Abstract
The paper explains and illustrates how the concept of word classes can be added to the widely used open-source speech recognition toolkit Kaldi. The suggested extensions to existing Kaldi recipes are limited to the word-level grammar (G) and the pronunciation lexicon (L) models. The implementation to modify the weighted finite state transducers employed in Kaldi makes use of the OpenFST library. In experiments on small and mid-sized corpora with vocabulary sizes of 1.5 K and 5.5 K respectively a slight improvement of the word error rate is observed when the approach is tested with (hand-crafted) word classes. Furthermore it is shown that the introduction of sub-word unit models for open word classes can help to robustly detect and classify out-of-vocabulary words without impairing word recognition accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See for example https://sourceforge.net/p/kaldi/discussion/1355348/thread/c7c5e4f6/.
- 2.
To save resources it was decided during the design phase of Evar that the system should only be able to provide information about express trains (so called IC/ICE trains). As a consequence only city names with an express train station were included in the vocabulary of the recognizer. While this may seem intuitive at first, it lead to a large number of OOVs because even cooperative users were not always sure in which cities there were express train stops.
References
Ney, H., Essen, U.: On smoothing techniques for bigram-based natural language modelling. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, ICASSP 1991, Toronto, Canada (1991)
Brown, P.F., et al.: Class-based \(N\)-gram models of natural language. In: Computational Linguistics, vol. 18, pp. 467–479. MIT Press, Cambridge (1992)
Kneser, R., Ney, H.: Improved clustering techniques for class-based statistical language modelling. In: Proceedings of EUROSPEECH 1993, Berlin, Germany (1993)
Bazzi, I., Glass, J.R.: A multi-class approach for modelling out-of-vocabulary words. In: Proceedings of INTERSPEECH 2002, Denver, Colorado, USA (2002)
Schaaf, T.: Detection of OOV words using generalized word models and a semantic class language model. In: Proceedings of INTERSPEECH 2001, Aalborg, Denmark, pp. 2581–2584 (2001)
Gallwitz, F.: Integrated stochastic models for spontaneous speech recognition. Ph.D. thesis, Pattern Recognition Lab, Computer Science Department 5, University of Erlangen-Nuremberg, Logos Verlag, Berlin, Germany (2002)
Seneff, S., Wang, C., Hetherington, I.L., Chung, G.: A dynamic vocabulary spoken dialogue interface. In: Proceedings of INTERSPEECH 2004, Jeju Island, Korea (2004)
Aleksic, P.S., Allauzen, C., Elson, D., Kracun, A., Casado, D.M., Moreno, P.J.: Improved recognition of contact names in voice commands. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, South Brisbane, Queensland, Australia, pp. 5172–5175 (2015)
Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society (2011)
Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. Comput. Speech Lang. 16(1), 69–88 (2002). Elsevier
Allauzen, C., Riley, M.D., Schalkwyk, J., Skut, W., Mohri, M.: OpenFst: a general and efficient weighted finite-state transducer library. In: Holub, J., Žd’árek, J. (eds.) CIAA 2007. LNCS, vol. 4783, pp. 11–23. Springer, Heidelberg (2007)
Schukat-Talamazzini, E.G.: Automatische Spracherkennung - Grundlagen, statistische Modelle und effiziente Algorithmen. Vieweg, Braunschweig (1995)
Eckert, W., Kuhn, T., Niemann, H., Rieck, S., Scheuer, A., Schukat-Talamazzini, E.G.: A spoken dialogue system for German intercity train timetable inquiries. In: Proceedings of EUROSPEECH 1993, Berlin, Germany, pp. 1871–1874 (1993)
Stemmer, G.: Modeling variability in speech recognition. Ph.D. thesis, Pattern Recognition Lab, Computer Science Department 5, University of Erlangen-Nuremberg, Logos Verlag, Berlin, Germany (2005)
Wahlster, W.: SmartWeb: Mobile applications of the Semantic Web. GI Jahrestagung 1, 26–27 (2004)
Mögele, H., Kaiser, M., Schiel, F.: SmartWeb UMTS speech data collection: the SmartWeb handheld corpus. In: Procedings of LREC 2006, Genova, Italy, pp. 2106–2111 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Horndasch, A., Kaufhold, C., Nöth, E. (2016). How to Add Word Classes to the Kaldi Speech Recognition Toolkit. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech, and Dialogue. TSD 2016. Lecture Notes in Computer Science(), vol 9924. Springer, Cham. https://doi.org/10.1007/978-3-319-45510-5_56
Download citation
DOI: https://doi.org/10.1007/978-3-319-45510-5_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45509-9
Online ISBN: 978-3-319-45510-5
eBook Packages: Computer ScienceComputer Science (R0)