Desarrollo de software libre para el análisis espectral de voces patológicas
Fuente:
Redalyc
Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | es |
| Published: |
Universidad de Carabobo
2017
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1876434822935609344 |
|---|---|
| author | Yanina Perdomo |
| author_facet | Yanina Perdomo |
| contents | Desarrollo de software libre para el análisis espectral de voces patológicas Yanina Perdomo Ahmad Osman Jesús Jiménez Ingeniería Voice Signal Spectral Analysis Discrete Fourier Transform The creation of free software for the spectral analysis of pathological voices using e ffi cient algorithms for the computation of the Discrete Fourier Transform (DFT), is considered. For this, the state of the art review of the Fast Fourier Transform (FFT) algorithms was performed and the implementation was proceeded, in code Fortran, of the most significant. Then, through Python’s importable modules, a graphical interface for the interactive use of the algorithms was designed. From the results of the FFT, some spectral parameters were determined: power spectrum, formant estimation, pitch estimation, spectral envelope extraction and spectrogram. Finally, we performed tests of estimation of parameters of some speech samples, obtaining results highly approximated to Praat software. 2017 artículo científico 1316-6832 https://www.redalyc.org/articulo.oa?id=70753474005 es http://www.redalyc.org/revista.oa?id=707 Revista INGENIERÍA UC application/pdf Universidad de Carabobo Revista INGENIERÍA UC (República Bolivariana de Venezuela) Num.2 Vol.24 |
| format | Artículo científico |
| id | redalyc_70753474005 |
| institution | Redalyc |
| language | es |
| publishDate | 2017 |
| publisher | Universidad de Carabobo |
| spellingShingle | Desarrollo de software libre para el análisis espectral de voces patológicas Yanina Perdomo Ingeniería Voice Signal Spectral Analysis Discrete Fourier Transform Desarrollo de software libre para el análisis espectral de voces patológicas Yanina Perdomo Ahmad Osman Jesús Jiménez Ingeniería Voice Signal Spectral Analysis Discrete Fourier Transform The creation of free software for the spectral analysis of pathological voices using e ffi cient algorithms for the computation of the Discrete Fourier Transform (DFT), is considered. For this, the state of the art review of the Fast Fourier Transform (FFT) algorithms was performed and the implementation was proceeded, in code Fortran, of the most significant. Then, through Python’s importable modules, a graphical interface for the interactive use of the algorithms was designed. From the results of the FFT, some spectral parameters were determined: power spectrum, formant estimation, pitch estimation, spectral envelope extraction and spectrogram. Finally, we performed tests of estimation of parameters of some speech samples, obtaining results highly approximated to Praat software. 2017 artículo científico 1316-6832 https://www.redalyc.org/articulo.oa?id=70753474005 es http://www.redalyc.org/revista.oa?id=707 Revista INGENIERÍA UC application/pdf Universidad de Carabobo Revista INGENIERÍA UC (República Bolivariana de Venezuela) Num.2 Vol.24 |
| title | Desarrollo de software libre para el análisis espectral de voces patológicas |
| topic | Ingeniería Voice Signal Spectral Analysis Discrete Fourier Transform |
| url | https://www.redalyc.org/articulo.oa?id=70753474005 |