観測信号のスペクトログラム上の特徴量に基づく音声領域と雑音領域との判別を用いた音声強調

概要

論文の詳細を見る
This paper presents a speech enhancement using the classification between the dominants of speech and noise. In our system, a new classification scheme between the dominants of speech and noise is proposed. The proposed classifications use the standard deviation of the spectrum of observation signal in each band. We introduce two oversubtraction factors for the dominants of speech and noise, respectively. And spectral subtraction is carried out after the classification. The proposed method is tested on several noise types from the Noisex-92 database. From the investigation of segmental SNR, Itakura-Saito distance measure, inspection of spectrograms and listening tests, the proposed system is shown to be effective to reduce background noise. Moreover, the enhanced speech using our system generates less musical noise and distortion than that of conventional systems.
社団法人電気学会の論文
2004-11-01