A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition
2018
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Preserved Fulltext
These features are normalized on a per-utterance basis. • The spectral features are mean-and variance-normalized. • The spatial features are mean-normalized. Simply feeding multi-microphone STFT coefficients resulted in performance degradation (see Tab. 2).
doi:10.1109/icassp.2018.8462081
dblp:conf/icassp/YoshiokaECA18
fatcat:n4thrqcn7jbs5g64juxjehe36i