Frame-by-frame language identification in short utterances using deep neural networks
Entidad
UAM. Departamento de Tecnología Electrónica y de las ComunicacionesEditor
Elsevier LtdFecha de edición
2015-04-01Cita
10.1016/j.neunet.2014.08.006
Neural Networks 64 (2015): 49-58
ISSN
0893-6080 (print); 1879-2782 (online)DOI
10.1016/j.neunet.2014.08.006Versión del editor
http://dx.doi.org/10.1016/j.neunet.2014.08.006Materias
DNNs; I-vectors; Real-time LID; TelecomunicacionesNota
This is the author’s version of a work that was accepted for publication in Neural Networks. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neural Networks, VOL 64, (2015) DOI 10.1016/j.neunet.2014.08.006Derechos
© 2015 Elsevier B.V. All rights reservedResumen
This work addresses the use of deep neural networks (DNNs) in automatic language identification (LID) focused on short test utterances. Motivated by their recent success in acoustic modelling for speech recognition, we adapt DNNs to the problem of identifying the language in a given utterance from the short-term acoustic features. We show how DNNs are particularly suitable to perform LID in real-time applications, due to their capacity to emit a language identification posterior at each new frame of the test utterance. We then analyse different aspects of the system, such as the amount of required training data, the number of hidden layers, the relevance of contextual information and the effect of the test utterance duration. Finally, we propose several methods to combine frame-by-frame posteriors. Experiments are conducted on two different datasets: the public NIST Language Recognition Evaluation 2009 (3 s task) and a much larger corpus (of 5 million utterances) known as Google 5M LID, obtained from different Google Services. Reported results show relative improvements of DNNs versus the i-vector system of 40% in LRE09 3 second task and 76% in Google 5M LID.
Lista de ficheros
Google Scholar:González Domínguez, Javier
-
López-Moreno, Ignacio
-
Moreno, Pedro J.
-
González Rodríguez, Joaquín
Lista de colecciones del ítem
Registros relacionados
Mostrando ítems relacionados por título, autor, creador y materia.