Utterance-level Aggregation For Speaker Recognition In The Wild

Abstract

The objective of this paper is speaker recognition "in the wild"-where utterances may be of variable length and also contain irrelevant signals. Crucial elements in the design of deep networks for this task are the type of trunk (frame level) network, and the method of temporal aggregation. We propose a powerful speaker recognition deep network, using a "thin-ResNet" trunk architecture, and a dictionary-based NetVLAD or GhostVLAD layer to aggregate features across time, that can be trained end-to-end. We show that our network achieves state of the art performance by a significant margin on the VoxCeleb1 test set for speaker recognition, whilst requiring fewer parameters than previous methods. We also investigate the effect of utterance length on performance, and conclude that for "in the wild" data, a longer length is beneficial.

To appear in: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019. (Oral Presentation)

References in corpus (9)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• Attentive Statistics Pooling for Deep Speaker Embedding
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• Attention-Based Models for Text-Dependent Speaker Verification
• Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System
• Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model
• Analysis of Length Normalization in End-to-End Speaker Verification System

Cited by in corpus (4)

• Large Margin Softmax Loss for Speaker Verification
• Emotionless: Privacy-Preserving Speech Analysis for Voice Assistants
• Reconstruction of IACT events using deep learning techniques with CTLearn
• Voice-Face Cross-modal Matching and Retrieval: A Benchmark