Pitch-Based Segregation of Reverberant Speech

Abstract

In everyday listening, both background noise and reverberation degrade the speech signal. Psychoacoustic evidence suggests that human speech perception under reverberant conditions relies primarily on monaural processing. While speech segregation based on periodicity has achieved considerable progress in handling additive noise, little research in monaural segregation has been devoted to reverberant scenarios. Reverberation smears the harmonic structure of speech signals, and our evaluations using a pitch-based segregation algorithm show that an increase in the room reverberation time causes a degradation in performance due to the loss in periodicity for the target signal. We propose a two-stage monaural separation system that combines the inverse filtering of the room impulse response corresponding to target location with a pitch-based speech segregation method. As a result of the first stage, the harmonicity of a signal arriving from target direction is partially restored while signals arriving from other locations are further smeared, and this leads to improved segregation. A systematic evaluation of the system shows that the proposed system results in considerable signal-to-noise ratio gains across different conditions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2005
Accession Number
AD1001150

Entities

People

  • DeLiang Wang
  • Nicoleta Roman

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Advanced Electronics
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Acoustic Properties
  • Acoustics
  • Algorithms
  • Amplitude Modulation
  • Automated Speech Recognition
  • Cognitive Science
  • Cognitive Systems Engineering
  • Computer Science
  • Electrical Engineering
  • Engineering
  • Frequency
  • Modulation
  • Psychology
  • Recognition
  • Signal Processing
  • Universities
  • White Noise

Fields of Study

  • Engineering

Readers

  • Acoustical Oceanography.
  • Neurodegenerative Parkinson's Disease and Rickettsial Disease handbook, including the data level of dopamine, BC, neurons, and PD.
  • Powder metallurgy of Titanium alloys.