5th International Conference on Spoken Language Processing
In this paper, we present an integration of Data Driven Parallel Model Combination (DPMC) and Bayesian Learning into a fast and accurate framework which can be easily integrated in standard training and recognition systems. The original DPMC technique has been enhanced to avoid any modification of the acoustic models, as required by the original method. The Bayesian Learning estimation has been used in order to specialize a general noisy speech model (the a priori model) to the target acoustic environment, where the DPMC-generated observations are used as adaptation data. Thanks to these innovations, the proposed method can achieve better performance than the original DPMC, while consuming far less computational resources.
Bibliographic reference. Crafa, Stefano / Fissore, Luciano / Vair, Claudio (1998): "Data-driven PMC and Bayesian learning integration for fast model adaptation in noisy conditions", In ICSLP-1998, paper 1140.