Affordable Access

Reducing errors by increasing the error rate: MLP Acoustic Modeling for Broadcast News Transcription

Authors
Publisher
Information Technology Laboratory, National Institute of Standards and Technology
Publication Date
Keywords
  • Electrical Engineering
  • Artificial Intelligence
Disciplines
  • Musicology
  • Physics

Abstract

We describe some aspects of a Broadcast News recognition system based on hybrid HMM/MLP acoustic modeling. These include the use of novel 'modulation spectrogram' features which are combined with conventional models at the posterior probability level, some experiments with nonlinear segment normalization, and an investigation of the interaction of model size and training set size for an multilayer perceptron (MLP) acoustic classifier. We also report preliminary results of incorporating gender-dependence into this system.

There are no comments yet on this publication. Be the first to share your thoughts.