Name
Abstract | ||
|---|---|---|
Speaker identification (SID) in cochannel speech, where two speakers are talking simultaneously over a single recording channel, is a challenging problem. Previous studies address this problem in the anechoic environment under the Gaussian mixture model (GMM) framework. On the other hand, cochannel SID in reverberant conditions has not been addressed. This paper studies cochannel SID in both anechoic and reverberant conditions. We first investigate GMM-based approaches and propose a combined system that integrates two cochannel SID methods. Secondly, we explore deep neural networks (DNNs) for cochannel SID and propose a DNN-based recognition system. Evaluation results demonstrate that our proposed systems significantly improve SID performance over recent approaches in both anechoic and reverberant conditions and various target-to-interferer ratios. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/TASLP.2015.2447284 | IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) |
Keywords | Field | DocType |
cochannel speaker identification,gaussian mixture model,reverberation,speech,hidden markov models,speech processing,speech recognition | Speech processing,Speaker identification,Reverberation,Pattern recognition,Recognition system,Computer science,Communication channel,Speech recognition,Anechoic chamber,Artificial intelligence,Hidden Markov model,Mixture model | Journal |
Volume | Issue | ISSN |
PP | 99 | 2329-9290 |
Citations | PageRank | References |
1 | 0.43 | 23 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaojia Zhao | 1 | 93 | 5.20 |
| Yu-Xuan Wang | 2 | 650 | 32.68 |
| DeLiang Wang | 3 | 3933 | 362.87 |