Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 236

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

The Pytorch-kaldi Speech Recognition Toolkit

Open access
Ravanelli, Mirco, Parcollet, Titouan, Bengio, Yoshua·2019·ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Abstract

The availability of open-source software is playing a remarkable role in the popularization of speech recognition and deep learning. Kaldi, for instance, is nowadays an established framework used to develop state-of-the-art speech recognizers. PyTorch is used to build neural networks with the Python language and has recently spawn tremendous interest within the machine learning community thanks to its simplicity and flexibility. The PyTorch-Kaldi project aims to bridge the gap between these popular toolkits, trying to inherit the efficiency of Kaldi and the flexibility of PyTorch. PyTorch-Kaldi is not only a simple interface between these software, but it embeds several useful features for developing modern speech recognizers. For instance, the code is specifically designed to naturally plug-in user-defined acoustic models. As an alternative, users can exploit several pre-implemented neural networks that can be customized using intuitive configuration files. PyTorch-Kaldi supports multiple feature and label streams as well as combinations of neural networks, enabling the use of complex neural architectures. The toolkit is publicly-released along with a rich documentation and is designed to properly work locally or on HPC clusters. Experiments, that are conducted on several datasets and tasks, show that PyTorch-Kaldi can effectively be used to develop modern state-of-the-art speech recognizers.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icassp.2019.8683713

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 3 references

Research works printed but not linked: 35

  1. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, Proc of AISTATS, 249
  2. 10.21437/Interspeech.2018-1407 · DOI
  3. 10.1109/TETCI.2017.2762739 · DOI · Paper page
  4. 10.1109/ICASSP.2017.7953084 · DOI
  5. 10.21437/Interspeech.2016-731 · DOI
  6. 10.1109/ASRU.2015.7404805 · DOI
  7. bergstra, 2012, Random search for hyper-parameter optimization, Journal of Machine Learning Research, 13, 281
  8. ravanelli, 2018, Interpretable Convolutional Filters with SincNet, Proc of NIPS IRASL
  9. rybach, 2011, RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit, Proc of ASRU
  10. 10.1109/ASRU.2015.7404775 · DOI
  11. 10.1007/978-3-540-74628-7_40 · DOI
  12. povey, 2011, The Kaldi Speech Recognition Toolkit, Proc of ASRU
  13. mohri, 1997, Finite-state transducers in language and speech processing, Computational Linguistics, 23, 269
  14. abadi, 2016, Tensorflow: A system for large-scale machine learning, Proc USENIX OSDI Symp, 265
  15. ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proc of ICML, 448
  16. ba, 2016, Layer normalization, CoRR
  17. 10.1109/SLT.2016.7846241 · DOI
  18. 10.1109/HSCMA.2008.4538700 · doi:10.1109/hscma.2008.4538700
  19. 10.1109/TASLP.2016.2630305 · DOI
  20. goodfellow, 2016, Deep Learning
  21. 10.1109/ASRU.2015.7404837 · DOI · Paper page
  22. 10.1109/ICASSP.2014.6854051 · doi:10.1109/icassp.2014.6854051
  23. cristoforetti, 2014, The DIRHA simulated corpus, Proc of LREC, 2629
  24. young, 2006, HTK – Hidden Markov Model Toolkit
  25. ravanelli, 2017, Deep learning for Distant Speech Recognition, PhD thesis
  26. lee, 2008, Recent development of open-source speech recognition engine julius, Proc APSIPA ASC
  27. yu, 2015, Automatic Speech Recognition – A Deep Learning Approach
  28. srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15, 1929
  29. 10.1109/ICASSP.2018.8462463 · DOI
  30. kingma, 2015, Adam: A method for stochastic optimization, Proceedings of ICL
  31. 10.1016/j.specom.2018.05.001 · DOI
  32. 10.21437/Interspeech.2017-775 · DOI
  33. 10.1109/JSTSP.2017.2763455 · DOI · Paper page
  34. ravanelli, 2015, Contaminated speech training methods for robust DNN-HMM distant speech recognition, Proc of Interspeech, 756
  35. 10.1006/csla.1998.0043 · DOI · Paper page

Cited by

See all 236

Metadata

Authors
Ravanelli, M., Parcollet, T., & Bengio, Y.
Venue
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2019-05
Pages
6465-6469
ISSN
1520-6149 (ISSN-L)
OpenAlex
W2900939497
Cited by
236
References
3
FWCI
17.43
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: The Pytorch-kaldi Speech Recognition Toolkit. https://app.cochat.ai/papers/10.1109/icassp.2019.8683713
The paper
Ravanelli, M., Parcollet, T., & Bengio, Y. (2019). The Pytorch-kaldi Speech Recognition Toolkit. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2019.8683713

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.