Combining Discriminative Feature, Transform, and Model Training for Large Vocabulary Speech Recognition

Abstract

Recent developments in large vocabulary continuous speech recognition (LVCSR) have shown the effectiveness of discriminative training approaches, employing the following three representative techniques: discriminative Gaussian training using the minimum phone error (MPE) criterion, discriminately trained features estimated by multilayer perceptrons (MLPs… (More)
DOI: 10.1109/ICASSP.2007.366992

3 Figures and Tables

Topics

  • Presentations referencing similar topics