full Paper

Bibliographic reference.  Kosaka, Tetsuo / Saito, You / Kato, Masaharu (2009): "Noisy speech recognition by using output combination of discrete-mixture HMMs and continuous-mixture HMMs", In INTERSPEECH-2009, 2379-2382.