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. In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture. The first one is inspired by gammatone filterbanks (Hoshen et al., 2015; Sainath et al, 2015), and the second one by the scattering transform (Zeghidour et al., 2017). We propose two modifications to these architectures and systematically compare them to mel-filterbanks, on the Wall Street Journal dataset. The first modification is the addition of an instance normalization layer, which greatly improves on the gammatone-based trainable filterbanks and speeds up the training of the scattering-based filterbanks. The second one relates to the low-pass filter used in these approaches. These modifications consistently improve performances for both approaches, and remove the need for a careful initialization in scattering-based trainable filterbanks. In particular, we show a consistent improvement in word error rate of the trainable filterbanks relatively to comparable mel-filterbanks. It is the first time end-to-end models trained from the raw signal significantly outperform mel-filterbanks on a large vocabulary task under clean recording conditions.
Liste complète des métadonnées

Contributor : Emmanuel Dupoux <>
Submitted on : Friday, December 7, 2018 - 2:40:40 PM
Last modification on : Thursday, February 7, 2019 - 4:58:41 PM
Document(s) archivé(s) le : Friday, March 8, 2019 - 2:41:35 PM


Files produced by the author(s)




Neil Zeghidour, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert, Emmanuel Dupoux. End-to-End Speech Recognition From the Raw Waveform. Interspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2414⟩. ⟨hal-01888739⟩



Record views


Files downloads