Next week several members of AGH’s Signal Processing Group will attend INTERSPEECH 2023 to present their work on joint source separation and dereverberation for automatic speech recognition and online noise reduction using deep neural architectures. Please meet our team members: Julitta Bartolewska, Mieszko Fraś, Stanisław Kacprzak, and Konrad Kowalczyk to talk about the research performed at our lab.
Wednesday 23 August 2023, 13:30 – 15:30, Poster Session on the Analysis of Speech and Audio Signals 3
Paper 2520: “Joint Blind Source Separation and Dereverberation for Automatic Speech Recognition using Delayed-Subsource MNMF with Localization Prior” by Mieszko Fraś, Marcin Witkowski, Konrad Kowalczyk
Wednesday 23 August 2023, 17:20–17:40, Oral session on Speech Coding: Intelligibility / Speech Enhancement
Paper 2177: “Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement” by Julitta Bartolewska, Stanisław Kacprzak, Konrad Kowalczyk