To Reverse the Gradient or Not: An Empirical Comparison of Adversarial
and Multi-task Learning in Speech Recognition

To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition

9 December 2018

Yossi Adi

Nicolas Usunier

Vitaliy Liptchinsky

Gabriel Synnaeve

Papers citing "To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition"

5 / 5 papers shown

Title
SA-SOT: Speaker-Aware Serialized Output Training for Multi-Talker ASR Zhiyun Fan Linhao Dong Jun Zhang Lu Lu Zejun Ma 43 5 0 04 Mar 2024
Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization Spandan Dey Md. Sahidullah G. Saha 18 11 0 10 Feb 2023
Are disentangled representations all you need to build speaker anonymization systems? Pierre Champion D. Jouvet Anthony Larcher 22 20 0 22 Aug 2022
Deep learning for time series classification Hassan Ismail Fawaz BDL AI4TS 43 35 0 01 Oct 2020
TTS Skins: Speaker Conversion via ASR Adam Polyak Lior Wolf Yaniv Taigman 13 27 0 18 Apr 2019