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

Stats

• citations50
• S2 citations—
• github stars0
• HF likes0
• heat score12.81
• arxiv keyzeghidour2018end

Related papers

• Fully Convolutional Speech Recognition (2018)0.00
• Learning Multiscale Features Directly From Waveforms (2016)0.00
• Raw Waveform Encoder With Multi-scale Globally Attentive Locally Recurrent Networks For End-to-end Speech Recognition (2021)0.00
• Wav2letter: An End-to-end Convnet-based Speech Recognition System (2016)0.00
• Learning Waveform-based Acoustic Models Using Deep Variational Convolutional Neural Networks (2019)6.77
• Raw Waveform-based Speech Enhancement By Fully Convolutional Networks (2017)16.63
• Detection Of Doctored Speech: Towards An End-to-end Parametric Learn-able Filter Approach (2022)0.00
• End-to-end Whisper To Natural Speech Conversion Using Modified Transformer Network (2020)0.00