Cosine Scoring with Uncertainty for Neural Speaker Embedding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929271139729408 |
|---|---|
| author | Wang, Qiongqiong Lee, Kong Aik |
| author_facet | Wang, Qiongqiong Lee, Kong Aik |
| contents | Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to handle uncertainty. To address this challenge, this paper proposes an approach for estimating uncertainty at the speaker embedding front-end and propagating it to the cosine scoring back-end. Experiments conducted on the VoxCeleb and SITW datasets confirmed the efficacy of the proposed method in handling uncertainty arising from embedding estimation. It achieved improvement with 8.5% and 9.8% average reductions in EER and minDCF compared to the conventional cosine similarity. It is also computationally efficient in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06404 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cosine Scoring with Uncertainty for Neural Speaker Embedding Wang, Qiongqiong Lee, Kong Aik Sound Machine Learning Audio and Speech Processing Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to handle uncertainty. To address this challenge, this paper proposes an approach for estimating uncertainty at the speaker embedding front-end and propagating it to the cosine scoring back-end. Experiments conducted on the VoxCeleb and SITW datasets confirmed the efficacy of the proposed method in handling uncertainty arising from embedding estimation. It achieved improvement with 8.5% and 9.8% average reductions in EER and minDCF compared to the conventional cosine similarity. It is also computationally efficient in practice. |
| title | Cosine Scoring with Uncertainty for Neural Speaker Embedding |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.06404 |