ITEM METADATA RECORD
Title: Unsupervised learning of time-frequency patches as a noise-robust representation of speech
Authors: Van Segbroeck, Maarten ×
Van hamme, Hugo #
Issue Date: Nov-2009
Publisher: North-Holland
Series Title: Speech Communication vol:51 issue:11 pages:1124-1138
Abstract: We present a self-learning algorithm using a bottom-up based approach to automatically discover, acquire and recognize the words of a language. First, 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 for static and dynamic speech features using a spectral representation of both short and long acoustic events. By describing speech in terms of the discovered time–frequency patches, patch activations are obtained which express to what extent each patch is present across time. We then show that speaker-independent patterns appear to recur in these patch activations and how they can be discovered by applying a second NMF-based algorithm on the co-occurrence counts of activation events. By providing information about the word identity to the learning algorithm, the retrieved patterns can be associated with meaningful objects of the language. In case of a small vocabulary task, the system is able to learn patterns corresponding to words and subsequently detects the presence of these words in speech utterances. Without the prior requirement of expert knowledge about the speech as is the case in conventional automatic speech recognition, we illustrate that the learning algorithm achieves a promising accuracy and noise robustness.
Description: Van Segbroeck M., Van hamme H., ''Unsupervised learning of time-frequency patches as a noise-robust representation of speech'', Speech communication, vol. 51, no. 11, pp. 1124-1138, November 2009.
ISSN: 0167-6393
Publication status: published
KU Leuven publication type: IT
Appears in Collections:ESAT - PSI, Processing Speech and Images
× corresponding author
# (joint) last author

Files in This Item:
File Description Status SizeFormat
mvansegb.pdf Submitted 1046KbAdobe 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.

© Web of science