Abstract | ||
---|---|---|
•It proposes two cosine metric learning (CML) back-end algorithms. The first one, named m-CML, aims to enlarge the between-class distance with a regularization term to control the within-class variance. The second one, named v-CML, attempts to reduce the within-class variance with a regularization term to prevent the between-class distance from getting smaller.•It combines m-CML with an i-vector front-end since m-CML is good at enlarging the between-class distance of Gaussian score distributions.•It combines v-CML with a d-vector or x-vector front-end as v-CML is able to reduce the within-class variance of heavy-tailed score distributions significantly.•Experimental results on the NIST and SITW speaker recognition evaluation corpora with both i-vector, d-vector and x-vector front-ends demonstrate the effectiveness of the proposed algorithms. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.specom.2020.02.003 | Speech Communication |
Keywords | Field | DocType |
Cosine metric learning,Inter-session variability compensation,Speaker verification | Compensation methods,Pattern recognition,Computer science,Communication channel,NIST,Speaker recognition,Regularization (mathematics),Gaussian,Artificial intelligence,Linear discriminant analysis,Initialization | Journal |
Volume | Issue | ISSN |
118 | C | 0167-6393 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhongxin Bai | 1 | 2 | 1.87 |
Xiao-Lei Zhang | 2 | 147 | 14.47 |
Jingdong Chen | 3 | 1460 | 128.79 |