Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020
arXiv:2009.14153
Abstract
This report describes our submission to the VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020. We perform a careful analysis of speaker recognition models based on the popular ResNet architecture, and train a number of variants using a range of loss functions. Our results show significant improvements over most existing works without the use of model ensemble or post-processing. We release the training code and pre-trained models as unofficial baselines for this year's challenge.
References in corpus (8)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Instance Normalization: The Missing Ingredient for Fast Stylization
- VoxCeleb2: Deep Speaker Recognition
- Attentive Statistics Pooling for Deep Speaker Embedding
- In defence of metric learning for speaker recognition
- BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
- NSML: A Machine Learning Platform That Enables You to Focus on Your Models
- VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge
Cited by in corpus (24)
- Bias in Automated Speaker Recognition
- Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus
- EfficientTDNN: Efficient Architecture Search for Speaker Recognition
- USAT: A Universal Speaker-Adaptive Text-to-Speech Approach
- Adversarial speech for voice privacy protection from Personalized Speech generation
- openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer
- End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions
- Contrastive-mixup learning for improved speaker verification
- SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
- Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits
- Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
- Adversarial Reweighting for Speaker Verification Fairness
- Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets
- Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021
- Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
- SVEva Fair: A Framework for Evaluating Fairness in Speaker Verification
- ShaneRun System Description to VoxCeleb Speaker Recognition Challenge 2020
- Tongji University Team for the VoxCeleb Speaker Recognition Challenge 2020
- Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning
- Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
- An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS
- Non-local convolutional neural networks (nlcnn) for speaker recognition
- Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020
- Generalized Operating Procedure for Deep Learning: an Unconstrained Optimal Design Perspective