Challenging margin-based speaker embedding extractors by using the variational information bottleneck
원문 초록
Speaker embedding extractors are typically trained using a classification loss over the training speakers. During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, yielding significant improvements in speaker recognition accuracy. Motivated by the fact that the margin merely reduces the logit of the target speaker during training, we consider a probabilistic framework that has a similar effect. The variational information bottleneck provides a principled mechanism for making deterministic nodes stochastic, resulting in an implicit reduction of the posterior of the target speaker. We experiment with a wide range of speaker recognition benchmarks and scoring methods and report competitive results to those obtained with the state-of-the-art Additive Angular Margin loss.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CoLMbo: Speaker Language Model for Descriptive Profiling
Private kNN-VC: Interpretable Anonymization of Converted Speech
SEED: Speaker Embedding Enhancement Diffusion Model
USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
VoxSim: A perceptual voice similarity dataset
Reshape Dimensions Network for Speaker Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.