Can I read An alternative Approach in Voice Extraction on EtoBox?

An alternative Approach in Voice Extraction by Pham, The Hieu; Nguyen, Phuong Thanh Tran; Nguyen, Xuan Tho; Nguyen, Tan Dat; Nguyen, Duc Dung is a scholarly article available to read on EtoBox.

What is An alternative Approach in Voice Extraction about?

The research on audio clue-based target speaker extraction (TSE) has mostly focused on modeling the mixture and reference speech, achieving high performance in English due to the availability of large datasets. However, less attention has been given to the consistent properties of human speech across languages. To bridge this gap, we introduce an alternative model which addresses the challenge of transferring TSE models from one language to another without fine-tuning. In this work, we proposed a gating mechanism that is able to modify specific frequencies based on the speaker's acoustic features. The model achieves an SI-SDR of 17.3544 on clean English speech and 13.2032 on clean speech mixed with Wham! noise, outperforming all other models in its ability to adapt to different languages.

Author

Pham, The Hieu; Nguyen, Phuong Thanh Tran; Nguyen, Xuan Tho; Nguyen, Tan Dat; Nguyen, Duc Dung

Published

2024

Language

EN