Mieszko Fras

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 8

Top Topics

Minimum Mean Square Error

Speech Recognition

Top Venues

IEEE Signal Process. Lett.

Publications

Mieszko Fras, Konrad Kowalczyk
Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors. IEEE ACM Trans. Audio Speech Lang. Process. 32 (2024)
Mieszko Fras, Marcin Witkowski, Konrad Kowalczyk
Joint Blind Source Separation and Dereverberation for Automatic Speech Recognition using Delayed-Subsource MNMF with Localization Prior. INTERSPEECH (2023)
Mieszko Fras, Konrad Kowalczyk
Convolutional Weighted Parametric Multichannel Wiener Filter for Reverberant Source Separation. IEEE Signal Process. Lett. 29 (2022)
Mieszko Fras, Marcin Witkowski, Konrad Kowalczyk
Convolutional Weighted Minimum Mean Square Error Filter for Joint Source Separation and Dereverberation. ICASSP (2022)
Mieszko Fras, Marcin Witkowski, Konrad Kowalczyk
Convolutive Weighted Multichannel Wiener Filter Front-end for Distant Automatic Speech Recognition in Reverberant Multispeaker Scenarios. INTERSPEECH (2022)
Mateusz Guzik, Mieszko Fras, Konrad Kowalczyk
Incorporation of Localization Information for Sound Source Separation in Spherical Harmonic Domain. MMSP (2021)
Mieszko Fras, Konrad Kowalczyk
Maximum a Posteriori Estimator for Convolutive Sound Source Separation with Sub-Source Based NTF Model and the Localization Probabilistic Prior on the Mixing Matrix. ICASSP (2021)
Mieszko Fras, Marcin Witkowski, Konrad Kowalczyk
Combating Reverberation in NTF-Based Speech Separation Using a Sub-Source Weighted Multichannel Wiener Filter and Linear Prediction. Interspeech (2021)