# On the effectiveness of enrollment speech augmentation for Target Speaker Extraction

arXiv: https://arxiv.org/abs/2409.09589 · HTML: https://mlsanity.com/paper/2409.09589/

## Key facts

- Cited by 3 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 15 Sep 2024.

## Built on by (most cited first, 3 of 3)

- [U3-xi: Pushing the Boundaries of Speaker Recognition by Incorporating Uncertainty](https://mlsanity.com/paper/2601.15719/) (2026)
- [UNet-Based Fusion and Exponential Moving Average Adaptation for Noise-Robust Speaker Recognition](https://mlsanity.com/paper/2604.25624/) (2026)
- [PAS-SE: Personalized Auxiliary-Sensor Speech Enhancement for Voice Pickup in Hearables](https://mlsanity.com/paper/2509.20875/) (2025)

## Abstract (arXiv)

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.