2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

SPE-51: Speech Enhancement 7: Single-channel Processing

Session Type: Poster
Time: Friday, 11 June, 13:00 - 13:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Ann Spriet, GOODIX Technology Inc.
 
 SPE-51.1: TSTNN: TWO-STAGE TRANSFORMER BASED NEURAL NETWORK FOR SPEECH ENHANCEMENT IN THE TIME DOMAIN
         Kai Wang; Concordia University
         Bengbeng He; Concordia University
         Wei-Ping Zhu; Concordia University
 
 SPE-51.2: SELF-ATTENTION GENERATIVE ADVERSARIAL NETWORK FOR SPEECH ENHANCEMENT
         Huy Phan; Queen Mary University of London
         Huy Le Nguyen; Ho Chi Minh City University of Technology
         Oliver Chén; University of Oxford
         Philipp Koch; University of Lübeck
         Ngoc Q. K.\ Duong; InterDigital R&D France
         Ian McLoughlin; Singapore Institute of Technology
         Alfred Mertins; University of Lübeck
 
 SPE-51.3: NEURAL KALMAN FILTERING FOR SPEECH ENHANCEMENT
         Wei Xue; JD AI Research
         Gang Quan; JD AI Research
         Chao Zhang; JD AI Research
         Guohong Ding; JD AI Research
         Xiaodong He; JD AI Research
         Bowen Zhou; JD AI Research
 
 SPE-51.4: NEURAL NOISE EMBEDDING FOR END-TO-END SPEECH ENHANCEMENT WITH CONDITIONAL LAYER NORMALIZATION
         Zhihui Zhang; Wuhan University of Technology
         Xiaoqi Li; Wuhan University of Technology
         Yaxing Li; Wuhan University of Technology
         Yuanjie Dong; Wuhan University of Technology
         Dan Wang; Wuhan University of Technology
         Shengwu Xiong; Wuhan University of Technology
 
 SPE-51.5: PERCEPTUAL LOSS BASED SPEECH DENOISING WITH AN ENSEMBLE OF AUDIO PATTERN RECOGNITION AND SELF-SUPERVISED MODELS
         Saurabh Kataria; Johns Hopkins University
         Jesús Villalba; Johns Hopkins University
         Najim Dehak; Johns Hopkins University
 
 SPE-51.6: TOWARDS AN ASR APPROACH USING ACOUSTIC AND LANGUAGE MODELS FOR SPEECH ENHANCEMENT
         Khandokar Md. Nayem; Indiana University
         Donald S. Williamson; Indiana University