Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances
This work addresses robustness in speaker verification systems for arbitrary utterance durations, representing an incremental improvement over existing multi-scale aggregation methods.
The paper tackles the problem of speaker verification for variable-duration utterances by improving multi-scale aggregation with a feature pyramid module, resulting in better performance than state-of-the-art methods on the VoxCeleb dataset for both short and long utterances.
Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a speaker feature extractor. Multi-scale aggregation (MSA), which utilizes multi-scale features from different layers of the feature extractor, has recently been introduced and shows superior performance for variable-duration utterances. To increase the robustness dealing with utterances of arbitrary duration, this paper improves the MSA by using a feature pyramid module. The module enhances speaker-discriminative information of features from multiple layers via a top-down pathway and lateral connections. We extract speaker embeddings using the enhanced features that contain rich speaker information with different time scales. Experiments on the VoxCeleb dataset show that the proposed module improves previous MSA methods with a smaller number of parameters. It also achieves better performance than state-of-the-art approaches for both short and long utterances.