Comparative Experiments on Large Vocabulary Speech Recognition

Abstract

This paper describes several key experiments in large vocabulary speech recognition. We demonstrate that, counter to our intuitions, given a fixed amount of training speech, the number of training speakers has little effect on the accuracy. We show how much speech is needed for speaker-independent (SI) recognition in order to achieve the same performance as speaker-dependent (SD) recognition. We demonstrate that, though the N-Best Paradigm works quite well up to vocabularies of 5,000 words, it begins to break down with 20,000 words and long sentences. We compare the performance of two feature preprocessing algorithms for microphone independence and we describe a new microphone adaptation algorithm based on selection among several codebook transformations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1993
Accession Number
ADA460561

Entities

People

  • Francis Kubala
  • George Zavaliagkos
  • John Makhoul
  • Long B. Nguyen
  • Richard Schwartz
  • Tasos Anastasakos

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Dictionaries
  • Errors
  • Grammars
  • Hidden Markov Models
  • Language
  • Markov Models
  • Models
  • Natural Language Processing
  • Preprocessing
  • Recognition
  • Resource Management
  • Signal Processing
  • Standards
  • Test Sets
  • Vocabulary

Fields of Study

  • Computer science

Readers

  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation