Modular Neural Networks for Speech Recognition.

Abstract

In recent years, researchers have established the viability of so called hybrid NN/IIMM large vocabulary, speaker independent continuous speech recognition systems, where neural networks (NN) are used for the estimation of acoustic emission probabilities for hidden Markov models (IIMM) which provide statistical temporal modeling. Work in this direction is based on a proof, that neural networks can be trained to estimate posterior class probabilities. Advantages of the hybrid approach over traditional mixture of Gaussians based systems include discriminative training, fewer parameters, contextual inputs and faster sentence decoding. However, hybrid systems usually have training times that are orders of magnitude higher than those observed in traditional systems. This is largely due to the costly, gradient-based error-back propagation learning algorithm applied to very large neural networks, which often requires the use of specialized parallel hardware. This thesis examines how a hybrid NN/IIMM system can benefit from the use of modular and hierarchical neural networks such as the hierarchical mixtures of experts (IIME) architecture. Based on a powerful statistical framework, it is shown that modularity and the principle of divide-and-conquer applied to neural network learning reduces training times significantly. We developed a hybrid speech recognition system based on modular neural networks and the state-of-the-art continuous density IIMM speech recognizer JANUS. The system is evaluated on the English Spontaneous Scheduling Task (ESST), a 2400 word spontaneous speech database.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1996
Accession Number
ADA326090

Entities

People

  • Juergen Fritsch

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Computers
  • Data Mining
  • Databases
  • Generative Models
  • Hidden Markov Models
  • Information Processing
  • Information Science
  • Information Systems
  • Kernel Functions
  • Markov Models
  • Network Science
  • Neural Networks
  • Probabilistic Models
  • Probability
  • Probability Distributions
  • Recurrent Neural Networks
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Computer Engineering
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks