Built on

D. B. Paul and J. M. Baker, “The design for the wall street journal-based csr corpus,” in
1992
Earlier work this paper cites.
D. Palaz, R. Collobert, and M. M. Doss, “End-to-end phoneme sequence recognition using convolutional neural networks,”
Original
2013
Earlier work this paper cites.
Z. Tüske, P. Golik, R. Schlüter, and H. Ney, “Acoustic modeling with deep neural networks using raw time signal for lvcsr,” in
2014
Earlier work this paper cites.
J. Andén and S. Mallat, “Deep scattering spectrum,”
2014
Earlier work this paper cites.
N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting.”
2014
Earlier work this paper cites.
A. Graves and N. Jaitly, “Towards end-to-end speech recognition with recurrent neural networks,” in
2014
Earlier work this paper cites.
Y. Hoshen, R. J. Weiss, and K. W. Wilson, “Speech acoustic modeling from raw multichannel waveforms,” in
2015
Earlier work this paper cites.
T. N. Sainath, R. J. Weiss, A. Senior, K. W. Wilson, and O. Vinyals, “Learning the speech front-end with raw waveform cldnns,” in
2015
Earlier work this paper cites.
Y. Miao, M. Gowayyed, and F. Metze, “Eesen: End-to-end speech recognition using deep RNN models and WFST-based decoding,” in
2015
Earlier work this paper cites.

Similar

Z. Zhu, J. H. Engel, and A. Hannun, “Learning multiscale features directly from waveforms,”
Original
2016
Cited alongside, same era.
A. Van Den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, “Wavenet: A generative model for raw audio,”
Original
2016
Cited alongside, same era.
P. Ghahremani, V. Manohar, D. Povey, and S. Khudanpur, “Acoustic modelling from the signal domain using cnns.” 2016
2016
Cited alongside, same era.
D. Ulyanov, A. Vedaldi, and V. Lempitsky, “Instance normalization: The missing ingredient for fast stylization,”
Original
2016
Cited alongside, same era.
R. Collobert, C. Puhrsch, and G. Synnaeve, “Wav2letter: an end-to-end convnet-based speech recognition system,”

Then

N. Zeghidour, N. Usunier, I. Kokkinos, T. Schatz, G. Synnaeve, and E. Dupoux, “Learning filterbanks from raw speech for phone recognition,”
Original
2017
Later among the works it cites.
W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, and A. Stolcke, “The microsoft 2017 conversational speech recognition system,”
Original
2017
Later among the works it cites.
K. J. Han, A. Chandrashekaran, J. Kim, and I. Lane, “The capio 2017 conversational speech recognition system,”
Original
2017
Later among the works it cites.
V. Liptchinsky, G. Synnaeve, and R. Collobert, “Letter-based speech recognition with gated convnets,”
Original
2017
Later among the works it cites.
S. Kim, T. Hori, and S. Watanabe, “Joint ctc-attention based end-to-end speech recognition using multi-task learning,” in

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2018

End-to-End Speech Recognition From the Raw Waveform

Zeghidour, Neil, Usunier, Nicolas, Synnaeve, Gabriel et al.

Understand

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.

Built on

D. B. Paul and J. M. Baker, “The design for the wall street journal-based csr corpus,” in
1992
Earlier work this paper cites.
D. Palaz, R. Collobert, and M. M. Doss, “End-to-end phoneme sequence recognition using convolutional neural networks,”
Original
2013
Earlier work this paper cites.
Z. Tüske, P. Golik, R. Schlüter, and H. Ney, “Acoustic modeling with deep neural networks using raw time signal for lvcsr,” in
2014
Earlier work this paper cites.
J. Andén and S. Mallat, “Deep scattering spectrum,”
2014
Earlier work this paper cites.
N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting.”
2014
Earlier work this paper cites.
A. Graves and N. Jaitly, “Towards end-to-end speech recognition with recurrent neural networks,” in
2014
Earlier work this paper cites.
Y. Hoshen, R. J. Weiss, and K. W. Wilson, “Speech acoustic modeling from raw multichannel waveforms,” in
2015
Earlier work this paper cites.
T. N. Sainath, R. J. Weiss, A. Senior, K. W. Wilson, and O. Vinyals, “Learning the speech front-end with raw waveform cldnns,” in
2015
Earlier work this paper cites.
Y. Miao, M. Gowayyed, and F. Metze, “Eesen: End-to-end speech recognition using deep RNN models and WFST-based decoding,” in
2015
Earlier work this paper cites.