Abstract
An algorithm for multichannel speech dereverberation is proposed that simultaneously estimates the clean signal, the linear prediction (LP) parameters of speech, and the acoustic parameters of the room. The received signals are processed in short segments to reduce the algorithm latency, and several expectation-maximization (EM) iterations are carried out on each segment to improve the signal estimation. In the expectation step, the fixed-lag Kalman smoother (FLKS) is applied to extract the clean signal from the data utilizing the estimated parameters. In the maximization step, the LP and room pa-rameters are updated using the output of the FLKS. Experimental results show that multiple EM iterations and the application of the LP model improve the quality of the output signal.
Original language | English |
---|---|
Title of host publication | 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 30-34 |
Number of pages | 5 |
ISBN (Electronic) | 9781479968084 |
DOIs | |
State | Published - 11 Nov 2014 |
Event | 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014 - Juan-les-Pins, France Duration: 8 Sep 2014 → 11 Sep 2014 |
Publication series
Name | 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014 |
---|
Conference
Conference | 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014 |
---|---|
Country/Territory | France |
City | Juan-les-Pins |
Period | 8/09/14 → 11/09/14 |
Bibliographical note
Publisher Copyright:© 2014 IEEE.
Keywords
- Acoustics
- Conferences
- Kalman filters
- Noise
- Speech
- Speech enhancement