Low-resource language recognition using a fusion of phoneme posteriorgram counts, acoustic and glottal-based i-vectors

D'haro Enríquez, Luis Fernando and Córdoba Herralde, Ricardo de and Caraballo Morcillo, Miguel Ángel and Pardo Muñoz, José Manuel (2013). Low-resource language recognition using a fusion of phoneme posteriorgram counts, acoustic and glottal-based i-vectors. In: "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", 26/05/2013 - 31/05/2013, Vancouver, Canada. pp. 6852-6856.

Description

Title: Low-resource language recognition using a fusion of phoneme posteriorgram counts, acoustic and glottal-based i-vectors
Author/s:
  • D'haro Enríquez, Luis Fernando
  • Córdoba Herralde, Ricardo de
  • Caraballo Morcillo, Miguel Ángel
  • Pardo Muñoz, José Manuel
Item Type: Presentation at Congress or Conference (Article)
Event Title: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Event Dates: 26/05/2013 - 31/05/2013
Event Location: Vancouver, Canada
Title of Book: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Título de Revista/Publicación: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Date: 2013
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería Electrónica
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (858kB)

Abstract

This paper presents a description of our system for the Albayzin 2012 LRE competition. One of the main characteristics of this evaluation was the reduced number of available files for training the system, especially for the empty condition where no training data set was provided but only a development set. In addition, the whole database was created from online videos and around one third of the training data was labeled as noisy files. Our primary system was the fusion of three different i-vector based systems: one acoustic system based on MFCCs, a phonotactic system using trigrams of phone-posteriorgram counts, and another acoustic system based on RPLPs that improved robustness against noise. A contrastive system that included new features based on the glottal source was also presented. Official and postevaluation results for all the conditions using the proposed metrics for the evaluation and the Cavg metric are presented in the paper.

More information

Item ID: 26034
DC Identifier: http://oa.upm.es/26034/
OAI Identifier: oai:oa.upm.es:26034
Official URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6638989
Deposited by: Memoria Investigacion
Deposited on: 17 May 2014 09:27
Last Modified: 22 Sep 2014 11:39
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM