Investigation of Spoken-Language Detection in Multilingual Environment

Authors

  • Vinay Kumar Jain Shri Shankaracharya Technical Campus, Shri Shankaracharya Group of Institution, Junwani, Chhattisgarh 490020, Bhilai, India

Keywords:

Pitch,, Formant, MFCC, GFCC,, Multilingual

Abstract

Spoken language contains lot of information such as information about the content of a message and information about the speaker of that message. Content is composed of several levels of linguistic information like phonological information, morphological information, syntactic information, and the semantic information. For Present study, Multilingual Speech Processing database of different speakers has been recorded in three Indian languages, i.e., Hindi, Marathi, and Rajasthani. The sentences consist of consonants, i.e., “Cha”, “Sha” and “Jha”. Total numbers of speakers involved are 30 including males and females. The basic features of the speech signal: Pitch and first three Formant F1, F2 and F3 are calculated through PRAAT software whereas cepstral features Mel- Frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) has been extracted from MATLAB software. A model is proposed to identify the speaker by multi language speech signal of a speaker using MFCC, GFCC and combine features as acoustic features. For training and testing, is performed on using neural network function Resilient Back Propagation Algorithm and Radial Basis Functions and results are compared. In this experiment accuracy of spoken language identification is 94.77% using BPA and 96.52% using RBF neural network.

References

Rathore P.S. and Tripathi N. 2014. Multilingual Person Identification, International Journal of Engineering Trends and Technology ,10(1):1-3.

Bourlard H. And Dines J. 2011. Current trends in multilingual speech processing, Indian Academy of Sciences, Sadhan 36(5): 885–915.

Tripathi N.,2006. Study of face and speech parameters and identification of their relationship for emotional status recognition, Ph.D thesis, NIT Raipur.

Bashar M. A., Ahmed M. T, Syduzzaman M., Ray P. J. and Islam A. Z. M. T. 2014.Text-Independent Speaker Identification System Using Average Pitch And Formant Analysis. International Journal on Information Theory (IJIT), 3(3):23-30.

Vimala.C and Radha.V, 2014. Suitable Feature Extraction and Speech Recognition Technique for Isolated Tamil Spoken Words. International Journal of Computer Science and Information Technologies, 5 (1): 378-383.

Pahwa A. and Aggarwal G. 2016. Speech Feature Extraction for Gender Recognition. I.J. Image, Graphics and Signal Processing, 9, :17-25

Moinuddin M. and Kanth A. N. 2014. Speaker Identification based on GFCC using GMM, International Journal of Innovative Research in Advanced Engineering (IJIRAE), 1(8):224-232.

Zhao X. and Wang D.,2013. Analyzing Noise Robustness of MFCC and GFCC Features In Speaker Identification, IEEE-ICASSP: 7204-7208.

Sarkar S., Rao K.S., Nandi D. and Kumar S.B.S., Multilingual speaker recognition on Indian languages, Annual IEEE India Conference (INDICON), Mumbai,2013:1-5.

Sharma S., Shukla A. and Mishra P., 2014. Speech and Language Recognition using MFCC and DELTA-MFCC, International Journal of Engineering Trends and Technology, 12(9):449-452.

Burgos W. 2014. Gammatone And Mfcc Features In Speaker Recognition, Mtech thesis, Florida Institute of Technology Melbourne, Florida.

Bhattacharjee U. and Sarmah K. 2012, A multilingual speech database for speaker recognition, IEEE International Conference on Signal Processing, Computing and Control (ISPCC), Waknaghat Solan:1-5.

Downloads

Published

2021-11-18

How to Cite

Jain, V. K. (2021). Investigation of Spoken-Language Detection in Multilingual Environment. CSVTU International Journal of Biotechnology, Bioinformatics and Biomedical, 6(02). Retrieved from http://csvtujournal.in/index.php/ijbbb/article/view/159

Issue

Section

Articles