Abstract | ||
---|---|---|
In this paper, we present our recent studies of F0 estimation from the surface electromyographic (EMG) data us ing a Gaussian mixture model (GMM)-based voice con version (VC) technique, referred to as EMG-to-F0. In our approach, a support vector machine recognizes individual frames as unvoiced and voiced (U/V), and voiced F0 contours are discriminated by the trained GMM based on the manner of minimum mean-square error. EMG-to-F0 is experimentally evaluated using three data sets of different speakers. Each data set includes almost 500 utterances. Objective experiments demonstrate that we achieve a correlation coefficient of up to 0.49 between estimated and target F0 contours with more than 84% U/V decision accuracy, although the results have large variations. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5946468 | Acoustics, Speech and Signal Processing |
Keywords | DocType | ISSN |
Gaussian processes,electromyography,feature extraction,frequency estimation,least mean squares methods,support vector machines,EMG,GMM,Gaussian mixture model,frequency estimation,minimum mean square error,support vector machine,surface electromyography,voice conversion,Electromyography,Feature estimation,Fundamental frequency,Voice conversion | Conference | 1520-6149 E-ISBN : 978-1-4577-0537-3 |
ISBN | Citations | PageRank |
978-1-4577-0537-3 | 5 | 0.57 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Keigo Nakamura | 1 | 103 | 7.60 |
Matthias Janke | 2 | 67 | 8.35 |
Michael Wand | 3 | 161 | 15.90 |
T. Schultz | 4 | 2423 | 252.72 |