Samenvatting
While nonnegative matrix factorization (NMF) has successfully been applied for gain-robust multi-pitch detection, a method to track pitch values over time was not provided. We embed NMF-based pitch detection into a recently proposed pitch-tracking system, based on a factorial hidden Markov model (FHMM). The original system models speech spectra with Gaussian mixture models, which is sensitive to a gain mismatch between training and test data. We therefore combine the advantages of these two approaches and derive a gain-adaptive observation model for the FHMM. As training algorithm we use a modification of ℓ0-sparse NMF, which represents the short-time spectrum with scalable basis vectors. In experiments we show that the new approach significantly increases the gain-robustness of the original tracking system.
Originele taal-2 | Engels |
---|---|
Titel | 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings |
Uitgeverij | Institute of Electrical and Electronics Engineers |
Pagina's | 5416-5419 |
Aantal pagina's | 4 |
ISBN van geprinte versie | 9781457705397 |
DOI's | |
Status | Gepubliceerd - 18 aug. 2011 |
Extern gepubliceerd | Ja |
Evenement | 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011) - Prague, Tsjechië Duur: 22 mei 2011 → 27 mei 2011 Congresnummer: 36 |
Congres
Congres | 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011) |
---|---|
Verkorte titel | ICASSP 2011 |
Land/Regio | Tsjechië |
Stad | Prague |
Periode | 22/05/11 → 27/05/11 |
Ander | 36th International Conference on Acoustics, Speech and Signal Processing |