no code implementations • 5 Feb 2024 • Zhenyu Zhou, Junhui Chen, Namin Wang, Lantian Li, Dong Wang
This adversarial learning empowers the network to generate speaker embeddings that can deceive the augmentation classifier, making the learned speaker embeddings more robust in the face of augmentation variations.
no code implementations • 25 May 2023 • Jiaying Wang, Xianglong Wang, Namin Wang, Lantian Li, Dong Wang
Modern speaker recognition systems represent utterances by embedding vectors.
no code implementations • 30 Nov 2022 • Yue Li, Li Zhang, Namin Wang, Jie Liu, Lei Xie
Specifically, the weight transfer fine-tuning aims to constrain the distance of the weights between the pre-trained model and the fine-tuned model, which takes advantage of the previously acquired discriminative ability from the large-scale out-domain datasets and avoids catastrophic forgetting and overfitting at the same time.
no code implementations • 6 Nov 2022 • Jixun Yao, Qing Wang, Yi Lei, Pengcheng Guo, Lei Xie, Namin Wang, Jie Liu
By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented.