Disfluency Detection Based on Prosodic Features for University Lectures

This paper focuses on the identification of disfluent sequences and their distinct structural regions, based on acoustic and prosodic features. Reported experiments are based on a corpus of university lectures in European Portuguese, with roughly 32h, and a relatively high percentage of disfluencies...

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:
prosodic features
automatic disfluency detection
corpus of university lectures
machine learning
Online Access:http://hdl.handle.net/10071/5351
Country:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/5351

Internet

http://hdl.handle.net/10071/5351

Similar Items