Speaker Recognition Based on Deep Learning: An Overview

Abstract

Speaker recognition is a task of identifying persons from their voices. Recently, deep learning has dramatically revolutionized speaker recognition. However, there is lack of comprehensive reviews on the exciting progress. In this paper, we review several major subtasks of speaker recognition, including speaker verification, identification, diarization, and robust speaker recognition, with a focus on deep-learning-based methods. Because the major advantage of deep learning over conventional methods is its representation ability, which is able to produce highly abstract embedding features from utterances, we first pay close attention to deep-learning-based speaker feature extraction, including the inputs, network structures, temporal pooling strategies, and objective functions respectively, which are the fundamental components of many speaker recognition subtasks. Then, we make an overview of speaker diarization, with an emphasis of recent supervised, end-to-end, and online diarization. Finally, we survey robust speaker recognition from the perspectives of domain adaptation and speech enhancement, which are two major approaches of dealing with domain mismatch and noise problems. Popular and recently released corpora are listed at the end of the paper.

References in corpus (27)

• VoxCeleb2: Deep Speaker Recognition
• Deep Visual Domain Adaptation: A Survey
• Attentive Statistics Pooling for Deep Speaker Embedding
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• In defence of metric learning for speaker recognition
• Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
• LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization
• Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection
• Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances
• End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification
• Voices Obscured in Complex Environmental Settings (VOICES) corpus
• Neural Speaker Diarization with Speaker-Wise Chain Rule
• Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification
• Few Shot Speaker Recognition using Deep Neural Networks
• The VOiCES from a Distance Challenge 2019 Evaluation Plan
• AM-MobileNet1D: A Portable Model for Speaker Recognition
• BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition
• Discriminative Neural Clustering for Speaker Diarisation
• The Attacker's Perspective on Automatic Speaker Verification: An Overview
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
• AutoSpeech: Neural Architecture Search for Speaker Recognition
• Online End-to-End Neural Diarization with Speaker-Tracing Buffer
• On the use of DNN Autoencoder for Robust Speaker Recognition
• The FFSVC 2020 Evaluation Plan
• DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
• Speaker Embedding Extraction with Phonetic Information
• Who said that?: Audio-visual speaker diarisation of real-world meetings

Cited by in corpus (2)

• Diarization of Legal Proceedings. Identifying and Transcribing Judicial Speech from Recorded Court Audio
• Learning Metrics from Mean Teacher: A Supervised Learning Method for Improving the Generalization of Speaker Verification System