Comparing different machine learning approaches for disfluency structure detection in a corpus of university lectures

machine learning methods on the identification of disfluencies and their distinct structural regions over speech data. Several machine learning methods have been applied, namely Naive Bayes, Logistic Regression, Classification and Regression Trees (CARTs), J48 and Multilayer Perceptron. Our experime...

Full description

Bibliographic Details
Main Author: Medeiros, Henrique (author)
Other Authors: Moniz, Helena (author), Batista, Fernando (author), Trancoso, Isabel (author), Nunes, Luís (author)
Format: conferenceObject
Language:eng
Published: 2013
Subjects:
Machine learning
speech processing
prosodic features
automatic detection of disfluencies
Online Access:http://hdl.handle.net/10071/5355
Country:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/5355

Internet

http://hdl.handle.net/10071/5355

Similar Items