arXiv
Open Access
2013
Deep Scattering Spectrum
Joakim Andén
Stéphane Mallat
Abstrak
A scattering transform defines a locally translation invariant representation which is stable to time-warping deformations. 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.
Penulis (2)
J
Joakim Andén
S
Stéphane Mallat
Akses Cepat
Informasi Jurnal
- Tahun Terbit
- 2013
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓