Initial evaluation of hidden dynamic models on conversational speech
Joseph Picone, Sam Pike, Richard A. Regan, Terri Kamm, Jon R. Bridle, Li Deng, Z. Ma, Hywel B. Richards, Maria Elke Schuster · 1999
Conversational speech recognition is a challenging problem primarily because speakers rarely fully articulate sounds. A successful speech recognition approach must infer intended spectral targets from the speech data, or develop a method of dealing with large variances in the data. Hidden dynamic models (HDMs) attempt to automatically learn such targets in a hidden feature space using models that integrate linguistic information with constrained temporal trajectory models. HDMs are a radical departure from conventional hidden Markov models (HMMs), which simply account for variation in the observed data. We present an initial evaluation of such models on a conversational speech recognition task involving a subset of the SWITCHBOARD corpus. We show that in an N-best rescoring paradigm, HDMs are capable of delivering performance competitive with HMMs.