Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances

Abstract

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.

arXiv commentAccepted to Interspeech 2020

References in corpus (7)

• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• Residual Networks Behave Like Ensembles of Relatively Shallow Networks
• Attentive Statistics Pooling for Deep Speaker Embedding
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs

Cited by in corpus (10)

• A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
• Speaker Recognition Based on Deep Learning: An Overview
• Intra-class variation reduction of speaker representation in disentanglement framework
• Rep Works in Speaker Verification
• MIRNet: Learning multiple identities representations in overlapped speech
• Bidirectional Multiscale Feature Aggregation for Speaker Verification
• Supervised attention for speaker recognition
• Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention
• X-Vectors with Multi-Scale Aggregation for Speaker Diarization