Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913288872263680 |
|---|---|
| author | Bousquet, Pierre-Michel Rouvier, Mickael |
| author_facet | Bousquet, Pierre-Michel Rouvier, Mickael |
| contents | The SdSv challenge Task 2 provided an opportunity to assess efficiency and robustness of modern text-independent speaker verification systems. But it also made it possible to test new approaches, capable of taking into account the main issues of this challenge (duration, language, ...). This paper describes the contributions of our laboratory to the speaker recognition field. These contributions highlight two other challenges in addition to short-duration and language: the mismatch between enrollment and test data and the one between subsets of the evaluation trial dataset. The proposed approaches experimentally show their relevance and efficiency on the SdSv evaluation, and could be of interest in many real-life applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19634 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2 Bousquet, Pierre-Michel Rouvier, Mickael Sound Computation and Language Audio and Speech Processing The SdSv challenge Task 2 provided an opportunity to assess efficiency and robustness of modern text-independent speaker verification systems. But it also made it possible to test new approaches, capable of taking into account the main issues of this challenge (duration, language, ...). This paper describes the contributions of our laboratory to the speaker recognition field. These contributions highlight two other challenges in addition to short-duration and language: the mismatch between enrollment and test data and the one between subsets of the evaluation trial dataset. The proposed approaches experimentally show their relevance and efficiency on the SdSv evaluation, and could be of interest in many real-life applications. |
| title | Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2 |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.19634 |