5th International Conference on Spoken Language Processing
Current state-of-the-art statistical speech recognition systems use hidden Markov models (HMM) for modeling the speech signal. However, it is well known that HMM's do not exploit the time-dependence in the speech process, since they are limited by the assumption of conditional independence of observations given the state sequence. Alternative techniques, such as segment modeling approaches, can effectively exploit time-dependencies in the acoustic signal by discarding the observation independence assumption. However, losing the basic HMM structure is often a high computational price to pay for improved acoustic models. In this paper, we introduce the parallel path HMM that exploits the time-dependence in speech via parametric trajectory models while maintaining the HMM framework. We present preliminary results on Switchboard, a large vocabulary conversational speech recognition task, demonstrating both improved modeling and potential for improved recognition performance.
Bibliographic reference. Iyer, Rukmini / Gish, Herbert / Siu, Man-Hung / Zavaliagkos, George / Matsoukas, Spyros (1998): "Hidden Markov models for trajectory modeling", In ICSLP-1998, paper 0891.