Language Discrimination from Speech Signal Using Perceptual and Physical Features
Humans are the most authoritative language identifiers in the province of speech recognition. They can determine within a glimpse of second whether the language of the hearing speech is known to them or not. This eventuality has come true because of the basic discrimination in the sound pattern characteristics based on frequency, time and perceptual domain. This certitude has provoked the motivation to introduce a potent scheme for the proposed plan. The proposed work includes the identification of three well-spoken languages in India that is English, Hindi and Bengali. The scheme has been encountered using some well known perceptual feature such as pitch along with some physical features like zero-crossing rate (ZCR) of the audio signal. To generate the feature set more efficient, the proposed effort has adopted mel-frequency cepstral coefficients (MFCCs) and the statistical textural features by calculating co-occurrence matrix from MFCC.
KeywordsLanguage identification system (LID) Zero-crossing rate (ZCR) Mel-frequency cepstral coefficient (MFCC)
- 1.Garg, Archana, Vishal Gupta, and Manish Jindal. “A survey of language identification techniques and applications.” Journal of Emerging Technologies in Web Intelligence 6.4 (2014): 388–400.Google Scholar
- 4.Grothe, Lena, Ernesto William De Luca, and Andreas Nürnberger. “A Comparative Study on Language Identification Methods.” LREC. 2008.Google Scholar
- 5.Behravan, Hamid, Tomi Kinnunen, and Ville Hautamäki. “Out-of-Set i-Vector Selection for Open-set Language Identification.” Odyssey 2016 (2016): 303–310.Google Scholar
- 6.Vatanen, Tommi, Jaakko J. Väyrynen, and Sami Virpioja. “Language Identification of Short Text Segments with N-gram Models.” LREC. 2010.Google Scholar
- 7.Torres-Carrasquillo, Pedro A., Douglas A. Reynolds, and John R. Deller. “Language identification using Gaussian mixture model tokenization.” Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on. Vol. 1. IEEE, 2002.Google Scholar
- 8.Lakhani, Vrishabh Ajay, and Rohan Mahadev. “Multi-Language Identification Using Convolutional Recurrent Neural Network.” arXiv preprint arXiv:1611.04010(2016).
- 9.Dehak, Najim, et al. “Language Recognition via i-vectors and Dimensionality Reduction.” Interspeech. 2011.Google Scholar
- 10.Yu, Chengzhu, et al. “UTD-CRSS system for the NIST 2015 language recognition i-vector machine learning challenge.” Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 2016.Google Scholar
- 11.Gwon, Youngjune L., et al. “Language recognition via sparse coding.” INTERSPEECH. 2016.Google Scholar
- 12.Chandrasekhar, Vijay, Mehmet Emre Sargin, and David A. Ross. “Automatic language identification in music videos with low level audio and visual features.” Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. IEEE, 2011.Google Scholar
- 13.Itrat, Madiha, et al. “Automatic Language Identification for Languages of Pakistan.” International Journal of Computer Science and Network Security (IJCSNS) 17.2.Google Scholar