Next: Introduction

The use of recurrent neural networks in continuous speech recognition

Tony Robinson, Mike Hochberg and Steve Renals

Cambridge University Engineering Department, Trumpington Street, Cambridge, CB2 1PZ, U.K.

Sheffield University

Hopefully this document will be published in a book called "Automatic Speech and Speaker Recognition - Advanced Topics", edited by C. H. Lee, K. K. Paliwal and F. K. Soong and published by Kluwer Academic Publishers.

• Introduction
• The Hybrid RNN/HMM Approach
  • The HMM Framework
  • Context Modelling
  • Recurrent Networks for Phone Probability Estimation
• System Description
  • The Acoustic Vector Level
  • The Phone Probability Level
  • Posterior Probabilities to Scaled Likelihoods
  • Decoding Scaled Likelihoods
• System Training
  • Training the RNN
    • RNN Objective Function
    • Gradient Computation
    • Weight Update
• Special Features
  • Connectionist Model Combination
  • Duration Modelling
  • Efficient Models
  • Decoding
    • Search Algorithm
    • Pruning
• Summary of Variations
  • Training Criterion
  • Distribution Assumptions
  • Practical Issues
• A Large Vocabulary System
• Conclusion
• Acknowledgments
• REFERENCES
• About this document ...