UNIGE document Book Chapter
previous document  unige:99298  next document
add to browser collection
Title

Lightweight Spoken Utterance Classification with CFG, tf-idf and Dynamic Programming

Authors
Published in Camelin, Nathalie, Estève, Yannick, Martín-Vide, Carlos. Statistical Language and Speech Processing (SLSP): Springer. 2017, p. 143-154
Collection Lecture Notes in Computer Science; 10583
Abstract We describe a simple spoken utterance classification method suitable for data-sparse domains which can be approximately described by CFG grammars. The central idea is to perform robust matching of CFG rules against output from a large-vocabulary recogniser, using a dynamic programming method which optimises the tf-idf score of the matched grammar string. We present results of experiments carried out on a substantial CFG-based medical speech translator and the publicly available Spoken CALL Shared Task. Robust utterance classification using the tf-idf method strongly outperforms plain CFG-based recognition for both domains. When comparing with Naive Bayes classifiers trained on data sampled from the CFG grammars, the tf-idf/dynamic programming method is much better on the complex speech translation domain, but worse on the simple Spoken CALL Shared Task domain.
Keywords Speech recognitionSpoken utterance classificationRobustnessContext-free grammarTf-idfMedical applications
Identifiers
ISBN: 978-3-319-68455-0
Note 5th International Conference, SLSP 2017, Le Mans, France, October 23–25, 2017, Proceedings
Full text
Structures
Citation
(ISO format)
RAYNER, Emmanuel, TSOURAKIS, Nikolaos, GERLACH, Johanna. Lightweight Spoken Utterance Classification with CFG, tf-idf and Dynamic Programming. In: Camelin, Nathalie, Estève, Yannick, Martín-Vide, Carlos (Ed.). Statistical Language and Speech Processing (SLSP). [s.l.] : Springer, 2017. p. 143-154. (Lecture Notes in Computer Science; 10583) https://archive-ouverte.unige.ch/unige:99298

59 hits

0 download

Update

Deposited on : 2017-11-21

Export document
Format :
Citation style :