Multi-objective optimisation of wavelet features for phoneme recognition

We proposed a novel approach for the optimisation of over-complete decompositions from a WPT dictionary based on a multi-objective genetic algorithm (MOGA). The MOGA allows to maximise the classification accuracy while minimising the number of features. For the purpose of obtaining appropriate featu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Vignolo, Leandro, Rufiner, Hugo Leonardo, Milone, Diego H.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2016
Materias:
Ciencias Informáticas
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/57025
http://45jaiio.sadio.org.ar/sites/default/files/ASAI-20_0.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-57025
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
spellingShingle Ciencias Informáticas
Vignolo, Leandro
Rufiner, Hugo Leonardo
Milone, Diego H.
Multi-objective optimisation of wavelet features for phoneme recognition
topic_facet Ciencias Informáticas
description We proposed a novel approach for the optimisation of over-complete decompositions from a WPT dictionary based on a multi-objective genetic algorithm (MOGA). The MOGA allows to maximise the classification accuracy while minimising the number of features. For the purpose of obtaining appropriate features for state of the art speech recognizers, a classifier based on hidden Markov models (HMM) is used to estimate the capability of candidate solutions, using on a set of English phonemes.
format Objeto de conferencia
Objeto de conferencia
author Vignolo, Leandro
Rufiner, Hugo Leonardo
Milone, Diego H.
author_facet Vignolo, Leandro
Rufiner, Hugo Leonardo
Milone, Diego H.
author_sort Vignolo, Leandro
title Multi-objective optimisation of wavelet features for phoneme recognition
title_short Multi-objective optimisation of wavelet features for phoneme recognition
title_full Multi-objective optimisation of wavelet features for phoneme recognition
title_fullStr Multi-objective optimisation of wavelet features for phoneme recognition
title_full_unstemmed Multi-objective optimisation of wavelet features for phoneme recognition
title_sort multi-objective optimisation of wavelet features for phoneme recognition
publishDate 2016
url http://sedici.unlp.edu.ar/handle/10915/57025
http://45jaiio.sadio.org.ar/sites/default/files/ASAI-20_0.pdf
work_keys_str_mv AT vignololeandro multiobjectiveoptimisationofwaveletfeaturesforphonemerecognition
AT rufinerhugoleonardo multiobjectiveoptimisationofwaveletfeaturesforphonemerecognition
AT milonediegoh multiobjectiveoptimisationofwaveletfeaturesforphonemerecognition
bdutipo_str Repositorios
_version_ 1764820476811542534

Ejemplares similares