Adaptive dereverberation of speech signals with speaker-position change detection

Authors:
Takuya Yoshioka;Hideyuki Tachibana;Tomohiro Nakatani;Masato Miyoshi
Affiliations:
NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikari-dai, Seika-cho, Soraku-gun, 619-0237, Japan;NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikari-dai, Seika-cho, Soraku-gun, 619-0237, Japan;NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikari-dai, Seika-cho, Soraku-gun, 619-0237, Japan;NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikari-dai, Seika-cho, Soraku-gun, 619-0237, Japan
Venue:
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year:
2009

Citing 0
Cited 3

Speech dereverberation based on variance-normalized delayed linear prediction

IEEE Transactions on Audio, Speech, and Language Processing - Special issue on processing reverberant speech: methodologies and applications
Correlation-based and model-based blind single-channel late-reverberation suppression in noisy time-varying acoustical environments

IEEE Transactions on Audio, Speech, and Language Processing - Special issue on processing reverberant speech: methodologies and applications
Online Speech Dereverberation Algorithm Based on Adaptive Multichannel Linear Prediction

IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a method for adaptive speech dereverberation and speaker-position change detection, which have not previously been addressed. Signal transmission channels in rooms are modeled as auto-regressive systems in individual frequency bands. The proposed method adaptively estimates the regression coefficients of this model, which are called room regression coefficients (RRCs). The proposed method has two distinguishing features: (1) The method is based on the weighted recursive least squares algorithm, which enables an efficient RRC-estimate update as well as a fast convergence rate; (2) The method detects changes in speaker position and so can quickly catch up with the sudden channel changes that such position changes cause. Detection is realized by finding time frames where the power of dereverberated speech is anomalously amplified. Experimental results showed that the proposed method attained convergence in 5 seconds and successfully detected changes in speaker position.