Fully Convolutional Speech Recognition

Abstract

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we present an alternative approach based solely on convolutional neural networks, leveraging recent advances in acoustic models from the raw waveform and language modeling. This fully convolutional approach is trained end-to-end to predict characters from the raw waveform, removing the feature extraction step altogether. An external convolutional language model is used to decode words. On Wall Street Journal, our model matches the current state-of-the-art. On Librispeech, we report state-of-the-art performance among end-to-end models, including Deep Speech 2 trained with 12 times more acoustic data and significantly more linguistic data.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzeghidour2018fully

Related papers

• Wav2letter: An End-to-end Convnet-based Speech Recognition System (2016)0.00
• End-to-end Speech Recognition From The Raw Waveform (2018)12.81
• Letter-based Speech Recognition With Gated Convnets (2017)0.00
• Advances In All-neural Speech Recognition (2016)11.29
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Acoustic-to-word Recognition With Sequence-to-sequence Models (2018)6.77
• Advancing CTC-CRF Based End-to-end Speech Recognition With Wordpieces And Conformers (2021)0.00
• Phoneme Based Neural Transducer For Large Vocabulary Speech Recognition (2020)9.59