IEEE transactions on signal processing, 2014-08, Vol.62 (16), p.4114-4128
2014
Volltextzugriff (PDF)
Details
- Autor(en) / Beteiligte
- Titel
- Deep Scattering Spectrum
- Ist Teil von
- IEEE transactions on signal processing, 2014-08, Vol.62 (16), p.4114-4128
- Ort / Verlag
- New York, NY: IEEE
- Erscheinungsjahr
- 2014
- Quelle
- IEEE Xplore
- Beschreibungen/Notizen
- A scattering transform defines a locally translation invariant representation which is stable to time-warping deformation. It extends MFCC representations by computing modulation spectrum coefficients of multiple orders, through cascades of wavelet convolutions and modulus operators. Second-order scattering coefficients characterize transient phenomena such as attacks and amplitude modulation. A frequency transposition invariant representation is obtained by applying a scattering transform along log-frequency. State-the-of-art classification results are obtained for musical genre and phone classification on GTZAN and TIMIT databases, respectively.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 1053-587XeISSN: 1941-0476DOI: 10.1109/TSP.2014.2326991Titel-ID: cdi_pascalfrancis_primary_28721805
- Format
- –
- Schlagworte
- Amplitude modulation, Applied sciences, Artificial intelligence, Audio classification, Cascades, Classification, Computer science, control theory, systems, Connectionism. Neural networks, Convolution, deep neural networks, Detection, estimation, filtering, equalization, prediction, Exact sciences and technology, Frequency modulation, Information, signal and communications theory, Invariants, MFCC, Miscellaneous, Modulation, modulation spectrum, Modulation, demodulation, Representations, Scattering, Signal and communications theory, Signal processing, Signal, noise, Spectrogram, Telecommunications and information theory, Transforms, Wavelet analysis, Wavelet transforms, wavelets