BUT System Description to VoxCeleb Speaker Recognition Challenge 2019

Abstract

In this report, we describe the submission of Brno University of Technology (BUT) team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2019. We also provide a brief analysis of different systems on VoxCeleb-1 test sets. Submitted systems for both Fixed and Open conditions are a fusion of 4 Convolutional Neural Network (CNN) topologies. The first and second networks have ResNet34 topology and use two-dimensional CNNs. The last two networks are one-dimensional CNN and are based on the x-vector extraction topology. Some of the networks are fine-tuned using additive margin angular softmax. Kaldi FBanks and Kaldi PLPs were used as features. The difference between Fixed and Open systems lies in the used training data and fusion strategy. The best systems for Fixed and Open conditions achieved 1.42% and 1.26% ERR on the challenge evaluation set respectively.

References in corpus (1)

• VoxCeleb2: Deep Speaker Recognition

Cited by in corpus (35)

• ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
• SpeechBrain: A General-Purpose Speech Toolkit
• In defence of metric learning for speaker recognition
• ECAPA-TDNN Embeddings for Speaker Diarization
• Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020
• VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
• VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge
• Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification
• The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021
• SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification
• Attention Back-end for Automatic Speaker Verification with Multiple Enrollment Utterances
• Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification
• Adversarial defense for automatic speaker verification by cascaded self-supervised learning models
• CN-Celeb: multi-genre speaker recognition
• Deep Normalization for Speaker Vectors
• Learning Speaker Embedding with Momentum Contrast
• The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020
• Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances
• A Multi-View Approach To Audio-Visual Speaker Verification
• Improving Noise Robustness In Speaker Identification Using A Two-Stage Attention Model
• Adversarially learning disentangled speech representations for robust multi-factor voice conversion
• Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
• Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
• Rep Works in Speaker Verification
• MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification
• LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity
• Delving into VoxCeleb: environment invariant speaker recognition
• STC speaker recognition systems for the NIST SRE 2021
• Tongji University Team for the VoxCeleb Speaker Recognition Challenge 2020
• Towards Robust Speaker Verification with Target Speaker Enhancement
• Improving Text-Independent Speaker Verification with Auxiliary Speakers Using Graph
• Xi-Vector Embedding for Speaker Recognition
• Inclusive Speaker Verification with Adaptive thresholding
• Coupling a generative model with a discriminative learning framework for speaker verification
• Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning