Syllable lattices as a basis for a children's speech reading tracker
Entity
UAM. Departamento de Ingeniería InformáticaDate
2007Citation
INTERSPEECH 2007: 8th Annual Conference of the International Speech Communication Association. ISCA, 2007. 198-201ISSN
1990-9772Editor's Version
http://www.isca-speech.org/archive/interspeech_2007/i07_0198.htmlSubjects
Speech recognition; Children’s speech; Reading tracker; Token passing; SVM; TelecomunicacionesNote
Proceedings of Interspeech 2007, Antwerp (Belgium)Rights
© 2007 ISCAAbstract
In this paper we present an algorithm that makes use of
information contained in syllable lattices to significantly
reduce the classification error rate of a children’s speech
reading tracker. The task is to verify whether each word in a
reference string was actually spoken. A syllable graph is
generated from the reference word string to represent
acceptable pronunciation alternatives. A syllable based
continuous speech recognizer is used to generate a syllable
lattice. The best alignment between the reference graph and
the syllable lattice is determined using a dynamic
programming algorithm. The speech vectors that are aligned
with each syllable are used as features for Support Vector
Machine classifiers that accept or reject each syllable in the
aligned path.
Experimental results over three children’s speech
corpora show that this algorithm can substantially reduce the
classification error rate over the standard word based tracker
and over a simple best-path syllable based tracker.
Files in this item
Google Scholar:Bolaños Alonso, Daniel
-
Ward, Wayne H.
-
Van Vuuren, Sarel
-
Garrido Salas, Javier
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.