Archives
Tomorrow our team members are heading to Incheon in South Korea to attend the upcoming INTERSPEECH 2022 conference. Meet Magdalen Rybicka, Julitta Bartolewska, Mieszko Fraś, Mateusz Guzik, Marcin Witkowski, Stanisław Kacprzak and Konrad Kowalczyk personally at INTERSPEECH 2022 to talk about their research on speaker diarization, speech separation, dereverberation and denoising using deep learning, hybrid, […]
Read More We are very proud to announce that 4 research papers authored by members of the AGH Signal Processing Group were accepted for presentation at the Annual Conf. Int. Speech Communication Association (INTERSPEECH) to be held in September of 2022 in Incheon, South Korea. Julitta Bartolewska, Stanisław Kacprzak, Konrad Kowalczyk, “Refining DNN-based Mask Estimation using CGMM-based […]
Read More
We are very happy to invite all participants of IEEE ICASSP 2022 conference to see 4 presentations of the members of AGH Signal Processing Group. Presentations are: 1. Marcin Witkowski and Konrad Kowalczyk, SPLIT BREGMAN APPROACH TO LINEAR PREDICTION BASED DEREVERBERATION WITH ENFORCED SPEECH SPARSITY, Session: System Identification and Reverberation ReductionPresentation Time: Sun, 8 May, […]
Read More
We are very happy that 3 papers authored by members of AGH Signal Processing Group were accepted for presentation at IEEE ICASSP 2022 conference. Stanisław Kacprzak, Magdalena Rybicka, Konrad Kowalczyk, “Spoken Language Recognition with Cluster-based Modeling“, accepted for IEEE ICASSP 2022. Mieszko Fraś, Marcin Witkowski, Konrad Kowalczyk, “Convolutional Weighted Minimum Mean Square Error Filter for […]
Read More
Join us at IEEE Intternational Workshop on Multimedia Signal Processing 2021 to be held in Tampere, Finland, where Julitta Bartolewska and Mateusz Guzik will give in-person presentations: Incorporation of Localization Information for Sound Source Separation in Spherical Harmonic Domain by Mateusz Guzik, Mieszko Fraś, and Konrad Kowalczyk during the session on Friday, October 8, 8:30-9:30. […]
Read More
Join us at INTERSPEECH 2021 conference in Brno, where Magdalena Rybicka and Mieszko Fraś will give 2 in-person oral presentations on: Spine2Net: SpineNet with Res2Net and Time-Squeeze-and-Excitation Blocks for Speaker Recognition by Magdalena Rybicka, Jesús Villalba, Piotr Żelasko, Najim Dehak, and Konrad Kowalczyk during the session: Embedding and Network Architecture for Speaker Recognition on Tuesday, […]
Read More
Join AGH Signal Processing group at the European Signal Processing Conference 2021 and visit 3 presentations by Stanisław Kacprzak, Marcin Witkowski, and former group member Daniel Krause on the outcome of two current projects MLSAP and APDAS: Stanisław Kacprzak will talk about Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording […]
Read More
The outcome of the Machine Learning for Spatial Audio Processing project will be presented by mgr inż. Daniel Krause at EUSIPCO 2020 virtual conference, which starts this week, with papers on “Comparison of Convolution Types in CNN-based Feature Extraction for Sound Source Localization” and “Feature Overview for Joint Modeling of Sound Event Detection and Localization […]
Read More
On Thursday, October the 29th, mgr inż. Magdalena Rybicka will present the paper entitled “On Parameter Adaptation in Softmax-based Cross-Entropy Loss for Improved Convergence Speed and Accuracy in DNN-based Speaker Recognition” at the INTERSPEECH 2020 conference. Congratulations Magda on paper acceptance and great presentation.
Read More