EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Speaker Adaptation in an ASR System Based on Nonlinear Dynamical Systems

Narada D. Warakagoda, Magne H. Johnsen

NTNU, Norway

The work presented here is centered around a speech production model called Chained Dynamical System Model (CDSM) which is motivated by the fundamental limitations of the mainstream ASR approaches. The CDSM is essentially a smoothly time varying continuous state nonlinear dynamical system, consisting of two sub dynamical systems coupled as a chain so that one system controls the parameters of the next system. The speech recognition problem is posed as inverting the CDSM, which is solved using the ideas borrowed from the theory of Embedding. The resulting architecture, which we call Inverted CDSM (ICDSM) is well suited for modeling variations of speaker and channel characteristics, by its nature. We have evaluated the ICDSM using a set of experiments involving speaker adaptation in a continuous speech recognition task on the TIMIT database. Results of these experiments confirm the feasibility and potential advantages of the approach.

Full Paper

Bibliographic reference.  Warakagoda, Narada D. / Johnsen, Magne H. (2001): "Speaker adaptation in an ASR system based on nonlinear dynamical systems", In EUROSPEECH-2001, 1273-1276.