High-Order Modeling Techniques for Continuous Speech Recognition.

Abstract

This research aims to develop new and more accurate stochastic models for speaker independent continuous speech recognition by developing acoustic and language models aimed at representing high-order statistical dependencies within and across utterances, including speaker, channel, and topic characteristics. These techniques, which have high computational costs because of the large search space associated with higher order models, are made feasible through a multi-pass search strategy that involves rescoring a constrained space given by an HMM decoding. With these overall project goals, the primary research efforts and results over the last quarter have included: (1) developed much of the theory for two new models for adaptation, (2) further explored methods for robust dependence tree topology design and implemented training algorithms for hidden dependence tree models; (3) repeated sentence-level mixture language modeling experiments with new versions of NAB training set, showing improvements in both perplexity and word error rates; (4) developed software tools for using HTK in experiments on HMM topology design; and (5) furthered efforts on establishing a baseline HTK recognition system

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 31, 1995
Accession Number
ADA314529

Entities

People

  • Mari Ostendorf

Organizations

  • Boston University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Coding
  • Computer Languages
  • Decoding
  • Formal Languages
  • Language
  • Mathematics
  • Message Decoding
  • Message Processing
  • Notation
  • Recognition
  • Topology
  • Training

Readers

  • Computational Linguistics
  • Computational Modeling and Simulation
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation
  • Space