DSpace Repository

A Robust Multiple Feature Approach To Endpoint Detection In Car Environment Based On Advanced Classifiers

Show simple item record

dc.contributor Universitat de Vic. Escola Politècnica Superior
dc.contributor Universitat de Vic. Grup de Recerca en Tecnologies Digitals
dc.contributor International Work-Conference on Artificial Neural Networks (8ena : Barcelona : 2005)
dc.contributor.author Comas, C.
dc.contributor.author Monte-Moreno, Enric
dc.contributor.author Solé-Casals, Jordi
dc.date.accessioned 2013-02-13T13:01:14Z
dc.date.available 2013-02-13T13:01:14Z
dc.date.created 2005
dc.date.issued 2005
dc.identifier.citation Cabestany, A. Prieto, F. Sandoval, editors. A robust multiple feature approach to endpoint detection in car environment based on advanced classifiers. Computational intelligence and bioinspired systems, proceedings; LECTURE NOTES IN COMPUTER SCIENCE; 8th international work-conference on artificial neural networks; JUN 08-10, 2005; BERLIN; HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY: SPRINGER-VERLAG BERLIN; 2005. NR: 7; TC: 0; J9: LECT NOTE COMPUT SCI; PG: 7; GA: BCO15. ca_ES
dc.identifier.isbn 978-3-540-26208-4
dc.identifier.uri http://hdl.handle.net/10854/2077
dc.description.abstract In this paper we propose an endpoint detection system based on the use of several features extracted from each speech frame, followed by a robust classifier (i.e Adaboost and Bagging of decision trees, and a multilayer perceptron) and a finite state automata (FSA). We present results for four different classifiers. The FSA module consisted of a 4-state decision logic that filtered false alarms and false positives. We compare the use of four different classifiers in this task. The look ahead of the method that we propose was of 7 frames, which are the number of frames that maximized the accuracy of the system. The system was tested with real signals recorded inside a car, with signal to noise ratio that ranged from 6 dB to 30dB. Finally we present experimental results demonstrating that the system yields robust endpoint detection. ca_ES
dc.format application/pdf
dc.format.extent 8 p. ca_ES
dc.language.iso eng ca_ES
dc.publisher Springer ca_ES
dc.rights (c) Springer, 2005
dc.rights Tots els drets reservats ca_ES
dc.subject.other Veu, Processament de ca_ES
dc.title A Robust Multiple Feature Approach To Endpoint Detection In Car Environment Based On Advanced Classifiers ca_ES
dc.type info:eu-repo/semantics/conferenceObject ca_ES
dc.relation.publisherversion http://www.springer.com/computer/theoretical+computer+science/book/978-3-540-26208-4
dc.rights.accesRights info:eu-repo/semantics/openAccess ca_ES

Files in this item

Show simple item record

Search RIUVic


Advanced Search

Browse

Statistics