Fetching the paper…

Reading the bibliography…

2020

Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models

Madikeri, Srikanth, Tong, Sibo, Zuluaga-Gomez, Juan et al.

Original
PDF
Post on X

Understand

We present a simple wrapper that is useful to train acoustic models in PyTorch using Kaldi's LF-MMI training framework.

The wrapper, called pkwrap (short form of PyTorch kaldi wrapper), enables the user to utilize the flexibility provided by PyTorch in designing model architectures.
It exposes the LF-MMI cost function as an autograd function.
Other capabilities of Kaldi have also been ported to PyTorch.

Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models · Around

Built on

J. J. Godfrey, E. C. Holliman, and J. McDaniel, “Switchboard: Telephone speech corpus for research and development,” in
1992
Earlier work this paper cites.
D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz
2011
Earlier work this paper cites.
D. Povey, X. Zhang, and S. Khudanpur, “Parallel training of dnns with natural gradient and parameter averaging,”
Original
2014
Earlier work this paper cites.
A. Hannun, C. Case, J. Casper, B. Catanzaro, G. Diamos, E. Elsen, R. Prenger, S. Satheesh, S. Sengupta, A. Coates
Original
2014
Earlier work this paper cites.
D. Kingma and J. Ba, “Adam: A method for stochastic optimization,”
2014
Earlier work this paper cites.
V. Panayotov, G. Chen, D. Povey, and S. Khudanpur, “Librispeech: An asr corpus based on public domain audio books,” in
2015
Earlier work this paper cites.

Similar

D. Povey
2016
Cited alongside, same era.
W. Jakob, J. Rhinelander, and D. Moldovan, “pybind11–seamless operability between c++ 11 and python,” 2017
2017
Cited alongside, same era.
D. Can, V. R. Martinez, P. Papadopoulos, and S. S. Narayanan, “Pykaldi: A python wrapper for kaldi,” in
2018
Cited alongside, same era.
H. Hadian
2018
Cited alongside, same era.
H. Hadian, H. Sameti, D. Povey, and S. Khudanpur, “End-to-end speech recognition using lattice-free mmi,” in
2018
Cited alongside, same era.

Then

A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, “Pytorch: An imperative style, high-performance deep learning library,” 2019
2019
Later among the works it cites.
L. Lu, X. Xiao, Z. Chen, and Y. Gong, “Pykaldi2: yet another speech toolkit based on kaldi and pytorch,”
Original
2019
Later among the works it cites.
Y. Shao, Y. Wang, D. Povey, and S. Khudanpur, “Pychain: A fully parallelized pytorch implementation of lf-mmi for end-to-end asr,”
Original
2020
Closest in time.
A. Prasad, P. Motlicek, and S. Madikeri, “Quantization of acoustic model parameters in automatic speech recognition framework,”
Original
2020
Closest in time.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…

S. Madikeri, B. Khonglah, S. Tong, P. Motlicek, H. Bourlard, and D. Povey, “Lattice-free maximum mutual information training of multilingual speech recognition systems,”

2020

Closest in time.