Cepstral Domain Teager Energy for Identifying Perceptually Similar Languages
Language Identification (LID) refers to the task of identifying an unknown language from the test utterances. In this paper, a new feature set, viz.,T-MFCC by amalgamating Teager Energy Operator (TEO) and well-known Mel frequency cepstral coefficients (MFCC) is developed. The effectiveness of the newly derived feature set is demonstrated for identifying perceptually similar Indian languages such as Hindi and Urdu. The modified structure of polynomial classifier of 2 nd and 3 rd order approximation has been used for the LID problem. The results have been compared with state-of-the art feature set, viz.,MFCC and found to be effective (an average jump 21.66%) in majority of the cases. This may be due to the fact that the T-MFCC represents the combined effect of airflow properties in the vocal tract (which are known to be language and speaker dependent) and human perception process for hearing.
KeywordsVocal Tract Speaker Recognition Average Success Rate Similar Language Test Utterance
- 5.Mary, L., Yegnanarayana, B.: Autoassociative neural network models for language identification. In: Int. Conf. on Intelligent Sensing and Information Processing, ICISIP, pp. 317–320 (2004)Google Scholar
- 6.Muthusamy, Y.K., Barnard, E., Cole, R.A.: Reviewing automatic language identification. IEEE Signal Processing Mag. 11, 3341 (1994)Google Scholar
- 7.Patil, H.A.: Speaker Recognition in Indian languages: A feature based approach. Ph.D. Thesis, Department of Electrical Engineering, IIT Kharagpur, India (July 2005)Google Scholar