Continuous Speech Recognition Technologies—A Review

Conference paper
Part of the Lecture Notes in Mechanical Engineering book series (LNME)


Speech recognition is the most emerging field of research, as speech is the natural way of communication. This paper presents the different technologies used for continuous speech recognition. The structure of speech recognition system with different stages is described. Different feature extraction techniques for developing speech recognition system have been studied with merits and demerits. Due to the vital role of language modeling in speech recognition, various aspects of language modeling in speech recognition were presented. Widely used classification techniques for developing speech recognition system were discussed. Importance of speech corpus during the speech recognition process was described. Speech recognition tools for analysis and development purpose were explored. Parameters of speech recognition system testing were discussed. Finally, a comparative study was listed for different technological aspects of speech recognition.


Speech recognition Feature extraction Continuous speech Classification Language model HMM 



The authors would like to acknowledge the Ministry of Electronics and Information Technology (MeitY), Government of India, for providing financial assistance for this research work through “Visvesvaraya Ph.D. Scheme for Electronics and IT”.


  1. 1.
    Sarma BD, Mahadeva Prasanna SR (2017) Acoustic–phonetic analysis for speech recognition: a review. IETE Tech Rev 1–23Google Scholar
  2. 2.
  3. 3.
    Furui S (2007) Speech and speaker recognition evaluation. In: Dybkjær L, Hemsen H, Minker W (eds) Evaluation of text and speech systems. Text, speech and language technology, vol 37. Springer, DordrechtGoogle Scholar
  4. 4.
    Saon George, Chien Jen-Tzung (2012) Large-vocabulary continuous speech recognition systems: a look at some recent advances. IEEE Signal Process Mag 29(6):18–33CrossRefGoogle Scholar
  5. 5.
    Kacur J, Rozinaj G (2008) Practical issues of building robust HMM models using HTK and SPHINX systems, speech recognition, France Mihelic and Janez Zibert (ed), InTech.
  6. 6.
    Bahl LR et al (1999) Context dependent modeling of phones in continuous speech using decision trees. HLTGoogle Scholar
  7. 7.
    Cutajar M et al (2013) Comparative study of automatic speech recognition techniques. IET Signal Process 7(1):25–46Google Scholar
  8. 8.
    Lippmann Richard P (1989) Review of neural networks for speech recognition. Neural Comput 1(1):1–38CrossRefGoogle Scholar
  9. 9.
    Vimala C, Radha V (2015) Isolated speech recognition system for Tamil language using statistical pattern matching and machine learning techniques. J Eng Sci Technol (JESTEC) 10(5):617–632Google Scholar
  10. 10.
    Picone Joseph W (1993) Signal modeling techniques in speech recognition. Proc IEEE 81(9):1215–1247CrossRefGoogle Scholar
  11. 11.
    Fook CY et al (2013) Comparison of speech parameterization techniques for the classification of speech disfluencies. Turkish J Electric Eng Comput Sci 21(1):983–1994Google Scholar
  12. 12.
    Scharenborg OE, Bouwman AGG, Boves LWJ (2000) Connected digit recognition with class specific word modelsGoogle Scholar
  13. 13.
    Nieuwoudt C, Botha EC (1999) Connected digit recognition in Afrikaans using hidden Markov modelsGoogle Scholar
  14. 14.
    Bhiksha R, Singh R (2011) Design and implementation of speech recognition systems. Carniege Mellon School of Computer ScienceGoogle Scholar
  15. 15.
    Davel M, Martirosian O (2009) Pronunciation dictionary development in resource-scarce environmentsGoogle Scholar
  16. 16.
    Wu T (2009) Feature selection in speech and speaker recognition. Katholieke Universiteit LeuvenGoogle Scholar
  17. 17.
    Kumar K, Kim C, Stern RM (2011) Delta-spectral cepstral coefficients for robust speech recognition. In: 2011 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEEGoogle Scholar
  18. 18.
    Aggarwal RK, Dave M (2012) Integration of multiple acoustic and language models for improved Hindi speech recognition system. Int J Speech Technol 15(2):165–180Google Scholar
  19. 19.
    Bush M, Kopec G (1987) Network-based connected digit recognition. IEEE Trans Acoust Speech Signal Process 35(10):1401–1413Google Scholar
  20. 20.
    Singhal S, Dubey RK (2015) Automatic speech recognition for connected words using DTW/HMM for English/Hindi languages. In: 2015 Communication, control and intelligent systems (CCIS). IEEEGoogle Scholar
  21. 21.
    He ZG, Liu ZM (2012) Chinese connected word speech recognition based on derivative dynamic time warping. In: Advanced materials research, vol 542. Trans Tech PublicationsGoogle Scholar
  22. 22.
    Bernardis G, Bourlard H (1998) Improving posterior based confidence measures in hybrid HMM/ANN speech recognition systems. In: Fifth international conference on spoken language processingGoogle Scholar
  23. 23.
    Bourlard H, Morgan N (1998) Hybrid HMM/ANN systems for speech recognition: overview and new research directions. In: Adaptive processing of sequences and data structures. Springer, Berlin, pp 389–417Google Scholar
  24. 24.
    Livescu Karen, Fosler-Lussier Eric, Metze Florian (2012) Subword modeling for automatic speech recognition: past, present, and emerging approaches. IEEE Signal Process Mag 29(6):44–57CrossRefGoogle Scholar
  25. 25.
    Renals S, McKelvie D, McInnes F (1991) A comparative study of continuous speech recognition using neural networks and hidden Markov models. In: 1991 International Conference on Acoustics, Speech, and Signal Processing. ICASSP-91. IEEEGoogle Scholar
  26. 26.
    Saini P, Kaur P, Dua M (2013) Hindi automatic speech recognition using htk. Int J Eng Trends Technol (IJETT), 4(6), 2223–2229 versité de Aix-en-Provence, 1998Google Scholar
  27. 27.
    Makhoul John, Schwartz Richard (1995) State of the art in continuous speech recognition. Proc Natl Acad Sci 92(22):9956–9963CrossRefGoogle Scholar
  28. 28.
    Klatt Dennis H (1977) Review of the ARPA speech understanding project. J Acoust Soc Am 62(6):1345–1366CrossRefGoogle Scholar
  29. 29.
    Jelinek Frederick (1976) Continuous speech recognition by statistical methods. Proc IEEE 64(4):532–556CrossRefGoogle Scholar
  30. 30.
    Levinson SE, Rabiner LR, Sondhi MM (1983) An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition. Bell Syst Tech J 62(4): 1035–1074Google Scholar
  31. 31. Scholar
  32. 32.
    Dev Amita S, Agrawal S, Roy Choudhury D (2003) Categorization of Hindi phonemes by neural networks. AI & SOCIETY 17(3–4):375–382Google Scholar
  33. 33.
    Anusuya MA, Katti SK (2011) Front end analysis of speech recognition: a review. Int J Speech Technol 14(2):99–145CrossRefGoogle Scholar
  34. 34.
  35. 35.
    Bhatt S, Dev A, Jain A Hindi speech vowel recognition using hidden Markov model. In: Proceedings of The 6th International Workshop on Spoken Language Technologies for Under-Resourced Languages, pp 196–199Google Scholar
  36. 36.
    Bhatt, Shobha, Dev, Amita Jain, Anurag. Hidden Markov Model Based Speech Recognition-A Review. In: 12 th INDIACom 2018, 5th International conference on “computing for sustainable global development, 1st to 3rd March, 2018.
  37. 37.
    Bhatt S, Jain A, Dev A (2017) Hindi Speech recognition: issues and challenges. In: 11th INDIACom 4rd International conference on computing for sustainable global Development. 1st to 3rd March, 2017.
  38. 38.
    Agrawal SS, Prakash N, Jain A (2010) Transformation of emotion based on acoustic features of intonation patterns for Hindi speech. Afr J Math Comput Sci Res 3(10): 255–266Google Scholar
  39. 39.
    Madan A, Gupta D (2014) Speech feature extraction and classification: a comparative review. Int J Comput Appl 90(9)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2021

Authors and Affiliations

  1. 1.U.S.I.C.T, Guru Gobind Singh Indraprastha UniversityDwarkaIndia
  2. 2.Indira Gandhi Delhi Technical University for WomenNew DelhiIndia

Personalised recommendations