I am a PhD student at the Centre de Mathématiques Appliquées at Ecole Polytechnique in Paris, France. My research focuses on invariant signal representations using the scattering transform developed by Stéphane Mallat. I am interested in understanding the properties of audio signals that allow us to successfully discriminate sounds while disregarding irrelevant differences and how to formalize these mathematically. Applications include various tasks of audio classification and similarity estimation for musical, speech and environmental dat
Deep Scattering Spectrum
J. Andén and S. Mallat. Submitted to IEEE Transactions on Signal Processing.
The scattering transform for temporal signals is defined and described in detail. Properties of this transform for audio are illustrated using examples of amplitude modulation and frequency component interference as well as reconstruction of signals from their scattering transforms. For frequency transposition invariance and frequency-warping stability, the separable time and frequency scattering transform is introduced. Finally, state-of-the-art results are obtained using these representations for the problems of musical genre classification and phone identification on the GTZAN and TIMIT datasets, respectively.
"Scattering Transform for Intrapartum Fetal Heart Rate Characterization and Acidosis Detection"
V. Chudáček, J. Andén, S. Mallat, P. Abry, and M. Doret. Proceedings of the EMBC 2013 conference.
The scattering transform applied to fetal heart rate signals is shown to provide meaningful information on subject health by characterizing the multiscale temporal dynamics of the signal through scaling coefficients. Notably, when used to classify a subject as healthy or non-healthy, these coefficients are shown to reduce the false positive rate (number of healthy subjects classified as non-healthy) by almost 50% compared to standard FIGO (International Federation of Gynecology and Obstetrics) guidelines while maintaining a 100% true positive rate (number of non-healthy subjects classified as non-healthy).
"Representing Environmental Sounds Using the Separable Scattering Transform"
C. Baugé, M. Lagrange, J. Andén, and S. Mallat. Proceedings of the ICASSP 2013 conference (Special Session on Acoustic Event Detection and Scene Analysis).
In order to judge the similarity of several environmental sounds, the scattering transform is used to define a time-shift invariant metric stable to time-warping deformation. Additional frequency transposition invariance is obtained by applying a second scattering transform along log-frequency. This metric outperforms state-of-the-art methods based on bags-of-frames and dynamic time warping applied to mel-frequency ceptral coefficient (MFCC) or log-spectrogram features.
"Scattering Representation of Modulated Sounds"
J. Andén and S. Mallat. Proceedings of the DAFx 2012 conference. (Best Paper Award)
The constant-Q structure of the mel scale for high frequencies is shown to stabilize mel-based representations to small dilations in the input signal. Since the scattering transform relies similarly on a constant-Q filter bank, it inherits this stability. In addition, a modulated source-filter model is introduced to illustrate how the second-order scattering coefficients capture important timbral information such as attacks, tremolo, vibrato, and chord structure.
"Multiscale Scattering for Audio Classification"
J. Andén and S. Mallat. Proceedings of the ISMIR 2011 conference, Miami, USA, Oct. 24-28.
This paper introduces the scattering transform in the audio context, extending mel-frequency ceptral coefficients (MFCCs) by recovering the lost high-frequency information due to temporal averaging. Comparing the results to traditional MFCC and Delta-MFCC features, scattering coefficients show a significant improvement on the GTZAN genre classification task. Using the algorithm developed by Irene Waldspurger, reconstructing audio signals from scattering coefficients is described with examples available online.
Together with Laurent Sifre, I have developed the ScatNet toolbox for calculating scattering transforms in MATLAB, complete with visualization and classification pipelines (affine space models and support vector classifiers) for duplicating the results of the above papers. Older MATLAB toolboxes scattering computation and affine space classifiers are available, but are no longer supported.
- To speed up computation and reduce memory size, I have introduced some changes to the popular LIBSVM library for support vector machine (SVM) training. The libsvm-compact package extends the library to handle precomputed Gaussian kernels, 32-bit precision, triangular kernels, and multi-core training as well as in-place routines for MATLAB.
I can be reached at firstname.lastname@example.org.