Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Flavio J. Reyes Díaz"'
Autor:
Flavio J. Reyes Díaz, Alejandro Roble Gutiérrez, Gabriel Hernández Sierra, José Ramón Calvo de Lara
Publikováno v:
Revista Cubana de Ciencias Informáticas, Vol 12, Iss 3, Pp 152-162 (2018)
Las señales de audio, incluida la voz, de alguna forma están expuestas al deterioro de su calidad debido a la incorporación de ruidos ambientales. Estos ruidos existentes en la señales de audio, provocan una degradación de la calidad en la infor
Externí odkaz:
https://doaj.org/article/88fc9e02c06b4f6db5a340903b04514b
Publikováno v:
International Journal of Speech Technology. 24:409-418
The article deals with the compensation of variability in Automatic Speaker Verification systems in scenarios where the variability conditions due to utterance duration, reverberation and environmental noise are simultaneously present. We introduce a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68e7236a3fe383a49f1acf39bafb5858
https://doi.org/10.1007/s10772-021-09796-1
https://doi.org/10.1007/s10772-021-09796-1
Autor:
Flavio J. Reyes Díaz, Gabriel Hernández Sierra, Orlando Jimenez Alcazar, José Ramón Calvo de Lara
Publikováno v:
International Journal of Speech Technology. 21:975-985
The recognition of a person by his voice or “speaker recognition”, is a biometric specialty increasingly used in electronic commerce and electronic banking transactions and forensic investigations, among others. Speaker recognition is supported b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ab4c39d542347a623966f1225bb0bd9
https://doi.org/10.1007/s10772-018-9547-0
https://doi.org/10.1007/s10772-018-9547-0
Publikováno v:
International Journal of Speech Technology. 20:475-485
The performance of state-of-the-art speaker verification in uncontrolled environment is affected by different variabilities. Short duration variability is very common in these scenarios and causes the speaker verification performance to decrease quic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2796dd0b86f5f13963c7a57d6b3cfe2c
https://doi.org/10.1007/s10772-017-9414-4
https://doi.org/10.1007/s10772-017-9414-4
Publikováno v:
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications ISBN: 9783642332746
CIARP
CIARP
Speaker recognition systems frequently use GMM - MAP method for modeling speakers. This method represents a speaker using a Gaussian mixture. However in this mixture not all the Gaussian components are truly representative of the speaker. In order to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31a499a51a0c7908a5cb7d812832a569
https://doi.org/10.1007/978-3-642-33275-3_89
https://doi.org/10.1007/978-3-642-33275-3_89
