[Ml-stat-talks] IDeAS Seminar 4/16/14 @ 3:00 pm - 110 Fine Hall

Amit Singer amits at math.Princeton.EDU
Fri Apr 11 10:30:34 EDT 2014

DATE: Wednesday April 16 , 2014


PLACE: 110 Fine Hall 

TIME: 3:00 pm 

SPEAKER: Joakim Anden - Princeton University

TITLE: Scattering Invariants for Audio Classification

Representations for classification tasks reduce the amount of training data by incorporating invariance to transformations that do not affect class membership, such as time-shifting and time-warping in audio. The scattering transform, a cascade of wavelet transforms and modulus operators, satisfies these conditions while capturing discriminative temporal structure and has similarities to traditional audio representations. Unfortunately, the transform is unsuited to capturing joint time-frequency structure, limiting its discriminative power. To remedy this, the joint time-frequency scattering transform is introduced, replacing one-dimensional with two-dimensional wavelet decompositions in the scattering cascade. Using these representations, state-of-the-art results are obtained on phone segment classification and musical genre recognition.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20140411/be055e06/attachment.html>

More information about the Ml-stat-talks mailing list