Filters








3 Hits in 5.0 sec

Square root-based multi-source early PSD estimation and recursive RETF update in reverberant environments by means of the orthogonal Procrustes problem

Thomas Dietzen, Simon Doclo, Marc Moonen, Toon Van Waterschoot
2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
The estimated unitary matrix and early PSD square roots further allow to recursively update the RETF estimate, which is not inherently possible in the conventional approach.  ...  State-of-the-art approaches to multisource early PSD estimation, given an estimate of the associated relative early transfer functions (RETFs), conventionally minimize the approximation error defined with  ...  The estimated unitary matrix and early PSD square roots further allow us to recursively update the RETF estimate, which is not inherently possible in the conventional approach.  ... 
doi:10.1109/taslp.2020.2966891 fatcat:mdgbshdanrgopjxhnkaa4fs52m

Cognitive-driven convolutional beamforming using EEG-based auditory attention decoding [article]

Ali Aroudi, Marc Delcroix, Tomohiro Nakatani, Keisuke Kinoshita, Shoko Araki, Simon Doclo
2020 arXiv   pre-print
combines a neural-network-based mask estimator, weighted minimum power distortionless response convolutional beamformers and AAD.  ...  Auditory attention decoding (AAD) methods allow to identify the target speaker which the listener is attending to from single-trial EEG recordings.  ...  To resolve this ambiguity, we align the masks obtained for each microphone based on the least-squares error.  ... 
arXiv:2005.04669v1 fatcat:nvgdko2hyfewpnqps2u5lxzvdq

ML Estimation and CRBs for Reverberation, Speech and Noise PSDs in Rank-Deficient Noise-Field [article]

Yaron Laufer, Bracha Laufer-Goldshtein, Sharon Gannot
2020 arXiv   pre-print
jointly estimates the reverberation and noise PSDs.  ...  The first is a non-blocking-based estimator which jointly estimates the speech, reverberation and noise PSDs, and the second is a blocking-based estimator, which first blocks the speech signal and then  ...  This method was further extended in [16] to jointly estimate the various PSDs along with the relative early transfer function (RETF) vector, using an alternating least-squares method.  ... 
arXiv:1907.09250v2 fatcat:oo5pgn5ecvbszjftsaeq7adjia