Publication Details
Hierarchical Neural Net Architectures for Feature Extraction in ASR
Speech recognition, Feature extraction, Neural network architecture
The paper is on the incorporation of Bottle-Neck features into hierarchical architecture of classifiers. This architecture was used for feature extraction for LVCSR of meetings and the resulting features were evaluated on NIST RT'05 and RT'07 test sets.
This paper presents the use of neural net hierarchy for feature extraction in ASR. The recently proposed Bottle-Neck feature extraction is extended and used in hierarchical structures to enhance the discriminative property of the features. Although many ways of hierarchical classification/feature extraction have been proposed, we restricted ourselves to use the outputs of the first stage neural network together with its inputs. This approach is evaluated on meeting speech recognition using RT'05 and RT'07 test sets. The evaluated hierarchical feature extraction brings consistent improvement over the use of just the first level neural net.
@INPROCEEDINGS{FITPUB9363, author = "Franti\v{s}ek Gr\'{e}zl and Martin Karafi\'{a}t", title = "Hierarchical Neural Net Architectures for Feature Extraction in ASR", pages = "1201--1204", booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)", journal = "Proceedings of Interspeech - on-line", volume = 2010, number = 9, year = 2010, location = "Makuhari, Chiba, JP", publisher = "International Speech Communication Association", ISBN = "978-1-61782-123-3", ISSN = "1990-9772", language = "english", url = "https://www.fit.vut.cz/research/publication/9363" }