CFP last date
20 May 2024
Reseach Article

Comparative Study of Techniques for Spoken Language Dialect Identification

by Ashwini G. Pawar, Nita V. Patil
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 186 - Number 7
Year of Publication: 2024
Authors: Ashwini G. Pawar, Nita V. Patil
10.5120/ijca2024923414

Ashwini G. Pawar, Nita V. Patil . Comparative Study of Techniques for Spoken Language Dialect Identification. International Journal of Computer Applications. 186, 7 ( Feb 2024), 47-58. DOI=10.5120/ijca2024923414

@article{ 10.5120/ijca2024923414,
author = { Ashwini G. Pawar, Nita V. Patil },
title = { Comparative Study of Techniques for Spoken Language Dialect Identification },
journal = { International Journal of Computer Applications },
issue_date = { Feb 2024 },
volume = { 186 },
number = { 7 },
month = { Feb },
year = { 2024 },
issn = { 0975-8887 },
pages = { 47-58 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume186/number7/comparative-study-of-techniques-for-spoken-language-dialect-identification/ },
doi = { 10.5120/ijca2024923414 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-22T22:17:52.843728+05:30
%A Ashwini G. Pawar
%A Nita V. Patil
%T Comparative Study of Techniques for Spoken Language Dialect Identification
%J International Journal of Computer Applications
%@ 0975-8887
%V 186
%N 7
%P 47-58
%D 2024
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Identifying variations in spoken language resulting from regional or socioeconomic factors, known as dialect identification, is a significant problem in natural language processing and linguistics. This study contrasts various dialect identification approaches and evaluates their effectiveness. Techniques include deep learning, transfer learning, classical acoustic feature analysis, machine learning (ML) algorithms, phonetic and phonological analysis, lexical and grammatical feature extraction, prosodic analysis, and phonological analysis. Meticulous application of these techniques is applied to a hand-picked dataset of multiple dialects, with their performance assessed using accepted evaluation measures. These findings reveal that different techniques capture dialectal variations differently. Phonetic and phonological analysis excels at detecting minute pronunciation changes, while acoustic feature-based ML demonstrates resilience in dialect discrimination. Lexical and grammatical factors effectively recognize small differences in vocabulary and grammar usage. Prosodic features enhance dialect identification through intonation and rhythm patterns. Moreover, deep learning models showcase their capacity to learn intricate patterns from large datasets, and transfer learning techniques are effective in scenarios with limited dialect-specific data. Multilingual and cross-lingual approaches leverage shared linguistic properties for enhanced identification accuracy. Ensemble methods harness the strengths of multiple techniques, resulting in improved overall performance. This study underscores the significance of a diversified approach to dialect identification, with the choice of technique depending on factors such as available resources, data availability, and dialect complexity.

References
  1. J. K. Chambers and P. Trudgill, "Dialectology," chapter one, pp. 4-9, 2nd edition, Cambridge University Press, 1998.
  2. H. Li, B. Ma, and K. A. Lee, "Spoken Language Recognition: From Fundamentals to Practice," Proceedings of the IEEE, vol. 101, pp. 1136- 1159, 2013.
  3. J. Lee, K. Kim, and M. Chung, "Korean Dialect Identification Using Intonation Features," no. April, 2021, doi: 10.13140/RG.2.2.19397.17126.
  4. S. B. Patil, N. V. Patil, and A. S. Patil, "Speaker Independent Isolated Word Recognition using HTK for Varhadi a Dialect of Marathi," Int. J. Eng. Adv. Technol., vol. 9, no. 3, pp. 748–751, 2020, doi: 10.35940/ijeat.b3832.029320.
  5. M. Nanmalar, P. Vijayalakshmi, and T. Nagarajan, "Literary and Colloquial Dialect Identification for Tamil using Acoustic Features," IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON, vol. 2019- Octob, pp. 1303–1306, 2019, doi 10.1109/TENCON.2019.8929499.
  6. H. S. Das and P. Roy, "Optimal prosodic feature extraction and classification in parametric excitation source information for Indian language identification using neural network based Q-learning algorithm," Int. J. Speech Technol., vol. 22, no. 1, pp. 67–77, 2019, doi: 10.1007/s10772-018-09582-6.
  7. T. Ismail and L. Joyprakash Singh, “Dialect Identification of Assamese Language using Spectral Features,” Indian J. Sci. Technol., vol. 10, no. 20, pp. 1–7, 2017, doi: 10.17485/ijst/2017/v10i20/115033.
  8. N. B. Chittaragi and S. G. Koolagudi, "Acoustic features based word level dialect classification using SVM and ensemble methods," 2017 10th Int. Conf. Contemp. Comput. IC3 2017, vol. 2018-Janua, no. January, pp. 1–6, 2018, doi: 10.1109/IC3.2017.8284315.
  9. C. Madhu, A. George, and L. Mary, "Automatic language identification for seven Indian languages using higher level features," 2017 IEEE Int. Conf. Signal Process. Informatics, Commun. Energy Syst. SPICES 2017, 2017, doi: 10.1109/SPICES.2017.8091332.
  10. A. Ankit et al., "Acoustic Speech Recognition for Marathi Language Using Sphinx," ICTACT J. Commun. Technol., vol. 7, no. 3, pp. 1361– 1365, 2016, doi: 10.21917/ijct.2016.0201.
  11. Ashok Shigli, Ibrahim Patel and K Srinivasa Rao, "Automatic Dialect and Accent Speech Recognition of South Indian English," International Journal of Latest Trends in Engineering and Technology, pp 103-111,2016.
  12. R. H. Chaudhari, K. Waghmare, and B. W. Gawali, "Accent Recognition using MFCC and LPC with Acoustic Features," Int. J. Innov. Res. Comput. Commun. Eng., vol. 3, no. 3, pp. 2128–2134, 2015.
  13. G. Liu and J. H. L. Hansen, "A systematic strategy for robust automatic dialect identification," Eur. Signal Process. Conf., no. Eusipco, pp. 2138–2141, 2011.
  14. R. W. M. Ng, T. Lee, C. C. Leung, B. Ma, and H. Li, "Analysis and selection of prosodic features for language identification," 2009 Int. Conf. Asian Lang. Process. Recent Adv. Asian Lang. Process. IALP 2009, no. Figure 2, pp. 123–128, 2009, doi: 10.1109/IALP.2009.34.
  15. A. Etman and A. A. L. Beex, "Language and Dialect Identification: A survey," IntelliSys 2015 - Proc. 2015.
  16. SAI Intell. Syst. Conf., pp. 220– 231, 2015, doi: 10.1109/IntelliSys.2015.7361147.
  17. D. Raval, V. Pathak, M. Patel, and B. Bhatt, "End-to-End Automatic Speech Recognition for Gujarati," Proc. 17th Int. Conf. Nat. Lang. Process., pp. 409–419, 2020.
  18. [17] N. B. Chittaragi and S. G. Koolagudi, "Acoustic-phonetic feature based Kannada dialect identification from vowel sounds," Int. J. Speech Technol., vol. 22, no. 4, pp. 1099–1113, 2019, doi: 10.1007/s10772- 019-09646-1.
  19. A. M. Ciobanu, S. Malmasi, and L. P. Dinu, "German Dialect Identification Using Classifier Ensembles," COLING 2018 - 27th Int. Conf. Comput. Linguist. Proc. 5th work. NLP Similar Lang. Var. Dialects, VarDial 2018, pp. 288–294, 2018.
  20. S. Malmasi and M. Zampieri, "Arabic dialect identification using iVectors and ASR transcripts," VarDial 2017 - 4th Work. NLP Similar Lang. Var. Dialects, Proc., no. 2015, pp. 178–183, 2017, doi: 10.18653/v1/w17-1222.
  21. S. Sinha, A. Jain, and S. S. Agrawal, "Fusion of multi-stream speech features for dialect classification," CSI Trans. ICT, vol. 2, no. 4, pp. 243–252, 2015, doi: 10.1007/s40012-015-0063-y.
  22. S. Sinha, A. Jain, and S. S. Agrawal, "Acoustic-phonetic feature based dialect identification in Hindi speech," Int. J. Smart Sens. Intell. Syst., vol. 8, no. 1, pp. 235–254, 2015, doi: 10.21307/ijssis-2017-757.
  23. A. Ankit et al., "Acoustic Speech Recognition for Marathi Language Using Sphinx," ICTACT J. Commun. Technol., vol. 7, no. 3, pp. 1361– 1365, 2016, doi: 10.21917/ijct.2016.0201.
  24. Caka,Nebi.(2015).https://www.researchgate.net/post/What-are-the- Spectral-and-Temporal-Features-in-Speech- signal/54fb90d1d11b8b897b8b4567
  25. S. Poornima, "Basic Characteristics of Speech Signal Analysis," Int. J. Innov. Res. Dev., vol. 5, no. 4, pp. 1–5, 2016.
  26. Essien,Akpan.(2015).https://www.researchgate.net/post/What-are-the-Spectral-and-Temporal-Features-in Speech- signal/550747c7d11b8b5d358b4630
  27. B. Ma and H. Li, "A Comparative Study of Four Language Identification Systems," Int. J. Comput. Linguist. Chinese Lang. Process. Vol. 11, No. 2, June 2006, vol. 11, no. 2, pp. 159–182, 2006.
  28. Z. Tang, D. Wang, Y. Chen, L. Li, and A. Abel, "Phonetic temporal neural model for language identification," IEEE/ACMTransactions on Audio, Speech, and Language Processing, vol. 26, no. 1, pp. 134–144, 2018.
  29. M. Tirusha, “Multilingual {Phonetic} {Features} for {Indian} {Language} {Identification},” no. February, 2020.
  30. Kamble, B. C., "Speech Recognition Using Artificial Neural Network–A Review," Int. J. Comput. Commun. Instrum. Eng, 3(1), 61-64, 2016.
  31. A. Pangotra, "Review on Speech Signal Processing & Its Techniques," Eur. J. Mol. Clin. Med., vol. 7, no. 7, pp. 3049–3052, 2020.
  32. S. Dass and A. K. Yadav, "Comparative Analysis of Speech Processing Techniques at Different Stages," Springer Int. Conf. Pattern Recognit. Tech., no. 1, 2017.
  33. M. K. Sharma, "Speech Recognition: a Review," Int. J. Adv. Eng. Res. Dev., vol. 1, no. 12, 2014, doi: 10.21090/ijaerd.011244.7.
  34. V. Waghmare Shri Swami Vivekanand Shikshan Sanstha, P. K. Kurzekar, R. R. Deshmukh, V. B. Waghmare, and P. P. Shrishrimal, "Continuous Speech Recognition System: a Review," Asian J. Comput. Sci. Inf. Technol. J. homepage, vol. 4, no. 6, pp. 62–66, 2014, doi: 10.15520/ajcsit.v4i6.3.
  35. S. E. Leninson, A. Ljolie, L.G. Miller, "Continuous Speech Recognition from a Phonetic Transcription," Acoustics, Speech, and Signal Processing, vol.1 pp. 93 – 96, Apr 1990.
  36. Paul Bamberg, Yen-lu Chow, Laurence Gillick, Robert Roth and Dean Sturtevant, "The Dragon Continuous Speech Recognition System: A Real-Time Implementation," Proceedings of DARPA Speech and Natural Language Workshop, Hidden Valley, Pennsylvania, pp. 78-81, June 1990.
  37. H. R. Kim, K. W. Hwang, N. Y. Han, and Y. M. Ahn, "Korean Continuous Speech Recognition System Using Context-Dependent Phone SCHMMs," Proceedings of the Fifth Australian International Conference on Speech Science and Technology, vol. II, pp.694 - 699, 1994.
  38. Simon King, Paul Taylor, "Detection of phonological features in continuous speech using neural networks," Computer Speech & Language, vol. 14, Issue 4, October 2000, pp. 333–353.
  39. Mark Huckvale and Alex Chengyu Fang, "Using Phonologically- Constrained Morphological Analysis in Continuous Speech Recognition," Computer Speech and Language, vol. 16, pp.165-181, 2002.
  40. Achim Sixtus and Hermann Ney, "From within-word model search to across-word model search in large vocabulary continuous speech recognition," Computer Speech and Language, Vol 16, 2002, pp.245– 27.
  41. Odette Scharenborg, Louis ten Bosch, Lou Boves, "Early recognition of polysyllabic words in continuous speech," Computer Speech and Language, Vol 21, pp. 54–71, 2007.
  42. Veera Venkataramani, Shantanu Chakrabartty, William Byrne "Ginisupport vector machines for segmental minimum Bayes risk decoding of continuous speech," Computer Speech and Language, Vol 21, pp. 423–442, 2007.
  43. Gopalakrishnan Anumanchipalli, Rahul Chitturi, Sachin Joshi, Rohit Kumar, Satinder Pal Singh R.N.V. Sitaram, S P Kishore, "Development of Indian Language Speech Databases for Large Vocabulary Speech Recognition Systems," International Institute of Information Technology, Hyderabad, India July 2007.
  44. Giulia Garau, Steve Renals "Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 3, March 2008.
  45. W.J. Smit, E. Barnard, "Continuous speech recognition with sparse coding," Computer Speech and Language, vol 23, pp. 200–219, 2009.
  46. Mohammad Abushariah, Raja Ainon, Roziati Zainuddin, Moustafa Elshafei, and Othman Khalifa, "Arabic Speaker-Independent Continuous Automatic Speech Recognition Based on a Phonetically Rich and Balanced Speech Corpus," The International Arab Journal of Information Technology, vol. 9, No. 1, January 2012.
  47. N. B. Chittaragi and S. G. Koolagudi, "Automatic dialect identification system for Kannada language using single and ensemble SVM algorithms," vol. 54, no. 2. Springer Netherlands, 2020.
Index Terms

Computer Science
Information Sciences
Natural Language Processing
Language Dialect Identification
Speech Processing.

Keywords

Dialect identification deep learning acoustic analysis phonological analysis transfer learning multilingual approaches ensemble methods.