Title | ||
---|---|---|
Incorporating scale information with cepstral features: Experiments on musical instrument recognition |
Abstract | ||
---|---|---|
We present two sets of novel features that combine multiscale representations of signals with the compact timbral description of Mel-frequency cepstral coefficients (MFCCs). We define one set of features, OverCs, from overcomplete transforms at multiple scales. We define the second set of features, SparCs, from a signal model found by sparse approximation. We compare the descriptiveness of our features against that of MFCCs by performing two simple tasks: pairwise musical instrument discrimination, and musical instrument classification. Our tests show that both OverCs and SparCs improve the characterization of the global timbre and local stationarity of an audio signal than do mean MFCCs with respect to these tasks. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.patrec.2009.12.035 | Pattern Recognition Letters |
Keywords | Field | DocType |
global timbre,musical instrument recognition,pairwise musical instrument discrimination,mean mfccs,incorporating scale information,sparse decompositions,audio signal classification,signal model,time–frequency/time-scale features,compact timbral description,multiple scale,cepstral feature,audio signal,mel-frequency cepstral coefficient,local stationarity,musical instrument classification,time frequency,mel frequency cepstral coefficient,sparse approximation | Mel-frequency cepstrum,Audio signal,Pattern recognition,Cepstrum,Sparse approximation,Musical instrument classification,Musical instrument,Speech recognition,Artificial intelligence,Audio signal processing,Timbre,Mathematics | Journal |
Volume | Issue | ISSN |
31 | 12 | Pattern Recognition Letters |
Citations | PageRank | References |
3 | 0.48 | 12 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcela Morvidone | 1 | 17 | 2.56 |
Bob L. Sturm | 2 | 241 | 29.88 |
L. Daudet | 3 | 672 | 62.06 |