Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing

2 November 2022

Kaizhi Qian

Cheng-I Jeff Lai

Papers citing "Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing"

6 / 6 papers shown

Title
Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning Y. Fu Ye Yuan Shang Wu Jiayi Yuan Yingyan Lin OOD 44 3 0 24 Apr 2023
A Unified Speaker Adaptation Approach for ASR Yingzhu Zhao Chongjia Ni C. Leung Shafiq R. Joty Chng Eng Siong B. Ma CLL 77 9 0 16 Oct 2021
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition Yangyang Shi Yongqiang Wang Chunyang Wu Ching-Feng Yeh Julian Chan Frank Zhang Duc Le M. Seltzer 49 168 0 21 Oct 2020
Multi-task self-supervised learning for Robust Speech Recognition Mirco Ravanelli Jianyuan Zhong Santiago Pascual P. Swietojanski João Monteiro J. Trmal Yoshua Bengio SSL 171 288 0 25 Jan 2020
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis Ye Jia Yu Zhang Ron J. Weiss Quan Wang Jonathan Shen ... Z. Chen Patrick Nguyen Ruoming Pang Ignacio López Moreno Yonghui Wu 201 817 0 12 Jun 2018
Listening while Speaking: Speech Chain by Deep Learning Andros Tjandra S. Sakti Satoshi Nakamura AuLLM 115 165 0 16 Jul 2017