On the effectiveness of enrollment speech augmentation for Target Speaker Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916394346479616 |
|---|---|
| author | Li, Junjie Zhang, Ke Wang, Shuai Li, Haizhou Mak, Man-Wai Lee, Kong Aik |
| author_facet | Li, Junjie Zhang, Ke Wang, Shuai Li, Haizhou Mak, Man-Wai Lee, Kong Aik |
| contents | Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a commonly adopted technique. Unlike typical data augmentation applied to speech mixtures, this work thoroughly investigates the effectiveness of augmenting the enrollment speech space. We found that for both pretrained and jointly optimized speaker encoders, directly augmenting the enrollment speech leads to consistent performance improvement. In addition to conventional methods such as noise and reverberation addition, we propose a novel augmentation method called self-estimated speech augmentation (SSA). Experimental results on the Libri2Mix test set show that our proposed method can achieve an improvement of up to 2.5 dB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09589 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the effectiveness of enrollment speech augmentation for Target Speaker Extraction Li, Junjie Zhang, Ke Wang, Shuai Li, Haizhou Mak, Man-Wai Lee, Kong Aik Sound Audio and Speech Processing Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a commonly adopted technique. Unlike typical data augmentation applied to speech mixtures, this work thoroughly investigates the effectiveness of augmenting the enrollment speech space. We found that for both pretrained and jointly optimized speaker encoders, directly augmenting the enrollment speech leads to consistent performance improvement. In addition to conventional methods such as noise and reverberation addition, we propose a novel augmentation method called self-estimated speech augmentation (SSA). Experimental results on the Libri2Mix test set show that our proposed method can achieve an improvement of up to 2.5 dB. |
| title | On the effectiveness of enrollment speech augmentation for Target Speaker Extraction |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.09589 |