Projekter pr. år
Abstract
We revisit the idea of ``inter-genre similarity'' (IGS)
for machine learning in general,
and music genre recognition in particular.
We show analytically that the probability of error for IGS
is higher than naive Bayes classification with zero-one loss (NB).
We show empirically that IGS does not perform well,
even for data that satisfies all its assumptions.
for machine learning in general,
and music genre recognition in particular.
We show analytically that the probability of error for IGS
is higher than naive Bayes classification with zero-one loss (NB).
We show empirically that IGS does not perform well,
even for data that satisfies all its assumptions.
| Originalsprog | Engelsk |
|---|---|
| Tidsskrift | I E E E Signal Processing Letters |
| Vol/bind | 20 |
| Udgave nummer | 11 |
| Sider (fra-til) | 1050-1053 |
| Antal sider | 4 |
| ISSN | 1070-9908 |
| DOI | |
| Status | Udgivet - nov. 2013 |
Fingeraftryk
Dyk ned i forskningsemnerne om 'Revisiting Inter-Genre Similarity'. Sammen danner de et unikt fingeraftryk.-
Greedy Sparse Approximation and the Automatic Description of Audio and Music Data
Sturm, B. L.
Technology and Production Independent Postdoc Center for Independent Research
01/01/2012 → …
Projekter: Projekt › Forskning
-
CoSound
Christensen, M. G., Tan, Z., Jensen, S. H. & Sturm, B. L.
01/01/2012 → 31/12/2015
Projekter: Projekt › Forskning