2022 IEEE Spoken Language Technology Workshop (SLT) · 2023 · 30 citations · 21 references
ComputingComputer ScienceFeature EngineeringMachine LearningNatural Language ProcessingDeep LearningPattern RecognitionRepresentation LearningSelf-supervised LearningSpeech RecognitionAttentionAttention PoolingLearning Rate SchedulingSelf-supervised Fine-tuningSelf-supervised Speech Representation LearningSpeaker AdaptationTraining TimeTransformer Models
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification task have yet to be fully explored. In this paper, we analyze several feature extraction approaches built on top of a pre-trained model, as well as regularization and a learning rate scheduler to stabilize the fine-tuning process and further boost performance: multi-head factorized attentive pooling is proposed to factorize the comparison of speaker representations into multiple phonetic clusters. We regularize towards the parameters of the pre-trained model and we set different learning rates for each layer of the pre-trained model during fine-tuning. The experimental results show our method can significantly shorten the training time to 4 hours and achieve SOTA performance: 0.59%, 0.79% and 1.77% EER on Vox1-O, Vox1-E and Vox1-H, respectively. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> Code is available at https://github.com/JunyiPeng00/IEEE-SLT22-Pretrained-Model-for-SV.
21
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
X-Vectors: Robust DNN Embeddings for Speaker Recognition
David Snyder, Daniel Garcia-Romero, Gregory Sell et al. · 2018 · 2.7K citations
VoxCeleb2: Deep Speaker Recognition
Joon Son Chung, Arsha Nagrani, Andrew Zisserman · 2018 · 2.3K citations · Full text