Aurora Gpe | Itpn - Academia.edu (original) (raw)
Address: Hidalgo, Michoacan de Ocampo, Mexico
less
Related Authors
Shahid Bahonar University of Kerman
University of Southern California
Uploads
Papers by Aurora Gpe
In this paper, we propose an F0 Frame Error (FFE) metric which combines Gross Pitch Error (GPE) a... more In this paper, we propose an F0 Frame Error (FFE) metric which combines Gross Pitch Error (GPE) and Voicing Decision Error (VDE) to objectively evaluate the performance of fundamental frequency (F0) tracking methods. A GPE-VDE curve is then developed to show the trade-off between GPE and VDE. In addition, we introduce a model-based Unvoiced/Voiced (U/V) classification frontend which can be used by any F0 tracking algorithm. In the U/V classification, we train speaker independent U/V models, and then adapt them to speaker dependent models in an unsupervised fashion. The U/V classification result is taken as a mask for F0 tracking. Experiments using the KEELE corpus with additive noise show that our statistically-based U/V classifier can reduce VDE and FFE for the pitch tracker TEMPO [1] in both white and babble noise conditions, and that minimizing FFE instead of VDE results in a reduction in error rates for a number of F0 tracking algorithms, especially in babble noise.
Caracterización de la asignatura.
In this paper, we propose an F0 Frame Error (FFE) metric which combines Gross Pitch Error (GPE) a... more In this paper, we propose an F0 Frame Error (FFE) metric which combines Gross Pitch Error (GPE) and Voicing Decision Error (VDE) to objectively evaluate the performance of fundamental frequency (F0) tracking methods. A GPE-VDE curve is then developed to show the trade-off between GPE and VDE. In addition, we introduce a model-based Unvoiced/Voiced (U/V) classification frontend which can be used by any F0 tracking algorithm. In the U/V classification, we train speaker independent U/V models, and then adapt them to speaker dependent models in an unsupervised fashion. The U/V classification result is taken as a mask for F0 tracking. Experiments using the KEELE corpus with additive noise show that our statistically-based U/V classifier can reduce VDE and FFE for the pitch tracker TEMPO [1] in both white and babble noise conditions, and that minimizing FFE instead of VDE results in a reduction in error rates for a number of F0 tracking algorithms, especially in babble noise.
Caracterización de la asignatura.