On the effectiveness of enrollment speech augmentation for Target Speaker Extraction

Autor:	Li, Junjie, Zhang, Ke, Wang, Shuai, Li, Haizhou, Mak, Man-Wai, Lee, Kong Aik
Rok vydání:	2024
Předmět:	Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by SLT2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.09589 Zobrazit plný text záznamu View this record from Arxiv