Low cost speech detection using Haar-like filtering for sensornet

Jun Nishimura, Tadahiro Kuroda

研究成果: Conference contribution

13 被引用数 (Scopus)

抄録

Haar-like filtering based speech detection is proposed as a new and very low calculation cost method for sensornet applications. The simple haarlike filters having variable filter width and shift width are trained to learn appropriate filter parameters from the training samples to detect speech. Our method yielded speech/nonspeech classification accuracy of 96.93% 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 85.77% efficient in terms of the amount of add and multiply calculations while capable of achieving the error rate of only 3.03% relative to MFCC.

本文言語English
ホスト出版物のタイトル2008 9th International Conference on Signal Processing, ICSP 2008
ページ2608-2611
ページ数4
DOI
出版ステータスPublished - 2008
外部発表はい
イベント2008 9th International Conference on Signal Processing, ICSP 2008 - Beijing, China
継続期間: 2008 10月 262008 10月 29

出版物シリーズ

名前International Conference on Signal Processing Proceedings, ICSP

Other

Other2008 9th International Conference on Signal Processing, ICSP 2008
国/地域China
CityBeijing
Period08/10/2608/10/29

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • コンピュータ サイエンスの応用

フィンガープリント

「Low cost speech detection using Haar-like filtering for sensornet」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル