Robust Training for Speaker Verification against Noisy Labels
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908998089834496 |
|---|---|
| author | Fang, Zhihua He, Liang Ma, Hanhan Guo, Xiaochen Li, Lin |
| author_facet | Fang, Zhihua He, Liang Ma, Hanhan Guo, Xiaochen Li, Lin |
| contents | The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a novel two-stage learning method to filter out noisy labels from speaker datasets. Since a DNN will first fit data with clean labels, we first train the model with all data for several epochs. Then, based on this model, the model predictions are compared with the labels using our proposed the OR-Gate with top-k mechanism to select the data with clean labels and the selected data is used to train the model. This process is iterated until the training is completed. We have demonstrated the effectiveness of this method in filtering noisy labels through extensive experiments and have achieved excellent performance on the VoxCeleb (1 and 2) with different added noise rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_12080 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Robust Training for Speaker Verification against Noisy Labels Fang, Zhihua He, Liang Ma, Hanhan Guo, Xiaochen Li, Lin Sound Audio and Speech Processing The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a novel two-stage learning method to filter out noisy labels from speaker datasets. Since a DNN will first fit data with clean labels, we first train the model with all data for several epochs. Then, based on this model, the model predictions are compared with the labels using our proposed the OR-Gate with top-k mechanism to select the data with clean labels and the selected data is used to train the model. This process is iterated until the training is completed. We have demonstrated the effectiveness of this method in filtering noisy labels through extensive experiments and have achieved excellent performance on the VoxCeleb (1 and 2) with different added noise rates. |
| title | Robust Training for Speaker Verification against Noisy Labels |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2211.12080 |