iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://doi.org/10.1007/978-981-15-3607-6_3
Toward Lexicon-Free Bangla Automatic Speech Recognition System | SpringerLink
Skip to main content
Springer Nature Link
Log in

Toward Lexicon-Free Bangla Automatic Speech Recognition System

  • Conference paper
  • First Online:
Proceedings of International Joint Conference on Computational Intelligence

Part of the book series: Algorithms for Intelligent Systems ((AIS))

  • 554 Accesses

Abstract

This article presents a lexicon-free automatic speech recognition (ASR) system for the Bangla language and investigates an open-source large bangla ASR corpus, which proved by OpenSLR. The model has been trained using improved MFCC acoustic features with deep LSTM acoustic model. Two types of decoding have been done—one is using joint decoder of connectionist temporal classification (CTC) and a statistical language model (LM) for beam decoder and another is connectionist temporal classification (CTC)-based greedy. We have achieved impressive performance than previous research work on Bangla on end-to-end approaches for non-augmented speech as an input that are 27.89% WER and 12.31% CER using beam decoder and 39.61% WER and 18.50% CER using greedy decoder. According to the best of our knowledge, this performance is state of the art for continuous Bangla speech recognition.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover 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

Institutional subscriptions

Similar content being viewed by others

References

  1. Openslr-large bengali ASR training data set. Google Inc. http://www.openslr.org/53/

  2. Abdel-Hamid O, Mohamed AR, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE/ACM Trans Audio Speech Lang Process 22(10):1533–1545

    Google Scholar 

  3. Ahmed A, Hifny Y, Shaalan K, Toral S (2016) Lexicon free Arabic speech recognition recipe. In: International conference on advanced intelligent systems and informatics. Springer, Cham, pp 147–159 (2016)

    Google Scholar 

  4. Ali MNY, Al-Mamun SA, Das JK, Nurannabi AM (2008) Morphological analysis of Bangla words for universal networking language. In: 2008 third international conference on digital information management. IEEE, pp 532–537

    Google Scholar 

  5. Alif Al Amin M, Towhidul Islam M, Kibria S, Shahidur Rahman M (2019) Continuous Bengali speech recognition based on deep neural network, pp 1–6. https://doi.org/10.1109/ECACE.2019.8679341

  6. Amodei D, Ananthanarayanan S, Anubhai R, Bai J, Battenberg E, Case C, Casper J, Catanzaro B, Cheng Q, Chen G, et al (2016) Deep speech 2: end-to-end speech recognition in english and mandarin. In: International conference on machine learning, pp 173–182

    Google Scholar 

  7. Bills A, David A, Dubinski E, Fiscus J, Gillies B, Harpe M, Jarrett A, Encarnación M, Molina P, Ray J, Rytting A, Paget S, Shen W, Silber R, Tzoukermann E, Wong J (2016) IARPA-babel103b-v0.4b LDC2016S08. Web Download. Linguistic Data Consortium, Philadelphia. https://catalog.ldc.upenn.edu/LDC2016S08 (2016)

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

    Google Scholar 

  9. Chorowski J, Bahdanau D, Serdyuk D, Cho K, Bengio Y (2015) Attention-based models for speech recognition. In: Advances in neural information processing systems

    Google Scholar 

  10. Das A, Bandyopadhyay S (2010) Morphological stemming cluster identification for Bangla. In: Knowledge sharing event-1: task, vol 3

    Google Scholar 

  11. Das B, Mandal S, Mitra P (2011) Bengali speech corpus for continuous automatic speech recognition system. In: 2011 International conference on speech database and assessments (Oriental COCOSDA). IEEE, pp 51–55

    Google Scholar 

  12. Graves A (2012) Sequence transduction with recurrent neural networks. arXiv:1211.3711

  13. Hannun A, Case C, Casper J, Catanzaro B, Diamos G, Elsen E, Prenger R, Satheesh S, Sengupta S, Coates A, et al (2014) Deep speech: scaling up end-to-end speech recognition. arXiv:1412.5567

  14. Hasnat M, Molwa J, Khan M (2007) Isolated and continuous Bangla speech recognition: implementation. Performance and application perspective

    Google Scholar 

  15. Hinton G, Deng L, Yu D, Dahl GE, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, et al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82–97

    Google Scholar 

  16. Hossain M, Rahman M, Prodhan UK, Khan M, et al (2013) Implementation of back-propagation neural network for isolated Bangla speech recognition. arXiv:1308.3785

  17. Huang X, Baker J, Reddy R (2014) A historical perspective of speech recognition. Commun ACM 57(1):94–103

    Article  Google Scholar 

  18. Islam M (2009) Research on Bangla language processing in Bangladesh: progress and challenges. In: 8th international language & development conference, pp 23–25

    Google Scholar 

  19. Jaitly N, Le QV, Vinyals O, Sutskever I, Sussillo D, Bengio S (2016) An online sequence-to-sequence model using partial conditioning. In: Advances in neural information processing systems, pp 5067–5075

    Google Scholar 

  20. Juang BH, Rabiner LR (2005) Automatic speech recognition–a brief history of the technology development. Georgia Institute of Technology. Atlanta Rutgers University and the University of California. Santa Barbara, vol 1, p 67

    Google Scholar 

  21. Karim R, Rahman MS, Iqbal MZ (2002) Recognition of spoken letters in Bangla. In: Proceedings of the 5th international conference on computer and information technology (ICCIT02)

    Google Scholar 

  22. Nahid MMH, Islam MA, Islam MS (2016) A noble approach for recognizing Bangla real number automatically using CMU Sphinx4. In: 2016 5th international conference on informatics, electronics and vision (ICIEV). IEEE, pp 844–849

    Google Scholar 

  23. Nahid MMH, Purkaystha B, Islam MS (2017) Bengali speech recognition: a double layered LSTM-RNN approach. In: 2017 20th international conference of computer and information technology (ICCIT). IEEE, pp. 1–6

    Google Scholar 

  24. Paul AK, Das D, Kamal MM (2009) Bangla speech recognition system using LPC and ANN. In: 2009. ICAPR’09. Seventh international conference on, advances in pattern recognition. IEEE, pp 171–174

    Google Scholar 

  25. Qian Y, Woodland PC (2016) Very deep convolutional neural networks for robust speech recognition. In: 2016 IEEE on spoken language technology workshop (SLT). IEEE, pp 481–488

    Google Scholar 

  26. Raffel C, Luong MT, Liu PJ, Weiss RJ, Eck D (2017) Online and linear-time attention by enforcing monotonic alignments. arXiv:1704.00784

  27. Rahman K, Hossain M, Das D, Islam T, Ali M (2003) Continuous Bangla speech recognition system. In: Proceedings of the 6th international conference on computer and information technology (ICCIT03)

    Google Scholar 

  28. Rahman Saurav J, Amin S, Kibria S, Shahidur Rahman M (2018) Bangla speech recognition for voice search. In: 2018 international conference on Bangla speech and language processing (ICBSLP), pp 1–4. https://doi.org/10.1109/ICBSLP.2018.8554944

  29. Rath SP, Povey D, Veselý K, Cernocký J (2013) Improved feature processing for deep neural networks, pp 109–113

    Google Scholar 

  30. Shrishrimal PP, Deshmukh RR, Waghmare VB (2012) Indian language speech database: a review. Int J Comput Appl 47(5):17–21

    Google Scholar 

  31. Sinha S, Jain A, Agrawal SS (2014) Speech processing for hindi dialect recognition. In: Advances in signal processing and intelligent recognition systems. Springer, Cham, pp 161–169

    Google Scholar 

  32. Stolcke A (2002) Srilm-an extensible language modeling toolkit. In: Seventh international conference on spoken language processing

    Google Scholar 

  33. Sultana S, Akhand M, Das PK, Rahman MH (2012) Bangla speech-to-text conversion using SAPI. In: 2012 international conference on computer and communication engineering (ICCCE). IEEE, pp 385–390

    Google Scholar 

  34. Sumit SH, Al Muntasir T, Zaman MA, Nandi RN, Sourov T (2018) Noise robust end-to-end speech recognition for Bangla language. In: 2018 international conference on Bangla speech and language processing (ICBSLP). IEEE, pp 1–5

    Google Scholar 

  35. Zhang Y, Chan W, Jaitly N (2017) Very deep convolutional networks for end-to-end speech recognition. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4845–4849

    Google Scholar 

  36. Zhang Y, Pezeshki M, Brakel P, Zhang S, Bengio CLY, Courville A (2017) Towards end-to-end speech recognition with deep convolutional neural networks. arXiv:1701.02720

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Kumargaon, Sylhet, 3114, Bangladesh

    Md. Mehadi Hasan, Md. Ariful Islam, Shafkat Kibria & Muhammad Shahidur Rahman

Authors
  1. Md. Mehadi Hasan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Md. Ariful Islam
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shafkat Kibria
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Muhammad Shahidur Rahman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Md. Mehadi Hasan .

Editor information

Editors and Affiliations

  1. Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh

    Mohammad Shorif Uddin

  2. Department of Mathematics, South Asian University, New Delhi, India

    Jagdish Chand Bansal

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mehadi Hasan, M., Ariful Islam, M., Kibria, S., Rahman, M.S. (2020). Toward Lexicon-Free Bangla Automatic Speech Recognition System. In: Uddin, M.S., Bansal, J.C. (eds) Proceedings of International Joint Conference on Computational Intelligence. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-15-3607-6_3

Download citation

Publish with us

Policies and ethics

Search

Navigation