Name
Abstract | ||
|---|---|---|
Mismatch between enrollment and test conditions causes serious performance degradation on speaker recognition systems. This paper presents a statistics decomposition (SD) approach to solve this problem. This approach decomposes the PLDA score into three components that corresponding to enrollment, prediction and normalization respectively. Given that correct statistics are used in each component, the resultant score is theoretically optimal. A comprehensive experimental study was conducted on three datasets with different types of mismatch: (1) physical channel mismatch, (2) long-term speaker characteristics mismatch, (3) near-far recording mismatch. The results demonstrated that the proposed SD approach is highly effective, and outperforms the ad-hoc multi-condition training approach that is commonly adopted but not optimal in theory. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TASLP.2022.3140558 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | DocType | Volume |
Condition mismatch,deep speaker embedding,speaker recognition | Journal | 30 |
Issue | ISSN | Citations |
1 | 2329-9290 | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lantian Li | 1 | 53 | 13.55 |
| Dong Wang | 2 | 375 | 39.86 |
| Jiawen Kang | 3 | 0 | 1.35 |
| Renyu Wang | 4 | 0 | 1.01 |
| Jing Wu | 5 | 49 | 16.62 |
| Zhendong Gao | 6 | 0 | 0.34 |
| Xi Chen | 7 | 333 | 70.76 |