End-to-End Speech Recognition from the Raw Waveform

Neil Zeghidour, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert, Emmanuel Dupoux

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 with clean recording conditions.

 DOI: 10.21437/Interspeech.2018-2414

Cite as: Zeghidour, N., Usunier, N., Synnaeve, G., Collobert, R., Dupoux, E. (2018) End-to-End Speech Recognition from the Raw Waveform. Proc. Interspeech 2018, 781-785, DOI: 10.21437/Interspeech.2018-2414.

  author={Neil Zeghidour and Nicolas Usunier and Gabriel Synnaeve and Ronan Collobert and Emmanuel Dupoux},
  title={End-to-End Speech Recognition from the Raw Waveform},
  booktitle={Proc. Interspeech 2018},