全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
外文文献 中文文献
筛选条件:

1. A systematic study of DNN based speech enhancement in reverberant and reverberant-noisy environments NSTL国家科技图书文献中心

Heming Wang |  Ashutosh Pandey... -  《Computer speech & language》 - 2025,89(Jan.) - 101677.1~101677.12 - 共12页

摘要: less effective for speech dereverberation. In this |  improvements for the task of speech enhancement, where deep |  speech from noisy and reverberant mixtures. Most of the |  larger window sizes is helpful for dereverberation, and | Deep learning has led to dramatic performance
关键词: Speech enhancement |  Speech dereverberation |  Self-attention |  ARN |  DC-CRN

2. Deep informed spatio-spectral filtering for multi-channel speech extraction against steering vector uncertainties NSTL国家科技图书文献中心

Luo X. |  Ke Y.... -  《Applied acoustics》 - 2025,228(Jan.) - 1.1~1.10 - 共10页

摘要:-spectral filtering for multi-channel speech extraction |  directional speech with only its early reflections. To |  than other baseline methods in terms of speech | © 2024 Elsevier LtdAdaptive beamforming |  combined with post-filtering is one of the most widely
关键词: Deep informed filtering |  Speech dereverberation |  Speech extraction |  Steering vector uncertainties

3. Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-Driven Diffusion NSTL国家科技图书文献中心

Jian Ma |  Wenguan Wang... -  《Computer Vision - ECCV 2024,Part XVIII》 -  European Conference on Computer Vision - 2025, - 331~349 - 共19页

摘要: dereverberation is effective in improving audio intelligibility |  dereverberation called dereverberator. The derever-berator |  two standard benchmarks, i.e., SoundSpaces-Speech | Visual acoustic matching (VAM) is pivotal for |  enhancing the immersive experience, and the task of
关键词: Visual acoustic matching |  Dereverberation |  Audio style transfer |  Mutual learning |  Diffusion

4. Distributed speech dereverberation using weighted prediction error NSTL国家科技图书文献中心

Yang, Ziye |  Zhang, Mengfei... -  《Signal Processing: The Official Publication of the European Association for Signal Processing (EURASIP)》 - 2024,225 - ARTN 109577~ - 共5页

摘要:Speech dereverberation aims to alleviate the |  introduces a distributed speech dereverberation method that |  speech dereverberation in dispersed microphone node |  dereverberation. However, in scenarios where microphone nodes |  negative impact of late reverberant components. The
关键词: Speech dereverberation |  Distributed estimation |  The weighted prediction error method |  Far-field scenario |  SIGNAL ESTIMATION

5. RVAE-EM: GENERATIVE SPEECH DEREVERBERATION BASED ON RECURRENT VARIATIONAL AUTO-ENCODER AND CONVOLUTIVE TRANSFER FUNCTION NSTL国家科技图书文献中心

Pengyu Wang |  Xiaofei Li -  《ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), Vol.2: Seoul, South Korea.14-19 April 2024》 -  IEEE International Conference on Acoustics, Speech and Signal Processing - 2024, - 496~500 - 共5页

摘要:-channel speech dereverberation show that the proposed |  intelligibility of speech. In this work, we propose a generative |  dereverberation method. Our approach is based on a probabilistic |  the clean speech. And our target is the maximum a |  posteriori (MAP) estimation of clean speech, which is
关键词: Speech enhancement |  speech dereverberation |  variational auto-encoder |  convolutive transfer function |  unsuper-vised learning

6. DUAL-PATH MINIMUM-PHASE AND ALL-PASS DECOMPOSITION NETWORK FOR SINGLE CHANNEL SPEECH DEREVERBERATION NSTL国家科技图书文献中心

Xi Liu |  Szu-Jui Chen... -  《ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), Vol.2: Seoul, South Korea.14-19 April 2024》 -  IEEE International Conference on Acoustics, Speech and Signal Processing - 2024, - 1261~1265 - 共5页

摘要: (DNN), many DNN-based speech dereverberation |  learning-based dereverberation methods solely focus on |  useful for dereverberation. In this paper, we propose a |  channel speech. First, we decompose speech signal into | With the development of deep neural networks
关键词: Blind speech dereverberation |  cepstral analysis |  minimum-phase |  all-pass system

7. Monaural Speech Dereverberation Using Deformable Convolutional Networks NSTL国家科技图书文献中心

Vinay Kothapally |  John H. L. Hansen -  《IEEE/ACM transactions on audio, speech, and language processing》 - 2024,32 - 1712~1723 - 共12页

摘要: speech dereverberation systems that aim to minimize | -channel speech dereverberation system that uses |  speech dereverberation task. We compare the performance |  speech quality and intelligibility when captured by a |  distortions introduced into speech captured in naturalistic
关键词: Speech enhancement |  Convolution |  Microphones |  Filtering |  Reflection |  Distortion |  Task analysis

8. Speech Dereverberation With Frequency Domain Autoregressive Modeling NSTL国家科技图书文献中心

Anurenjan Purushotha... |  Debottam Dutta... -  《IEEE/ACM transactions on audio, speech, and language processing》 - 2024,32 - 29~38 - 共10页

摘要: framework of speech dereverberation for improving the | Speech applications in far-field real world |  reverberation. The task of dereverberation constitutes an |  speech recognition (ASR). We propose a unified |  speech quality and the ASR performance using the
关键词: Frequency-domain analysis |  Reverberation |  Task analysis |  Convolution |  Predictive models |  Mirrors |  Analytical models

9. Plug-and-Play WPE Guided by Deep Spectrum Estimation for Speech Dereverberation NSTL国家科技图书文献中心

Ziye Yang |  Jie Chen... -  《2024 IEEE International Conference on Signal Processing,Communications and Computing》 -  IEEE International Conference on Signal Processing,Communications and Computing - 2024, - 1~5 - 共5页

摘要:Speech dereverberation aims to attenuate the |  represents an innovative approach to dereverberation with |  effects of late-reverberant components. While the plug | -and-play weighted prediction error (PnPWPE) method |  exceptional performance, it can be further enhanced from
关键词: Additive noise |  Accuracy |  Estimation |  Manuals |  Artificial neural networks |  Signal processing |  Speech processing |  Spectral analysis

10. Multichannel Linear Prediction-Based Speech Dereverberation Considering Sparse and Low-Rank Priors NSTL国家科技图书文献中心

Taihui Wang |  Feiran Yang... -  《IEEE/ACM transactions on audio, speech, and language processing》 - 2024,32 - 1724~1735 - 共12页

摘要: linear prediction (MCLP)-based speech dereverberation |  maximum-likelihood criterion, speech dereverberation is |  priors of speech spectrograms. We utilize the complex | This article addresses the multi-channel |  problem by jointly considering the sparsity and low-rank
关键词: Speech processing |  Reverberation |  Microphones |  Time-frequency analysis |  Shape |  Indexes |  Cost function
检索条件Speech dereverberation
  • 检索词扩展

NSTL主题词

  • NSTL学科导航