| Paper: | SP-L1.6 |
| Session: | Neural Network Trends in Speech Recognition |
| Location: | Yangtse River Hall (5F) |
| Session Time: | Tuesday, March 22, 13:30 - 15:30 |
| Presentation Time: | Tuesday, March 22, 15:10 - 15:30 |
| Presentation: |
Lecture
|
| Topic: |
Speech Processing: Acoustic Modeling for Automatic Speech Recognition |
| Paper Title: |
A DEEP SCATTERING SPECTRUM - DEEP SIAMESE NETWORK PIPELINE FOR UNSUPERVISED ACOUSTIC MODELING |
| Authors: |
Neil Zeghidour, Ecole des Hautes Etudes en Sciences Sociales, France; Gabriel Synnaeve, Facebook A.I. Research, France; Maarten Versteegh, École normale supérieure, France; Emmanuel Dupoux, Ecole des Hautes Etudes en Sciences Sociales, France |
