Jul 14, 2024 · We propose a lightweight adaptor framework to boost SV with Whisper, namely Whisper-SV. Given that Whisper is not specifically optimized for SV tasks.

We propose a lightweight adaptor framework to boost SV with Whisper, namely Whisper-SV. Given that Whisper is not specifically optimized for SV tasks.

Feb 13, 2024 · Whisper-SV, characterized by its small number of trainable parameters and low data requirements, outperforms other competitive methods in low-resource SV tasks.

Jul 18, 2024 · We propose a lightweight adaptor framework to boost SV with Whisper, namely Whisper-SV. Given that Whisper is not specifically optimized for SV tasks.

Jul 21, 2024 · Trained on 680,000 hours of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior ...

Whisper-SV: Adapting Whisper for low-data-resource speaker verification ... Deep speaker verification model for low-resource languages and Vietnamese dataset.

Jul 15, 2024 · The Whisper-SV paper presents a novel approach for adapting the powerful Whisper speech recognition model to the task of low-data-resource speaker verification.

Jul 16, 2024 · ``Whisper-SV: Adapting Whisper for Low-data-resource Speaker Verification,'' Li Zhang, Ning Jiang, Qing Wang, Yue Li, Quan Lu, Lei Xie ...

Whisper-Sv: Adapting Whisper for Low-Resource Speaker Verification ... Authors: Li Zhang; Ning Jiang; Qing Wang; Yue Li; Quan Lu; Lei Xie. List of references.

Aug 28, 2024 · In this paper, Whisper, a large-scale pre-trained model for automatic speech recognition, is proposed to apply to speaker verification.