Quantizing mixture-weights in a tied-mixture HMM

In this paper, we describe new techniques to signi cantly reduce computational, storage and memory access requirements of a tied-mixture HMM based speech recognition system. Although continuous mixture HMMs o er improved recognition performance, we show that tied-mixture HMMs may o er signi cant advantage in complexity reduction for low-cost implementations. In particular, we consider two tasks: (a) connected digit recognition in car noise; and (b) sub-word modeling for command word recognition in a noisy o ce environment. We show that quantization of mixture weights can provide an almost three fold reduction in mixture-weight storage requirements without any signi cant loss in recognition performance. Furthermore, we show that by combining mixture-weight quantization with techniques such as VQ-Assist the computational and memory access requirements can be reduced by almost 60-80% without any degradation in recognition performance.