Automatic Dialect Classification using SVM

Authors(5) :-Achala H A, Avni Sharma, Rakshitha G K, Ramya V, Ramesh G

Automatic Dialect Classification has attracted researchers in the field of speech signal processing. Dialect is defined as the language characteristics of a specific community. As such, dialect can be recognized by speaker phonemes, pronunciation, and traits such as tonality, loudness, and nasality. Dialect classification is a substantial tool in speech recognition and has the potential to improve the efficiency of Automatic Speech Recognition systems. This paper presents a study of different dialects in English language (American) and features that are useful for their classification. The experiment demonstrates that there are several features of the speech signal which are conducive for recognizing different dialects within a language such as chroma features and spectral features. Other speech features including MFCC and FDLP were also used with these features in order to improve the performance of the classifier. The supervised machine learning classifier that has been used in our research is the Support Vector Machine. Some refinements were introduced to the existing chroma feature extraction processes to make them more suitable for speech signal classification.

Authors and Affiliations

Achala H A
Department of Computer Science and Engineering, The National Institute of Engineering, Mysuru, Karnataka, India
Avni Sharma
Department of Computer Science and Engineering, The National Institute of Engineering, Mysuru, Karnataka, India
Rakshitha G K
Department of Computer Science and Engineering, The National Institute of Engineering, Mysuru, Karnataka, India
Ramya V
Department of Computer Science and Engineering, The National Institute of Engineering, Mysuru, Karnataka, India
Ramesh G
Department of Computer Science and Engineering, The National Institute of Engineering, Mysuru, Karnataka, India

Dialect classification, MATLAB R2014a, chroma features, spectral features, Support Vector Machine, MFCC.

  1. Giannakopoulos T, ”A method for silence removal and segmentation of speech signals, implemented in MATLAB”.
  2. Muller M, and Sebastian E, ”CHROMA TOOLBOX: MATLAB IMPLEMENTATIONS FOR EXTRACTING VARIANTS OF CHROMA-BASED AUDIO FEATURES”, 2011 .
  3. David Gerhard, ”Audio Signal Classification: History and Current Techniques”, Technical Report TRCS 2003-07 November, 2003, p. 22.
  4. Sriram Ganapathy, Samuel Thomas, and Hynek Hermansky, ”Static and Dynamic modulation spectrum for speech recognition”, ISCA, (2009)2823-2826.
  5. Parwinder Pal Singh, and Pushpa Rani, ”An Aproach to extract features using MFCC”, IOSCR Journal of Engineering(IOSRJEN), Vol.04, August. 2014, Issue 8.
  6. Kamil Aida-zade, Anar Xocayev, and Samir Rustamov, ”Speech recognition using Support Vector Machines”, Application of Information and Communication Technologies (AICT), 2016 IEEE 10th International Conference, 27 JULY 2017.
  7. Manikandan J, and Venkataramani B, ”Design of a real time automatic speech recognition system using Modified One Against All SVM classifier”, ELSEVIER, 24 June 2011.
  8. Yun Le., and John H. L. Hansen., ”Dialect Classification via Text-Independent Training and Testing for Arabic, Spanish, and Chinese”, IEEE Transactions On Audio, Speech, and Language Processing, Vol.19, No. 1, January (2011). 8
  9. Esra J. Harfash, Abdul-kareem A. Hassan, ”Automatic Arabic Dialect Classification”, International Journal of Computer Applications (0975 8887), Volume 176 No.3, October 2017.
  10. Mathworks, Inc.Matlab, 2014.

Publication Details

Published in : Volume 4 | Issue 6 | May-June 2018
Date of Publication : 2018-05-08
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 376-382
Manuscript Number : CSEIT184671
Publisher : Technoscience Academy

ISSN : 2456-3307

Cite This Article :

Achala H A, Avni Sharma, Rakshitha G K, Ramya V, Ramesh G, "Automatic Dialect Classification using SVM", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 4, Issue 6, pp.376-382, May-June-2018.
Journal URL : http://ijsrcseit.com/CSEIT184671

Article Preview

Follow Us

Contact Us