Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Lucimar Sasso Vieira"'
Autor:
Shi-Huang Chen, Carlos Dias Maciel, Paulo Rogério Scalassara, Rodrigo Capobianco Guido, Sylvio Barbon, José Carlos Pereira, Everthon Silva Fonseca, Lucimar Sasso Vieira, Fabrício Lopes Sanchez
Publikováno v:
Journal of Computational and Applied Mathematics. 227:271-287
Dynamic Time Warping (DTW), a pattern matching technique traditionally used for restricted vocabulary speech recognition, is based on a temporal alignment of the input signal with the template models. The principal drawback of DTW is its high computa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7438e630c665f91e0a9ece420ce624c0
https://doi.org/10.1016/j.cam.2008.03.015
https://doi.org/10.1016/j.cam.2008.03.015
Autor:
Rodrigo Capobianco Guido, Fabrício Lopes Sanchez, Lucimar Sasso Vieira, Sylvio Barbon Junior, Carlos Dias Maciel, José Carlos Pereira, Everthon Silva Fonseca
Publikováno v:
Neurocomputing. 71:174-180
In this letter we propose a new architecture for voice conversion that is based on a joint neural-wavelet approach. We also examine the characteristics of many wavelet families and determine the one that best matches the requirements of the proposed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd64b8169689d6c3af34d406aa102635
https://doi.org/10.1016/j.neucom.2007.08.010
https://doi.org/10.1016/j.neucom.2007.08.010
Autor:
Paulo Rogério Scalassara, Lucimar Sasso Vieira, Fabrício Lopes Sanchez, Rodrigo Capobianco Guido, Sylvio Barbon Junior, José Carlos Pereira, Carlos Dias Maciel, Vitor Muller Puia
Publikováno v:
International Journal of Semantic Computing. :347-357
This work presents a spoken document summarization (SDS) scheme that is based on an improved version of the Dynamic Time Warping (DTW) algorithm, and on the Discrete Wavelet Transform (DWT). Tests and results with sentences extracted from TIMIT speec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1984f0baaf507210d8e9073575c3c2f1
https://doi.org/10.1142/s1793351x07000214
https://doi.org/10.1142/s1793351x07000214
Autor:
Lucimar Sasso Vieira
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
O presente trabalho de doutorado teve por objetivo a criaçãao de uma nova família de transformadas wavelet, chamadas Morphlets, que é específica para o processo de conversão de voz. Antes de explicar a criação da Morphlet, foi apresentada uma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e2dd3bf7cdb50749bda3ce8aeb251f6
https://doi.org/10.11606/t.76.2012.tde-02052012-173331
https://doi.org/10.11606/t.76.2012.tde-02052012-173331
Autor:
Lucimar Sasso Vieira
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Dentre as inúmeras técnicas de conversão de voz utilizadas atualmente, aquelas baseadas em bancos de filtros wavelet, associadas com redes neurais artificiais,têm se destacado. Este trabalho se concentra em tais técnicas, realizando um estudo qu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::486747ed2e3fd4137e7f6e837e785838
https://doi.org/10.11606/d.76.2007.tde-05092007-192622
https://doi.org/10.11606/d.76.2007.tde-05092007-192622
Autor:
Lucimar Sasso Vieira
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USPUniversidade de São PauloUSP.
O presente trabalho de doutorado teve por objetivo a criaçãao de uma nova família de transformadas wavelet, chamadas Morphlets, que é específica para o processo de conversão de voz. Antes de explicar a criação da Morphlet, foi apresentada uma
Publikováno v:
ISM
This paper introduces Morph let, a new wavelet transform adapted for voice conversion purposes. The paradigm of joint time-frequency-shape analysis of discrete-time signals, possible by means of the Discrete Shape let Transform (DST), is the basis us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eee55d64198d5e2d797e56c6c52de79d
https://doi.org/10.1109/ism.2011.93
https://doi.org/10.1109/ism.2011.93
Autor:
Michel Alves Lacerda, Jussara Ribeiro, Shi-Huang Chen, Leonardo Mendes Souza, Rodrigo Capobianco Guido, Luciene Cavalcanti Rodrigues, Sylvio Barbon Junior, Lucimar Sasso Vieira, João Paulo Lemos Escola, Paulo Ricardo Franchi Zulato
Publikováno v:
ISM
Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, epsilon, uses to be defined experimentally. In this letter, we der
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8879da397f7d054c2c5bde8a4a76a28b
https://hdl.handle.net/11368/3004528
https://hdl.handle.net/11368/3004528
Autor:
Rodrigo Capobianco Guido, Carlos Dias Maciel, Paulo Rogério Scalassara, Fabrício Lopes Sanchez, Lucimar Sasso Vieira, José Carlos Pereira, Júnior Sylvio Barbon, Shi-Huang Chen, Everthon Silva Fonseca
In this paper we present a new wavelet-based algorithm for low-cost computation of the cepstrum. It can be used for real time precise pitch determination in automatic speech and speaker recognition systems. Many wavelet families are examined to deter
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06b4c0327ebcac3290652c182927a72a
https://hdl.handle.net/11368/3004467
https://hdl.handle.net/11368/3004467