Loading Events

« All Events

  • This event has passed.

TALC seminar : Neil Zeghidour (Facebook & ENS)

May 30, 2018 @ 2:00 pm - 3:30 pm

Neil Zeghidour (Facebook AI Research & Ecole Normale Supérieure) will give a talk in the TALC Seminar (Department 4) on May Wednesday the 10th at 2.00 pm in room C005.

The title is : “End-to-end speech recognition from the raw waveform”.

Abstract :

State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. We study end-to-end systems trained directly from the raw waveform, introducing a trainable replacement of mel-filterbanks that uses a convolutional architecture, based on the scattering transform. These time-domain filterbanks (TD-filterbanks) are initialized as an approximation of melfilterbanks, and then fine-tuned jointly with the remaining convolutional architecture. We perform phone recognition experiments on TIMIT and show that models trained on TD-filterbanks consistently outperform their counterparts trained on comparable mel-filterbanks. We then improve this model and another frontend previously proposed and based on gammatones. We perform open vocabulary experiments on Wall Street Journal and show a consistent and significant improvement in Word Error Rate of our trainable frontends over mel-filterbanks, even with random initialization.

Details

Date:
May 30, 2018
Time:
2:00 pm - 3:30 pm
Event Category:

Logo du CNRS

Logo d'Inria

Logo Université de Lorraine