TU2.PA3.7
Estimation of output SI-SDR solely from enhanced speech signals in diffusion-based generative speech enhancement method
Satoru Emura, Kyoto university of advanced science, Japan
Session:
TU2.PA3: Acoustic Noise Reduction and Control, Enhancement of Audio and Speech Poster
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Poster Area 3
Presentation Time:
Tue, 27 Aug, 14:30 - 16:10 France Time (UTC +1)
Session Co-Chairs:
Simon Doclo, Oldenburg University and Dirk Slock, EURECOM
Presentation
Discussion
Resources
No resources available.
Session TU2.PA3
TU2.PA3.1: FILTER SYNTHESIS FOR ROBUST FEEDBACK ACTIVE NOISE CONTROL USING NON-UNIFORMLY DISCRETIZED FOURIER SPECTRA
Willem Alexander Klatt, Ruhr-Universität Bochum, Germany; Michael Bürger, WS Audiology, Germany; Rainer Martin, Ruhr-Universität Bochum, Germany; Henning Puder, Technische Universität Darmstadt, Germany
TU2.PA3.2: Frequency-domain Feedback Active Noise Control using Weighted LMS Algorithm
Ryota Noguchi, Yosuke Sugiura, Tetsuya Shimamura, Saitama university, Japan
TU2.PA3.3: Spline Adaptive Exponential Functional Link Filter for Nonlinear Acoustic Echo Cancellation
Alireza Nezamdoust, Sapienza University of Rome and Johannes Kepler University of Linz, Italy; Michele Scarpiniti, Aurelio Uncini, Danilo Comminiello, Sapienza University of Rome, Italy
TU2.PA3.4: Attention-based Dual Stream Interactive Network for Nonlinear Residual Echo Suppression
Kai Xie, Ziye Yang, Jie Chen, Northwestern Polytechnical University, China; Junjie Li, China Coal Shaanxi Energy & Chemical Group Co.,Ltd., China
TU2.PA3.5: Normalized Multichannel Frequency-Domain LMS Filter With Nearest Kronecker Product Decomposition for Blind Identification of Low-Rank Acoustic Systems
Zhimin Qiu, Hongsen He, Southwest University of Science and Technology, China; Jingdong Chen, Northwestern Polytechnical University, China; Jacob Benesty, University of Quebec, Canada; Yi Yu, Southwest University of Science and Technology, China
TU2.PA3.6: SINGLE-CHANNEL SPEECH RESTORATION USING DEEP SPEECH FEATURES RECONSTRUCTION
Amos Schreibman, Elior Hadad, Boris Rubenchik, Moshe Tzur, Eli Tzirkel-Hancock, General Motors Ltd, Israel
TU2.PA3.7: Estimation of output SI-SDR solely from enhanced speech signals in diffusion-based generative speech enhancement method
Satoru Emura, Kyoto university of advanced science, Japan
TU2.PA3.8: Reference Channel Selection by Multi-Channel Masking for End-to-End Multi-Channel Speech Enhancement
Wang Dai, Tampere University, Finland; Xiaofei Li, Westlake University & Westlake Institute for Advanced Study, China; Archontis Politis, Tuomas Virtanen, Tampere University, Finland