Hierarchical Approach and Downsampling Schemes

Abstract

A simple and successful phoneme recognizer in a hierarchical ANN framework is proposed in [Pinto 08b]. In Section 3.4 we could observed that this method compares favorably to hitherto approaches. In this scheme, phoneme posteriors are estimated by a two-level hierarchical structure. In the first level, a MLP estimates intermediate phoneme posteriors based on a temporal window of cepstral features. In the second level, another MLP estimates final phoneme posteriors based on a temporal window of intermediate posterior features. The final phoneme posteriors are then input to a Viterbi decoder.