Name
Abstract | ||
|---|---|---|
Novel techniques are proposed to enhance time-domain adaptive decorrelation filtering (ADF) for separation and recognition of cochannel speech in reverberant room conditions. The enhancement techniques include whitening filtering on cochannel speech to improve condition of adaptive estimation, block-iterative formulation of ADF to speed up convergence, and integration of multiple ADF outputs through post filtering to reduce reverberation noise. Experimental data were generated by convolving TIMIT speech with acoustic path impulse responses measured in real room environment, with approximately 2 m microphone-source distance and initial target-to-interference ratio of about 0 dB. The proposed techniques significantly improved ADF convergence rate, target-to-interference ratio, and accuracy of phone recognition |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/TSA.2005.860833 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
convolving timit speech,phone recognition,enhanced speech separation,proposed technique,adaptive estimation,adf convergence rate,reverberant room condition,real room environment,cochannel speech,initial target-to-interference ratio,multiple adf output,speedup convergence,noise reduction,convergence,speech recognition,transient response,impulse response,adaptive filters,reverberation,time domain,adaptive filter,convergence rate,filtering,blind source separation,decorrelation | Noise reduction,Speech enhancement,Speech processing,TIMIT,Reverberation,Decorrelation,Computer science,Speech recognition,Adaptive filter,Blind signal separation | Journal |
Volume | Issue | ISSN |
14 | 4 | 1558-7916 |
Citations | PageRank | References |
5 | 0.62 | 13 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yunxin Zhao | 1 | 807 | 121.74 |
| Rong Hu | 2 | 5 | 0.62 |
| Xiaolong Li | 3 | 362 | 36.92 |