Yanpei Shi

TL;DR: The obtained results show that the proposed approach using speech enhancement and multi-stage attention models outperforms two strong baselines not using them in most acoustic conditions in the authors' experiments.

TL;DR: In this paper, a hierarchical attention network is proposed to generate utterance-level embeddings (H-vectors) for speaker identification and verification, which aims to learn speaker related information locally and globally.

TL;DR: The obtained results show that the use of H-vectors can achieve a significantly better performance and are more discriminative than the two baselines when mapped into a 2D space using t-SNE.

TL;DR: In this paper, a multi-stage attention mechanism is employed to highlight the speaker related features learned from context information in time and frequency domain to improve speaker recognition performance when speech signals are corrupted by noise.

TL;DR: This work aims at improving the data efficiency of the model and achieving a many-to-many non-parallel StarGAN-based voice conversion for a relatively large number of speakers with limited training samples and shows the proposed model outperforms baseline methods significantly.