8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Model-Space MLLR for Trajectory HMMs

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda

Nagoya Institute of Technology, Japan

This paper proposes model-space Maximum Likelihood Linear Regression (mMLLR) based speaker adaptation technique for trajectory HMMs, which have been derived from HMMs by imposing explicit relationships between static and dynamic features. This model can alleviate two limitations of the HMM: constant statistics within a state and conditional independence assumption of state output probabilities without increasing the number of model parameters. Results in a continuous speech recognition experiments show that the proposed algorithm can adapt trajectory HMMs to a specific speaker and improve the performance of a trajectory HMM-based speech recognition system.

Full Paper

Bibliographic reference.  Zen, Heiga / Nankaku, Yoshihiko / Tokuda, Keiichi (2007): "Model-space MLLR for trajectory HMMs", In INTERSPEECH-2007, 2065-2068.