Haar-like filtering with center-clipped emphasis for speech detection in sensornet

Jun Nishimura, Tadahiro Kuroda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The use of haar-like filtering for resourced-constrained speech detection in sensornet application is explored. The simple haar-like filters having variable filter width and shift width are trained to learn appropriate filter parameters from the training samples to detect speech. To further refine the accuracy, the center-clipped emphasis is proposed as a new degree of freedom for more adaptive Haar-like filter designs. Our method yielded speech/nonspeech classification accuracy of 98.33% for the input length of 0.1s. Compared with high performance feature extraction method MFCC (Mel-Frequency Cepstrum Coefficient), the proposed haar-like filtering can be approximately 98.40% efficient in terms of the amount of add and multiply computation while capable of achieving the error rate of only 1.63% relative to MFCC.

Original languageEnglish
Title of host publication2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings
Pages1-4
Number of pages4
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009 - Marco Island, FL, United States
Duration: 2009 Jan 42009 Jan 7

Publication series

Name2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings

Other

Other2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009
Country/TerritoryUnited States
CityMarco Island, FL
Period09/1/409/1/7

Keywords

  • Center-clipped emphasis
  • Haar-like filtering
  • Sensornet
  • Speech detection

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Haar-like filtering with center-clipped emphasis for speech detection in sensornet'. Together they form a unique fingerprint.

Cite this