The HCCL system for VoxCeleb Speaker Recognition Challenge 2022

This report describes our submission to track1 and track3 for VoxCeleb Speaker Recognition Challenge 2022(VoxSRC2022). Our best system achieves minDCF 0.1397 and EER 2.414 in track1, minDCF 0.388 and EER 7.030 in track3.

Speech Recognition and Synthesis Natural Language Processing Techniques Computer Science Engineering

View graph Source

Paper

References (38)

01MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker VerificationYang Zhang, Zhiqiang Lv, Haibin Wu et al.2022 · Interspeech · 181 citations In Library

02The Coral++ Algorithm for Unsupervised Domain Adaptation of Speaker RecognitionRongjin Li, Weibin Zhang, Dongpeng Chen2022 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 28 citations In Library

03VoxSRC 2021: The Third VoxCeleb Speaker Recognition ChallengeA. Brown, Jaesung Huh, Joon Son Chung et al.2022 · arXiv.org · 48 citations In Library

04Explore Long-Range Context feature for Speaker VerificationZhuo Li2021 · arXiv.org · 8 citations In Library

05Torchaudio: Building Blocks for Audio and Speech ProcessingYao-Yuan Yang, Moto Hira, Zhaoheng Ni et al.2021 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 215 citations In Library

06The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021Miao Zhao, Yufeng Ma, Min Liu et al.2021 · arXiv.org · 69 citations In Library

07Contextual Transformer Networks for Visual RecognitionYehao Li, Ting Yao, Yingwei Pan et al.2021 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 675 citations In Library

08Adaptive Margin Circle Loss for Speaker VerificationRunqiu Xiao2021 · Interspeech · 15 citations In Library

09SpeechBrain: A General-Purpose Speech ToolkitM. Ravanelli, Titouan Parcollet, Peter William VanHarn Plantinga et al.2021 · arXiv.org · 1.0k citations In Library

10Speaker embeddings by modeling channel-wise correlationsThemos Stafylakis, Johan Rohdin, Lukáš Burget2021 · Interspeech · 10 citations In Library

11RepVGG: Making VGG-style ConvNets Great AgainXiaohan Ding, X. Zhang, Ningning Ma et al.2021 · Computer Vision and Pattern Recognition · 2.4k citations In Library

12CN-Celeb: multi-genre speaker recognitionLantian Li, Ruiqi Liu, Jiawen Kang et al.2020 · Speech Communication · 162 citations In Library

Scroll for more · 26 remaining

Similar papers

The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021Miao Zhao, Yufeng Ma, Min Liu et al.2021 · arXiv (Cornell University) · 69 citations In Library

The Kriston AI System for the VoxCeleb Speaker Recognition Challenge 2022Qutang Cai, Guoqiang Hong, Zhijian Ye et al.2022 · arXiv (Cornell University) · 8 citations In Library

UNISOUND System for VoxCeleb Speaker Recognition Challenge 2023Yufeng Zheng, Yajun Zhang, Chuanying Niu et al.2023 · arXiv (Cornell University) · 6 citations In Library

The Microsoft System for VoxCeleb Speaker Recognition Challenge 2022Gang Liu, Tianyan Zhou, Yongheng Zhao et al.2022 · arXiv (Cornell University) · 2 citations In Library

The Royalflush System for VoxCeleb Speaker Recognition Challenge 2022Jingguang Tian, Xinhui Hu, Xinkang Xu2022 · arXiv (Cornell University) · 1 citation In Library

The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020Xu Xiang2020 · arXiv (Cornell University) · 15 citations In Library

The DKU-Tencent System for the VoxCeleb Speaker Recognition Challenge 2022Xiaoyi Qin, Na Li, Yuke Lin et al.2022 · arXiv (Cornell University) · 12 citations In Library

The DKU-MSXF Speaker Verification System for the VoxCeleb Speaker Recognition Challenge 2023Ze Li, Yuke Lin, Xiaoyi Qin et al.2023 · arXiv (Cornell University) · 8 citations In Library

The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System DescriptionNikita Torgashov, Rostislav Makarov, Ivan Yakovlev et al.2023 · arXiv (Cornell University) · 12 citations In Library

The IDLAB VoxCeleb Speaker Recognition Challenge 2021 System DescriptionJenthe Thienpondt, Brecht Desplanques, Kris Demuynck2021 · arXiv.org · 26 citations In Library

Patents near this paper

FEATURE AND FEATURE VARIANT RECONSTRUCTION FOR RECURRENT MODEL ACCURACY IMPROVEMENT IN SPEECH RECOGNITIONUS 11,404,047 · INTERNATIONAL BUSINESS MACHINES CORPORATION · 2022 RECOGNITION CONFIDENCE MEASURING BY LEXICAL DISTANCE BETWEEN CANDIDATESUS 8,990,086 · SAMSUNG ELECTRONICS CO., LTD. · 2015 Singular Value Decomposition for Improved Voice Recognition in Presence of Multi-Talker Background NoiseUS 9,177,557 · GENERAL MOTORS CORPORATION · 2015 ACOUSTIC SPEECH RECOGNITION METHOD AND SYSTEM USING STEREO VISION NEURAL NETWORKS WITH COMPETITION AND COOPERATIONUS 6,947,890 · KITAZOE, TETSURO · 2005 FAST SPEAKER RECOGNITION SCORING USING I-VECTOR POSTERIORS AND PROBABILISTIC LINEAR DISCRIMINANT ANALYSISUS 9,373,330 · NUANCE COMMUNICATIONS, INC. · 2016

Source of record

OpenAlex