Exploiting lightweight neural post-filtering for directional speech enhancement
Authors:
- Tianchi SunTSTianchi Sun
- Xiaobin RongXRXiaobin Rong
- Dahan WangDWDahan Wang
- Yuxiang HuYHYuxiang Hu
- Kai ChenKCKai Chen
- Jing LuJLJing Lu
- 30 May 2025
- journal article
- Published by Elsevier in Applied Acoustics
- Vol. 239
Abstract
No abstract availableFunding Information
- Nanjing University
- National Natural Science Foundation of China (12274221)
This publication has 24 references indexed in Scilit:
- Exploiting spatial information and target speaker phoneme loss for multichannel directional speech enhancement and recognitionComputer Speech & Language, 2025
- Enhancing real-world far-field speech with supervised adversarial trainingApplied Acoustics, 2024
- Nonspeech7k dataset: Classification and analysis of human non‐speech soundIET Signal Processing, 2023
- Time-Variance Aware Dynamic Kernel Generation for Real-Time Acoustic Echo CancellationIEEE Signal Processing Letters, 2022
- Exploiting the directional coherence function for multichannel source extractionSpeech Communication, 2021
- Time-Domain Multi-Modal Bone/Air Conducted Speech EnhancementIEEE Signal Processing Letters, 2020
- rVAD: An unsupervised segment-based robust voice activity detection methodComputer Speech & Language, 2020
- Hybrid probabilistic adaptation mode controller for generalized sidelobe cancellers applied to multi-microphone speech enhancementDigital Signal Processing, 2014
- Analysis of CFA-BF: Novel combined fixed/adaptive beamforming for robust speech recognition in real car environmentsSpeech Communication, 2009
- A short proof of the equivalence of LCMV and GSC beamformingIEEE Signal Processing Letters, 2002