Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition

IF 2.4 3区计算机科学 Journal on Audio Speech and Music Processing Pub Date : 2021-04-03 DOI:10.1186/s13636-021-00215-6

Lujun Li, Yikai Kang, Yucheng Shi, Ludwig Kürzinger, Tobias Watzel, G. Rigoll

引用次数: 12

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

具有自注意机制的对抗性联合训练用于鲁棒的端到端语音识别

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Journal on Audio Speech and Music Processing Engineering-Electrical and Electronic Engineering

CiteScore

4.10

自引率

4.20%

发文量

期刊介绍： The aim of “EURASIP Journal on Audio, Speech, and Music Processing” is to bring together researchers, scientists and engineers working on the theory and applications of the processing of various audio signals, with a specific focus on speech and music. EURASIP Journal on Audio, Speech, and Music Processing will be an interdisciplinary journal for the dissemination of all basic and applied aspects of speech communication and audio processes.

期刊最新文献

A survey of technologies for automatic Dysarthric speech recognition Improving speech recognition systems for the morphologically complex Malayalam language using subword tokens for language modeling Robustness of ad hoc microphone clustering using speaker embeddings: evaluation under realistic and challenging scenarios W2VC: WavLM representation based one-shot voice conversion with gradient reversal distillation and CTC supervision YuYin: a multi-task learning model of multi-modal e-commerce background music recommendation