Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal

Shimmer is a classical acoustic measure of the amplitude perturbation of a signal. This kind of variation in the human voice allow to characterize some properties, not only of the voice itself, but of the person who speaks. During the last years deep learning techniques have become the state of the...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: García, Mario Alejandro, Destéfanis, Eduardo A.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2017
Materias:
Ciencias Informáticas
shimmer
voice quality
deep learning
deep neural network
convolutional neural network
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/63484
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-63484
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
shimmer
voice quality
deep learning
deep neural network
convolutional neural network
spellingShingle Ciencias Informáticas
shimmer
voice quality
deep learning
deep neural network
convolutional neural network
García, Mario Alejandro
Destéfanis, Eduardo A.
Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal
topic_facet Ciencias Informáticas
shimmer
voice quality
deep learning
deep neural network
convolutional neural network
description Shimmer is a classical acoustic measure of the amplitude perturbation of a signal. This kind of variation in the human voice allow to characterize some properties, not only of the voice itself, but of the person who speaks. During the last years deep learning techniques have become the state of the art for recognition tasks on the voice. In this work the relationship between shimmer and deep neural networks is analyzed. A deep learning model is created. It is able to approximate shimmer value of a simple synthesized audio signal (stationary and without formants) taking the spectrogram as input feature. It is concluded firstly, that for this kind of synthesized signal, a neural network like the one we proposed can approximate shimmer, and secondly, that the convolution layers can be designed in order to preserve the information of shimmer and transmit it to the following layers.
format Objeto de conferencia
Objeto de conferencia
author García, Mario Alejandro
Destéfanis, Eduardo A.
author_facet García, Mario Alejandro
Destéfanis, Eduardo A.
author_sort García, Mario Alejandro
title Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal
title_short Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal
title_full Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal
title_fullStr Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal
title_full_unstemmed Deep Neural Networks for Shimmer Approximation in Synthesized Audio Signal
title_sort deep neural networks for shimmer approximation in synthesized audio signal
publishDate 2017
url http://sedici.unlp.edu.ar/handle/10915/63484
work_keys_str_mv AT garciamarioalejandro deepneuralnetworksforshimmerapproximationinsynthesizedaudiosignal
AT destefaniseduardoa deepneuralnetworksforshimmerapproximationinsynthesizedaudiosignal
bdutipo_str Repositorios
_version_ 1764820480839122944

Ejemplares similares