Deep Scattering Spectrum with deep neural networks

By Vijayaditya Peddinti, Tara N. Sainath, Shay Maymon, Bhuvana Ramabhadran, David Nahamoo, Vaibhava Goel. 2014

38 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Model Architectures, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Gabriel Synnaeve
2. Emmanuel Dupoux
3. Thomas Schatz
4. Neil Zeghidour
5. Maarten Versteegh
6. Nicolas Usunier
7. Michael Auli
8. Iasonas Kokkinos

In Model Architectures

1. Thomas Schatz
2. Emmanuel Dupoux
3. Maarten Versteegh
4. Nicolas Usunier
5. Iasonas Kokkinos
6. Gabriel Synnaeve
7. Neil Zeghidour
8. Alan L. Yuille

In Signal Processing

1. Emmanuel Dupoux
2. Neil Zeghidour
3. Thomas Schatz
4. Gabriel Synnaeve
5. Maarten Versteegh
6. Nicolas Usunier
7. Iasonas Kokkinos
8. Yossi Adi

Citations in the corpus

• Learning Filterbanks from Raw Speech for Phone Recognition (2017, methodology): “Deep scattering spectra have been used as inputs to neural networks trained for phone recognition [13] or classification [14], which showed better performances than comparable models trained on MFSC.”
• A deep scattering spectrum — Deep Siamese network pipeline for unsupervised acoustic modeling (2016, background): “These results suggest that deep architectures that are trained on standard spectral features are not exploited to their full potential, as previously shown in a supervised setting in [21].”