机构

• 自动化研究所 [4]
• 长春光学精密机械与物... [1]

采集方式

• OAI收割 [5]

内容类型

• 期刊论文 [4]
• 会议论文 [1]

发表日期

• 2023 [1]
• 2022 [1]
• 2021 [1]
• 2020 [1]
• 2010 [1]

学科主题

筛选

浏览/检索结果: 共5条，第1-5条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Two-stage deep spectrum fusion for noise-robust end-to-end speech recognition 期刊论文  OAI收割 APPLIED ACOUSTICS, 2023, 卷号: 212, 页码: 10 作者:  Fan, Cunhang;  Ding, Mingming;  Yi, Jiangyan;  Li, Jinpeng;  Lv, Zhao   |  收藏  |  浏览/下载：11/0  |  提交时间：2023/11/16 Robust end-to-end ASR  Speech enhancement  Masking and mapping  Speech distortion  Deep spectrum fusion   SpecMNet: Spectrum mend network for monaural speech enhancement 期刊论文  OAI收割 APPLIED ACOUSTICS, 2022, 卷号: 194, 页码: 9 作者:  Fan, Cunhang;  Zhang, Hongmei;  Yi, Jiangyan;  Lv, Zhao;  Tao, Jianhua   |  收藏  |  浏览/下载：45/0  |  提交时间：2022/07/25 Monaural speech enhancement  Speech distortion  Spectrum mend network  SI-SNR  BLSTM   Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition 期刊论文  OAI收割 IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 198-209 作者:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun   |  收藏  |  浏览/下载：47/0  |  提交时间：2021/03/08 Speech enhancement  Speech recognition  Training  Noise measurement  Logic gates  Acoustic distortion  Task analysis  Gated recurrent fusion  robust end-to-end speech recognition  speech distortion  speech enhancement  speech transformer   Improving speech enhancement by focusing on smaller values using relative loss 期刊论文  OAI收割 IET SIGNAL PROCESSING, 2020, 卷号: 14, 期号: 6, 页码: 374-384 作者:  Li, Hongfeng;  Xu, Yanyan;  Ke, Dengfeng;  Su, Kaile   |  收藏  |  浏览/下载：22/0  |  提交时间：2020/09/07 speech enhancement  speech intelligibility  performance evaluation  learning (artificial intelligence)  neural nets  absolute differences  speech quality  relative loss  single-channel speech enhancement  noisy speech  ideal ratio mask  phase-sensitive mask  mean square error  loss function  absolute error values  magnitude spectra  deep learning  clean speech recovery  short-time objective intelligibility  signal-to-distortion ratio  segmental signal-to-noise ratio  performance evaluation   Speech signal enhancement through wavelet domain MMSE filtering (EI CONFERENCE) 会议论文  OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China Fenghua Z.; Le Y.; Jian W.; Qiang S. 收藏  |  浏览/下载：21/0  |  提交时间：2013/03/25 A new speech enhancement system that combine robust signal enhancement and minimum signal distortion is proposed in this paper. The proposed method introduces frequency depended  parametric  MMSE filtering techniques that involve wavelet packets. Voice activity detection (VAD) is used to further distinguish speech from noise and help to adaptively remove noise components from color noise eruptive noisy speech  while perceptual criteria is also taken into account. Experimental results and objective quality measurement test results validate the proposed speech enhancement system and illustrate the benefit of the proposed wavelet domain MMSE filtering as an excellent speech enhancement method to provide sufficient noise reduction and good intelligibility and perceptual quality  without causing considerable signal distortion and musical background noise method. 2010 IEEE.