Advertisement

Mandarin Language Learning System for Nasal Voice User

  • Thagirarani MuniandyEmail author
  • Thamilvaani Arvaree Alvar
  • Chong Jiang Boon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10645)

Abstract

Since the technology is growing rapidly, a lot of people nowadays start to learn the foreign language by using computer or mobile phone where they can simply download the language learning software into their phone or computer, and learn it without attending the traditional class room. However, most of the language learning software on the market does not support the nasal recognition. If a user contains nasal voice, the system may not able to recognize and determine his/her voice. Thus, nasal user may find it difficult in using this kind of language learning system. In this research, a new Mandarin Language Learning System is developed for nasal voice user. This Mandarin Language Learning System able to understand the nasal pronunciation which allows the nasal voice user to learn Mandarin without facing any problems. Once the system able to recognize the nasal pronunciation, it will increase the accuracy of recognition and also the efficiency of the system. In this research, Mel Frequency Cepstral Coefficient (MFCC) features are extracted from nasal speech signal and normal voice signal. Later extracted signals are studied the difference and matching using Dynamic Time Warping (DTW) techniques. Results obtain are compared with Hidden Markov Model (HMM). The accuracy of Nasal Voice is much higher by Combining MFCC features and DTW.

Keywords

Nasal voice Mel Frequency Cepstral Coefficient (MFCC) Dynamic Time Warping (DTW) Hidden Markov Model (HMM) 

References

  1. 1.
    Valoes, L.D.: The Importance of Language - Why Learning a Second Language is Important (2014). http://www.trinitydc.edu/continuing-education/2014/02/26/importance-of-language-why-learning-a-second-language-is-important/. Accessed 22 Nov 2015
  2. 2.
    Wantchinatimes: Number of Mandarin Chinese learners hits 100 million (2014). http://www.wantchinatimes.com/news-subclassnt.aspx?id=20140901000011&cid=1104%20/. Accessed 22 Nov 2015
  3. 3.
    Merritte, A.: Why learn a foreign language? Benefits of bilingualism (2013). http://www.telegraph.co.uk/education/educationopinion/10126883/Why-learn-a-foreign-language-Benefits-of-bilingualism.html. Accessed 22 Nov 2015
  4. 4.
    Berger, M.K.: Instrumental Assessment of Velopharyngeal Dysfunction: Multi-View Videofluoroscopy vs. Nasopharyngoscopy (n.d.). http://www.ohioslha.org/pdf/Convention/2011%20Handouts/SC18VoiceBergerC.pdf. Accessed 24 Nov 2015
  5. 5.
  6. 6.
    Tsai, R: Teaching and learning the tones of Mandarin Chinese (2011). http://www.scilt.org.uk/portals/24/library/slr/issues/24/24_5_tsai.pdf. Accessed 21 Mar 2016
  7. 7.
    Zhang, F., Yin, P.: A study of pronunciation problems of English learners in China. Asian Soc. Sci. 5(6), 141–146 (2009)Google Scholar
  8. 8.
    Finegan, E., Rickford, J.R.: Language in USA: Themes for the Twenty First Century. Cambridge University Press, Cambridge (2004)CrossRefGoogle Scholar
  9. 9.
    Lutter, M.: Mel-Frequency Cepstral Coefficients (2014). http://recognize-speech.com/feature-extraction/mfcc. Accessed 20 Mar 2016
  10. 10.
    Kaur, P., Singh, P., Garg, V.: Speech recognition system; challenges and techniques. Int. J. Comput. Sci. Inf. Technol. 3(3), 3989–3992 (Online)Google Scholar
  11. 11.
    Huang, X., Deng, L.: An overview of modern speech recognition. Accessed 26 Nov 2015Google Scholar
  12. 12.
    Lin, Y.C., Wang, H.C.: Nasal Detection in Continuous Mandarin Speech (n.d.). http://slam.iis.sinica.edu.tw/NGASR/paper/O-Cocosda2005-HCW.pdf. Accessed 26 Nov 2015
  13. 13.
    Schuller, B., Rigoll, G., Lang, M.: ‘Hidden Markov Model Based Speech Emotion Recognition’. In: IEEE ICASSP, pp. 1–3 (2003)Google Scholar
  14. 14.
    Rabiner, L.R., Juang, B.: Fundamentals of Speech Recognition, 2nd edn. Pearson Education Press, Singapore (2005)zbMATHGoogle Scholar
  15. 15.
    Tiwari, V.: “MFCC and its applications in speaker recognition”. Deptartment of Electronics Engineering, Gyan Ganga Institute of Technology and Management, Bhopal, MP, India, (Received 5 Nov 2009, Accepted 10 Feb 2010)Google Scholar
  16. 16.
    Dhingra, S.D., Nijhawan, G.: Speech recognition using MFCC and DTW. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering (An ISO 3297: 2007 Certified Organization), vol. 2, issue 8, August 2013. (Copyright to IJAREEIE)Google Scholar
  17. 17.
    Kong, J.: Speech Multi-Mode Research and Diversified Phonetics in Voice of China. Commercial Press, Beijing (2008)Google Scholar
  18. 18.
    Dang, J., Honda, K., Suzuki, H.: Morphological and acoustical analysis of the nasal and the paranasal cavities. J. Acoust. Soc. Amer. 96, 2088–2099 (1994)CrossRefGoogle Scholar
  19. 19.
    Hawkins, S., Stevens, K.: Acoustic and perceptual correlates of the non nasal-nasal distinction of vowels. J. Acoust. Soc. Amer. 77, 1560–1575 (1985)CrossRefGoogle Scholar
  20. 20.
    Gold, B., Morgan, N.: Speech and Audio Signal Processing. Wiley, New York (2000)Google Scholar
  21. 21.
    Becchetti, C., Ricotti, L.P.: Speech Recognition. Wiley, England (1999)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Thagirarani Muniandy
    • 1
    Email author
  • Thamilvaani Arvaree Alvar
    • 1
    • 2
  • Chong Jiang Boon
    • 1
  1. 1.Nilai University, Persiaran UniversityNilaiMalaysia
  2. 2.University of Nottingham Malaysia CampusSemenyihMalaysia

Personalised recommendations