7th International Conference on Spoken Language Processing September 16-20, 2002 Denver, Colorado, USA

Memory Space Reduction for Hidden Markov Models in Low-Resource Speech Recognition Systems

Sergey Astrov

Siemens AG, Germany

Low-cost recognition systems based on hidden Markov models (HMM) for mobile speech recognizers (mobile phones, PDAs) have a limited quantity of memory and processing power. Furthermore, the resources have to be shared between several applications. In this paper memory efficient HMMs were investigated for low-cost recognition platforms. The feature parameter tying HMM and subspace distribution clustering HMM (SDCHMM) were explored. In order to achieve less memory requirements, a shared codebook approach for feature parameter tying HMM and SDCHMM was developed and its effectiveness was experimentally proved. It was shown that this approach leads to a relative increase of word error rate of less than 10% for 50% of memory reduction.

Full Paper

Bibliographic reference.  Astrov, Sergey (2002): "Memory space reduction for hidden Markov models in low-resource speech recognition systems", In ICSLP-2002, 1585-1588.