A Schema-based Model for Phonemic Restoration

Abstract

Phonemic restoration is the perceptual synthesis of phonemes when masked by appropriate replacement sounds by utilizing lexical context. Current models for phonemic restoration however, use only temporal continuity. These models poorly restore unvoiced phonemes and are limited in their ability to restore voiced phonemes too. We present a schema-based model for phonemic restoration. The model employs a missing data speech recognition system to decode speech based on intact portions and activates word templates corresponding to the words containing the masked phonemes. An activated template is dynamically time warped to the noisy word and is then used to restore the speech frames corresponding to the masked phoneme, thereby synthesizing it. The model is able to restore both voiced and unvoiced phonemes with a high degree of naturalness. Systematic testing shows that this model outperforms a Kalman-filter based model.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
AD1001125

Entities

People

  • DeLiang Wang
  • Soundararajan Srinivasan

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Computer Programming
  • Computers
  • Feature Extraction
  • Frequency
  • Hidden Markov Models
  • Information Processing
  • Information Science
  • Kalman Filtering
  • Kalman Filters
  • Network Science
  • Power Spectra
  • Probability
  • Recognition
  • Reliability
  • Signal Processing
  • White Noise

Readers

  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference