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.
Cite as: Warakagoda, N.D., Johnsen, M.H. (2001) Speaker adaptation in an ASR system based on nonlinear dynamical systems. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1273-1276, doi: 10.21437/Eurospeech.2001-330
@inproceedings{warakagoda01_eurospeech,
author={Narada D. Warakagoda and Magne H. Johnsen},
title={{Speaker adaptation in an ASR system based on nonlinear dynamical systems}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1273--1276},
doi={10.21437/Eurospeech.2001-330}
}