Speaker adaptation of acoustic models using correlations of training transfer vectors

Abstract

The authors proposed for acoustic models based on the hidden Markov model a method that involves applying constraints to the model structure and tying the model's parameters in order to improve the training efficiency. Conventionally, the tied structure of an acoustic model is, mostly, defined by tying several adjacent parameters and expressing them with a single representative parameter. This method can be regarded as a tying method based on the parameters' values, under the assumption that adjacent parameters, usually, exhibit similar behavior. As opposed to this concept, the current study proposes a tied structure with consideration of transfer (movement) of parameters. A large volume of training data was used to measure transfer of each parameter during training, and tying relationships regarding the transfer vectors were organized between parameters performing statistically similar movements. In particular, in the current study, the authors concentrated on mean vectors of fundamental distributions and followed movements of these mean vectors during training of initial models (speaker-independent models) by acoustic data from different speakers. The structure was defined by identifying the mean vectors characterized by strong correlation of movements during training, and tying their corresponding transfer vectors. Speaker adaptation tests confirmed high training efficiency of the model obtained as a result of this tying. © 2000 Scripta Technica, Syst Comp Jpn, 31(14): 74–82, 2000