< Back to previous page
Researcher
Nilesh Madhu
- Keywords:signal detection, statistical signal processing, microphone arrays, signal processing, source localisation, beamforming
- Disciplines:Telecommunication and remote sensing, Image and language processing, Biomedical image processing, Audio and speech processing, Audio and speech computing, Biomedical signal processing, Human health engineering, Pattern recognition and neural networks
Affiliations
- Department of Electronics and information systems (Department)
Member
From1 Oct 2017 → Today
Projects
1 - 8 of 8
- Deep-Learning based Joint Audio, Video Processing for Augmented ListeningFrom1 Oct 2022 → TodayFunding: BOF - mobility
- NeLF: Next Level Flemish Speech RecognitionFrom1 Oct 2022 → TodayFunding: FWO Strategic Basic Research (SBO)
- Enabling Effortless Communication Under Adverse Conditions by Exploitation of Direction-of-Arrival Estimates and Other A-Priori Knowledge in Joint Acoustic Source Separation and DereverberationFrom1 Nov 2020 → TodayFunding: FWO fellowships
- Improving group musical experiences in virtual reality, using a biofeedback control systemFrom1 Oct 2020 → TodayFunding: BOF - projects
- Hearing augmentation based on environment classification and auditory scene analysisFrom1 Oct 2020 → TodayFunding: BOF - mobility
- Robust speech capture and enhancement using ad hoc distributed microphone arrays by integrating and embedding domain-specific signal models within deep-learning frameworksFrom1 Jan 2020 → 31 Dec 2023Funding: FWO research project (including WEAVE projects)
- Robust language diarization in reverberant and noisy environmentsFrom1 Oct 2019 → 1 Oct 2019Funding: BOF - doctoral mandates
- Hybrid solutions for the one-microphone speech enhancement problemFrom1 Jan 2019 → 31 Dec 2022Funding: BOF - projects
Publications
1 - 10 of 60
- On the disentanglement and robustness of self-supervised speech representations(2024)
Authors: Yanjue Song, Doyeon Kim, Nilesh Madhu, Hong-Goo Kang
Pages: 662 - 666 - Robust detection of background acoustic scene in the presence of foreground speech(2024)
Authors: Siyuan Song, Yanjue Song, Nilesh Madhu
- Spatially selective speaker separation using a DNN with a location dependent feature extraction(2024)
Authors: Alexander Bohlender, Ann Spriet, Wouter Tirry, Nilesh Madhu
Pages: 930 - 945 - Investigating spherical head models to simulate binaural room impulses for training deep neural networks(2023)
Authors: Jasper Maes, Siyuan Song, Stijn Kindt, Pieter-Jan Maes, Bruno Masiero, Nilesh Madhu
Pages: 104 - 108 - Margin-mixup : a method for robust speaker verification in multi-speaker audio(2023)
Authors: Jenthe Thienpondt, Nilesh Madhu, Kris Demuynck
Number of pages: 1 - Enhancing multichannel laser-doppler vibrometry signals with application to (carotid-femoral) pulse transit time estimation(2023)
Authors: Simeon Beeckman, Yanlu Li, Soren Aasmul, Roel Baets, Pierre Boutouyrie, Patrick Segers, Nilesh Madhu
Number of pages: 1 - Detecting translocation of DNA nanostructures through nanopores : first steps towards structural barcode readout(2023)
Authors: Pratima Upretee, S Santermans, K Martens, J Gevers, S Marion, W Van Den Bosch, Jan Fostier, Nilesh Madhu
Pages: 1205 - 1209 - Ad hoc distributed microphones clustering : a comparative analysis on using coherence and signal-specific features(2023)
Authors: Stijn Kindt, Martijn Meeldijk, Nilesh Madhu
Pages: 11 - 15 - Comparative study of LC3plus and Lyra codec on DNN-based source localisation for hearing aids(2023)
Authors: Siyuan Song, Stijn Kindt, Jasper Maes, Alexander Bohlender, Nilesh Madhu
Pages: 71 - 75 - Aiding speech harmonic recovery in DNN-based single channel noise reduction using cepstral excitation manipulation (CEM) components(2023)
Authors: Yanjue Song, Nilesh Madhu
Number of pages: 1