A Two-stage Algorithm for One-microphone Reverberant Speech Enhancement

Abstract

Under noise-free conditions, the quality of reverberant speech is dependent on two distinct perceptual components: coloration and long-term reverberation. They correspond to two physical variables: signal-to-reverberant energy ratio (SRR) and reverberation time, respectively. Inspired by this observation, we propose a two-stage reverberant speech enhancement algorithm using one microphone. In the first stage, an inverse filter is estimated to reduce coloration effects or increase SRR. The second stage employs spectral subtraction to minimize the influence of long-term reverberation. The proposed algorithm significantly improves the quality of reverberant speech. A comparison with a recent enhancement algorithm is made on a corpus of speech utterances in a number of reverberant conditions, and the results show that our algorithm performs substantially better.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2003
Accession Number
AD1001217

Entities

People

  • DeLiang Wang
  • Mingyang Wu

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Adaptive Filters
  • Algorithms
  • Automated Speech Recognition
  • Databases
  • Distortion
  • Equations
  • Filters
  • Filtration
  • Frequency
  • Frequency Bands
  • Frequency Domain
  • Information Retrieval
  • Information Science
  • Noise
  • Power Spectra
  • Speech Quality
  • Time Domain

Readers

  • Image Processing and Computer Vision.
  • Operations Research
  • Speech Processing/Speech Recognition.