Title | ||
---|---|---|
Specmurt Analysis of Multi-Pitch Music Signals with Adaptive Estimation of Common Harmonic Structure |
Abstract | ||
---|---|---|
This paper describes a multi-pitch analysis method using specmurt analysis with iterative estimation of the quasi- optimal common harmonic structure function. Specmurt analysis (Sagayama et al., 2004) is based upon the idea that superimposed harmonic structure pattern can be ex- pressed as a convolution of two components, a funda- mental frequency distribution and a 'common harmonic structure' function if each underlying tone component has similar harmonic structure pattern. As proved in our pre- vious work (Sagayama et al., 2004) inappropriate com- mon structure function leads to inaccurate analysis results. The iterative algorithm proposed in this paper automati- cally chooses a proper structure, which results in finding concurrent multiple fundamental frequencies and reduces the dependency on heuristically chosen initial common harmonic structure. The experimental evaluation showed promising results. |
Year | Venue | Keywords |
---|---|---|
2005 | ISMIR 2013 | specmurt analysis,visualization of the fundamental frequency.,audio feature extraction,structure function,fundamental frequency,iterative algorithm |
Field | DocType | Citations |
Heuristic,Fundamental frequency,Pattern recognition,Convolution,Computer science,Iterative method,Speech recognition,Harmonic structure,Artificial intelligence,Structure function | Conference | 5 |
PageRank | References | Authors |
0.61 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shoichiro Saito | 1 | 34 | 3.39 |
Hirokazu Kameoka | 2 | 801 | 79.06 |
Takuya Nishimoto | 3 | 227 | 28.95 |
Shigeki Sagayama | 4 | 1217 | 137.97 |