Speaker Representation Learning Via Contrastive Loss With Maximal Speaker Separability
2022 · Zhe Li, Man-Wai Mak
Abstract
A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning objective to learn a speaker embedding space by effectively leveraging the label information in the training data. In such a space, utterance pairs spoken by the same or similar speakers will stay close, while utterance pairs spoken by different speakers will be far apart. For each training speaker, we perform random data augmentation on their utterances to form positive pairs, and utterances from different speakers form negative pairs. To maximize speaker separability in the embedding space, we incorporate the additive angular-margin loss into the contrastive learning objective. Experimental results on CN-Celeb show that this new learning objective can cause ECAPA-TDNN to find an embedding space that exhibits great speaker discrimination. The contrastive
Authors
(none)
Tags
Stats
Related papers
- Discriminative Speaker Representation Via Contrastive Learning With Class-aware Attention In Angular Space (2022)8.60
- Contrastive Separative Coding For Self-supervised Representation Learning (2021)0.00
- Label-efficient Self-supervised Speaker Verification With Information Maximization And Contrastive Learning (2022)6.77
- Experimenting With Additive Margins For Contrastive Self-supervised Speaker Verification (2023)4.52
- Unsupervised Representation Learning For Speaker Recognition Via Contrastive Equilibrium Learning (2020)0.00
- Additive Margin In Contrastive Self-supervised Frameworks To Learn Discriminative Speaker Representations (2024)2.26
- Margin Matters: Towards More Discriminative Deep Neural Network Embeddings For Speaker Recognition (2019)15.25
- Improving Speaker Representations Using Contrastive Losses On Multi-scale Features (2024)0.00