Multi-style MLP features for BN transcription

It has become common practice to adapt acoustic models to specific-conditions (gender, accent, bandwidth) in order to improve the performance of speech-to-text (STT) transcription systems. With the growing interest in the use of discriminative features produced by a multi layer perceptron (MLP) in such systems, the question arise of whether it is necessary to specialize the MLP to particular conditions, and if so, how to incorporate the condition-specific MLP features in the system. This paper explores three approaches (adaptation, full training, and feature merging) to use condition-specific MLP features in a state-of-the-art BN STT system for French. The third approach without condition-specific adaptation was found to outperform the original models with condition-specific adaptation, and was found to perform almost as well as full training of multiple condition-specific HMMs.

• Type: Conference
• Year: 2010
• Where: ICASSP
• Authors: Viet-Bac Le, Lori Lamel, Jean-Luc Gauvain
• Keywords: Acoustic Models, Common Practice, Condition-specific Mlp, ICASSP 2010, Signal Processing