Abstract | ||
---|---|---|
We describe a feature extraction method for general audio mod- eling using a temporal extension of Independent Component Analysis (ICA) and demonstrate its utility in the context of a sound classification task in a kitchen environment. Our ap- proach accounts for temporal dependencies over multiple anal- ysis frames much like the standard audio modeling technique of adding first and second temporal derivatives to the feature set. Using a real-world dataset of kitchen sounds, we show that our approach outperforms a canonical version of this standard front end, the mel-frequency cepstral coefficients (MFCCs), which has found successful application in automatic speech recogni- tion tasks. |
Year | Venue | Keywords |
---|---|---|
2005 | INTERSPEECH | front end,feature extraction,mel frequency cepstral coefficient,independent component analysis |
Field | DocType | Citations |
Front and back ends,Mel-frequency cepstrum,Pattern recognition,Computer science,Sound classification,Speech recognition,Feature extraction,Feature set,Independent component analysis,Artificial intelligence | Conference | 18 |
PageRank | References | Authors |
1.43 | 6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Florian Kraft | 1 | 48 | 5.25 |
Robert Malkin | 2 | 85 | 10.30 |
Thomas Schaaf | 3 | 364 | 44.96 |
Alex Waibel | 4 | 6343 | 1980.68 |