在无语音或含噪语音下推进语音识别
音频与语音处理
2020-03-17 v9 计算与语言
机器学习
声音
机器学习
摘要
在本文中,我们展示了以脑电图(EEG)信号为输入且不含语音信号的端到端连续语音识别(CSR)。我们实现了基于注意力模型的自动语音识别(ASR)与基于连接主义时序分类(CTC)的 ASR 系统来执行识别。我们进一步通过融合 EEG 特征展示了针对含噪语音的 CSR。
引用
@article{arxiv.1906.08871,
title = {Advancing Speech Recognition With No Speech Or With Noisy Speech},
author = {Gautam Krishna and Co Tran and Mason Carnahan and Ahmed H Tewfik},
journal= {arXiv preprint arXiv:1906.08871},
year = {2020}
}
备注
Extended version of our accepted IEEE EUSIPCO 2019 paper with additional results for CTC model based recognition. arXiv admin note: substantial text overlap with arXiv:1906.08045, arXiv:1906.08044