ITEM METADATA RECORD
Title: Applying non-negative matrix factorization on time-frequency reassignment spectra for missing data mask estimation
Authors: Van Segbroeck, Maarten
Van hamme, Hugo #
Issue Date: 2009
Host Document: Proceedings Interspeech2009
Conference: Interspeech2009 - 10th annual conference of the international speech communication association location:Brighton, UK date:6-10 September 2009
Abstract: The application of Missing Data Theory (MDT) has shown to
improve the robustness of automatic speech recognition (ASR)
systems. A crucial part in a MDT-based recognizer is the computation
of the reliability masks from noisy data. To estimate
accurate masks in environments with unknown, non-stationary
noise statistics, we need to rely on a strong model for the speech.
In this paper, an unsupervised technique using non-negative matrix
factorization (NMF) discovers phone-sized time-frequency
patches into which speech can be decomposed. The input matrix
for the NMF is constructed using a high resolution and
reassigned time-frequency representation. This representation
facilitates an accurate detection of the patches that are active
in unseen noisy speech. After further denoising of the patch
activations, speech and noise can be reconstructed from which
missing feature masks are estimated. Recognition experiments
on the Aurora2 database demonstrate the effectiveness of this
technique.
Description: Van Segbroeck M., Van hamme H., ''Applying non-negative matrix factorization on time-frequency reassignment spectra for missing data mask estimation'', Proceedings Interspeech2009 - 10th annual conference of the international speech communication association, 4 pp., September 6-10, 2009, Brighton, UK.
Publication status: published
KU Leuven publication type: IC
Appears in Collections:ESAT - PSI, Processing Speech and Images
# (joint) last author

Files in This Item:
File Description Status SizeFormat
mvansegb.pdf Published 281KbAdobe PDFView/Open Request a copy

These files are only available to some KU Leuven Association staff members

 




All items in Lirias are protected by copyright, with all rights reserved.