Skip to main content
SpringerLink
Log in
Book cover

International Conference on Statistical Language and Speech Processing

SLSP 2019: Statistical Language and Speech Processing pp 177–187Cite as

An Amharic Syllable-Based Speech Corpus for Continuous Speech Recognition

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 11816))

Abstract

Speech recognition systems play an important role in solving problems such as spoken content retrieval. Thus, we are interested in the task of speech recognition for low-resource languages, such as Amharic. The main challenges in solving Amharic speech recognition are the limited availability of corpora and complex morphological nature of the language. This paper presents a new corpus for the low-resource Amharic language which is suitable for training and evaluation of speech recognition systems. The corpus prepared contains 90 h of speech data with word and syllable-based annotation. Moreover, the use of syllable units for acoustic and language model in comparison with a morpheme-based model is presented. Syllable-based triphone speech recognition system provides a lower word error rate of 16.82% on the subset of the dataset. Moreover, syllable-based hybrid deep neural network with hidden Markov model provides a 14.36% word error rate.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   74.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    https://www.ethnologue.com/language/amh (last accessed on 30.11.2018).

  2. 2.

    https://github.com/hltdi/HornMorpho.

  3. 3.

    http://www.findke.ovgu.de/findke/en/Research/Data+Sets/Amharic+Speech+Corpus.html.

  4. 4.

    https://www.audacityteam.org/.

  5. 5.

    https://github.com/kaldi-asr/kaldi.git.

  6. 6.

    https://kheafield.com/code/kenlm/.

References

  1. Gales, M., Steve, Y.: The application of hidden Markov models in speech recognition. Found. Trends® Signal Process. 1(3), 195–304 (2008)

    Article  Google Scholar 

  2. Chelba, C., Timothy, H., Murat, S.: Retrieval and browsing of spoken content. IEEE Signal Process. Mag. 25(3), 39–49 (2008)

    Article  Google Scholar 

  3. Larson, M., Stefan, E.: Using syllable-based indexing features and language models to improve German spoken document retrieval. In: Eighth European Conference on Speech Communication and Technology (2003)

    Google Scholar 

  4. Getahun, A.: (Modern Amharic Grammar in a simple approach), Addis Ababa (2008)

    Google Scholar 

  5. Baye, Y.: (Short and simple Amharic Grammar). Addis Ababa (2008)

    Google Scholar 

  6. Solomon, T.: Automatic speech recognition for Amharic. Ph.D. thesis (2006). http://www.sub.unihamburg.de/opus/volltexte/2006/2981/pdf/thesis.pdf

  7. Solomon, T., Wolfgang, M.: Syllable-based speech recognition for Amharic. In: Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources. Association for Computational Linguistics (2007)

    Google Scholar 

  8. Martha, Y., Solomon, T., Wolfgang, M.: Morpheme-based automatic speech recognition for a morphologically rich language-Amharic. In: Spoken Languages Technologies for Under-Resourced Languages (2010)

    Google Scholar 

  9. Martha, Y., Solomon, T., Laurent, B.: Using different acoustic, lexical and language modeling units for ASR of an under-resourced language–Amharic. Speech Commun. 56, 181–194 (2014)

    Article  Google Scholar 

  10. Solomon, T., Wolfgang, M., Bairu, T.: An Amharic speech corpus for large vocabulary continuous speech recognition. In: 9th European Conference on Speech Communication and Technology (2005)

    Google Scholar 

  11. Michael, M., Laurent, B., Million, M.: Amharic speech recognition for speech translation. Atelier Traitement Automatique des Langues Africaines (TALAF). JEP-TALN (2016)

    Google Scholar 

  12. Nirayo, H., Sebsibe, H.: Modeling improved syllabification algorithm for Amharic. In: Proceedings of the International Conference on Management of Emergent Digital EcoSystems. ACM (2012)

    Google Scholar 

  13. Chelba, C., Timothy, H., Ramabhadran, B., Saraçlar, M.: Speech retrieval. Spoken language understanding: systems for extracting semantic information from speech (2011)

    Chapter  Google Scholar 

  14. Lee, L., et al.: Spoken content retrieval: beyond cascading speech recognition with text retrieval. IEEE/ACM Trans. Audio Speech Lang. Process. (TASLP) 23(9), 1389–1420 (2015)

    Article  Google Scholar 

  15. Larson, M., Gareth, J.: Spoken content retrieval: a survey of techniques and technologies. Found. Trends® Inf. Retr. 5(4–5), 235–422 (2012)

    Article  Google Scholar 

  16. Huang, X., et al.: Spoken Language Processing: A Guide to Theory, Algorithm, And System Development, vol. 95. Prentice Hall PTR, Upper Saddle River (2001)

    Google Scholar 

  17. Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)

    Article  Google Scholar 

  18. Can, D., Murat, S.: Lattice indexing for spoken term detection. IEEE Trans. Audio Speech Lang. Process. 19(8), 2338–2347 (2011)

    Article  Google Scholar 

  19. Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and Mandarin. In: International Conference on Machine Learning (2016)

    Google Scholar 

  20. Bahdanau, D., Chorowski, J., Serdyuk, D., Bengio, Y., et al.: End-to-end attention-based large vocabulary speech recognition. In: ICASSP, pp. 4945–4949. IEEE (2016)

    Google Scholar 

  21. Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: ICASSP, pp. 4960–4964. IEEE (2016)

    Google Scholar 

  22. Kim, S., Seltzer, M. L.: Towards language-universal end-to-end speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4914–4918. IEEE (2018)

    Google Scholar 

  23. Mikolov, T., et al.: Recurrent neural network based language model. In: 11th Annual Conference of the International Speech Communication Association (2010)

    Google Scholar 

  24. Andargachew, M.G., Binyam, E.S., Michael, G., Andreas, N.: Contemporary Amharic corpus: automatically morpho-syntactically tagged Amharic corpus. In: Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing, pp. 65–70 (2018)

    Google Scholar 

  25. Sami, V., Peter, S., Stig-Arne, G., Mikko, K.: Morfessor 2.0: python implementation and extensions for Morfessor Baseline. Aalto University publication series SCIENCE + TECHNOLOGY, 25/2013. Aalto University, Helsinki (2013)

    Google Scholar 

  26. Mulugeta, S.: The syllable structure and syllabification in Amharic. Masters of philosophy in general linguistic thesis. Department of Linguistics, Trondheim, Norway (2001)

    Google Scholar 

Download references

Acknowledgments

The authors would like to thank the DAAD and MoSHE for funding this research work and DW for allowing us to use Amharic radio program audio from their online archive.

Author information

Authors and Affiliations

  1. Fakultät für Informatik, Data and Knowledge Engineering Group, Otto von Guericke Universität Magdeburg, Universitätsplatz 2, 39106, Magdeburg, Germany

    Nirayo Hailu Gebreegziabher & Andreas Nürnberger

Authors
  1. Nirayo Hailu Gebreegziabher
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andreas Nürnberger
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nirayo Hailu Gebreegziabher .

Editor information

Editors and Affiliations

  1. Rovira i Virgili University, Tarragona, Spain

    Carlos Martín-Vide

  2. Queen Mary University of London, London, UK

    Matthew Purver

  3. Jožef Stefan Institute, Ljubljana, Slovenia

    Senja Pollak

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gebreegziabher, N.H., Nürnberger, A. (2019). An Amharic Syllable-Based Speech Corpus for Continuous Speech Recognition. In: Martín-Vide, C., Purver, M., Pollak, S. (eds) Statistical Language and Speech Processing. SLSP 2019. Lecture Notes in Computer Science(), vol 11816. Springer, Cham. https://doi.org/10.1007/978-3-030-31372-2_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-31372-2_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-31371-5

  • Online ISBN: 978-3-030-31372-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation