Carregant...
Carregant...

Vés al contingut (premeu Retorn)

BaNa: a noise resilient fundamental frequency detection algorithm for speech and music

Autor
Yang, N.; Ba, H.; Cai, W.; Demirkol, I.; Heinzelman, W.
Tipus d'activitat
Article en revista
Revista
IEEE transactions on audio speech and language processing
Data de publicació
2014-08-27
Volum
22
Número
12
Pàgina inicial
1833
Pàgina final
1848
DOI
https://doi.org/10.1109/TASLP.2014.2352453 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/102780 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/document/6884780/ Obrir en finestra nova
Resum
Fundamental frequency (F0) is one of the essential features in many acoustic related applications. Although numerous F0 detection algorithms have been developed, the detection accuracy in noisy environments still needs improvement. We present a hybrid noise resilient F0 detection algorithm named BaNa that combines the approaches of harmonic ratios and Cepstrum analysis. A Viterbi algorithm with a cost function is used to identify the F0 value among several F0 candidates. Speech and music databas...
Citació
Yang, N., Ba, H., Cai, W., Demirkol, I., Heinzelman, W. BaNa: a noise resilient fundamental frequency detection algorithm for speech and music. "IEEE transactions on audio speech and language processing", 27 Agost 2014, vol. 22, núm. 12, p. 1833-1848.
Paraules clau
Cepstrum, Fundamental frequency detection, Harmonics, Noise resilience, Viterbi algorithm
Grup de recerca
WNG - Grup de xarxes sense fils

Participants

Arxius