Name
Abstract | ||
|---|---|---|
In this paper, we propose a novel feature compensation approach based on the interacting multiple model (IMM) algorithm specially designed for joint processing of background noise and acoustic reverberation. Our approach to cope with the time-varying environmental parameters is to establish a switching linear dynamic model for the additive and convolutive distortions, such as the background noise and acoustic reverberation, in the log-spectral domain. We construct multiple state space models with the speech corruption process in which the log spectra of clean speech and log frequency response of acoustic reverberation are jointly handled as the state of our interest. The proposed approach shows significant improvements in the Aurora-5 automatic speech recognition (ASR) task which was developed to investigate the influence on the performance of ASR for a hands-free speech input in noisy room environments. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TASL.2013.2256893 | IEEE Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
clean speech,noise robust feature compensation,environmental parameters,hands-free speech,speech recognition,log frequency response,noise,interacting multiple model algorithm,reverberation,speech corruption process,noisy room environments,asr,aurora-5 automatic speech recognition,interacting multiple model (imm),imm,dereverberation,convolutive distortions,acoustic reverberation,additive distortions,feature compensation | Speech processing,Background noise,Reverberation,Frequency response,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Feature compensation,State space | Journal |
Volume | Issue | ISSN |
21 | 8 | 1558-7916 |
Citations | PageRank | References |
6 | 0.50 | 17 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chang Woo Han | 1 | 29 | 4.46 |
| Shin Jae Kang | 2 | 55 | 6.48 |
| Nam Soo Kim | 3 | 638 | 55.85 |