Speaker Adaptation Using Multiple Reference Speakers

Abstract

We introduce a new technique for using the speech of multiple reference speakers as a basis for speaker adaptation in large vocabulary continuous speech recognition. In contrast to other methods that use a pooled reference model, this technique normalizes the training speech from multiple reference speakers to a single common feature space before pooling it. The normalized and pooled speech can then be treated as if it came from a single reference speaker for training the reference hidden Markov model (HMM). Our usual prohabilistic spectrum transformation can be applied to the reference HMM to model a new (target) speaker. In this paper, we describe our baseline (single reference speaker) speaker-adaptation system and give current performance results from a recent formal evaluation of the system. We also describe our proposal for adapting from multiple reference speakers and report on recent preliminary experimental results in support of the proposed technique.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1989
Accession Number
ADA457475

Entities

People

  • Chris Barry
  • Francis Kubala
  • Richard Schwartz

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Databases
  • Dynamic Range
  • Grammars
  • Hidden Markov Models
  • Identities
  • Markov Models
  • Materials
  • Models
  • Numbers
  • Recognition
  • Resource Management
  • Spectra
  • Standards
  • Test And Evaluation
  • Test Sets
  • Training

Readers

  • Regression Analysis.
  • Speech Processing/Speech Recognition.

Technology Areas

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