Monday, October 31
12.10 - 1.00
CSE 4140

Speaker: Karen Livescu, TTI-Chicago
Title: Recent advances in articulatory modeling for speech recognition

Abstract:
The standard approach to speech recognition represents words as concatenations of hidden Markov models, each representing a phonetic unit such as a particular vowel or consonant in a particular context. For several decades the speech research community has also experimented with models of speech articulation, that is models of the behavior of the lips, tongue, vocal folds, and soft palate during speech production, as an alternative to phone-based models. This work is motivated by the potential for improved pronunciation modeling, language portability, and noise robustness. However, such models have not yet made it into mainstream recognition systems, in part because of their complexity relative to traditional approaches. Current interest in structured prediction and low-resource speech recognition has renewed interest in this approach. This talk will review the current state of articulatory models and will describe one particular model family, using dynamic graphical models (dynamic Bayesian networks and conditional random fields) over articulatory variables. This approach allows for probabilistic modeling of asynchrony between articulators and reduction in articulatory gestures that lead to pronunciation variation. Time permitting, the talk will include highlights of other related work at TTI-Chicago, including multi-view learning and nearest-neighbor approaches in speech processing.