Transport-Oriented Feature Aggregation for Speaker Embedding Learning
Yusheng Tian, Jingyu Li, Tan Lee · Interspeech 2022 · 2022
Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling.Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the statistical distribution over the pre-aggregation layer's output, and propose to use transport-oriented feature aggregation for deriving speaker embeddings.The aggregated representation encodes the geometric structure of the underlying feature distribution, which is expected to contain valuable speaker-specific information that may not be represented by the commonly used statistical measures like mean and variance.The original transportoriented feature aggregation is also extended to a weightedframe version to incorporate the attention mechanism.Experiments on speaker verification with the Voxceleb dataset show improvement over statistics pooling and its attentive variant.