Joint time-frequency scattering for audio classification
2015
We introduce the joint time-frequency scattering transform, a time shift invariant descriptor of time-frequency structure for audio classification. It is obtained by applying a two-dimensional wavelet transform in time and log-frequency to a time-frequency wavelet scalogram. We show that this descriptor successfully characterizes complex time-frequency phenomena such as time-varying filters and frequency modulated excitations. State-of-the-art results are achieved for signal reconstruction and phone segment classification on the TIMIT dataset.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
13
References
22
Citations
NaN
KQI