雑音量に依存しない音声領域と雑音領域との判別方法
野村 行弘, 呂 建明, 関屋 大雄, 谷萩 隆嗣
第47回 自動制御連合講演会, pp.526, Nov., 2004. [pdf document]

<Abstract>

This paper presents a speech/noise-dominant decision regardless of SNR. In the proposed decision, the influence of noise is reduced by subtracting the noise component. Therefore, the proposed method decides between the speech dominant and noise one accurately. From the investigation performance evaluation, the speech enhancement using the proposed decision reduces speech distortion thoug h segmental SNR improvement is kept.