Towards A Unified Conformer Structure: from ASR to ASV Task

14 November 2022

Papers citing "Towards A Unified Conformer Structure: from ASR to ASV Task"

6 / 6 papers shown

Title
Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning Danwei Cai Zexin Cai Ming Li 25 0 0 03 Jan 2024
Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition Shuai Wang Qibing Bai Qi Liu Jianwei Yu Zhengyang Chen Bing Han Yan-min Qian Haizhou Li 19 1 0 21 Sep 2023
Wespeaker baselines for VoxSRC2023 Shuai Wang Che-Yuan Liang Xu Xiang Bing Han Zhengyang Chen Hongji Wang Wen Ding 25 0 0 27 Jun 2023
Multi-task Learning for Speaker Verification and Voice Trigger Detection Siddharth Sigtia Erik Marchi S. Kajarekar Devang Naik J. Bridle 40 29 0 26 Jan 2020
VoxCeleb2: Deep Speaker Recognition Joon Son Chung Arsha Nagrani Andrew Zisserman 224 2,234 0 14 Jun 2018
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 281 2,889 0 15 Sep 2016