The week's pick
Random Articles
Reseach Article
Combination of Features for Multilingual Speaker Identification with the Constraint of Limited Data
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 70 - Number 6 |
| Year of Publication: 2013 |
| Authors: Nagaraja B.g., H. S. Jayanna |
10.5120/11963-7823
|
Nagaraja B.g., H. S. Jayanna . Combination of Features for Multilingual Speaker Identification with the Constraint of Limited Data. International Journal of Computer Applications. 70, 6 ( May 2013), 1-6. DOI=10.5120/11963-7823
Abstract
In the modern day digital automated world, speaker identification system plays a very important role in the field of fast growing internet based communications/transactions. In this paper, speaker identification in the context of mono, cross and multilingual are demonstrated using the two different feature extraction techniques, i. e. , Mel-Frequency Cepstral Coefficients (MFCC) and Linear Predictive Cepstral Coefficients (LPCC) with the constraint of limited data. The languages considered for the study are English (international language), Hindi (national language) and Kannada (regional language). Since the standard multilingual database is not available, experiments are carried out on our own created database of 30 speakers in the college laboratory environment who can speak the three different languages. In case of limited data condition, owing to less data the existing techniques in each stage may not provide good performance. To alleviate the problem of limited data, the vocal tract feature extracted from MFCC and LPCC techniques are combined. As a result the combination of features gives nearly 30% higher performance compared to the individual features for a set of 30 speakers.
References
- B. S. Atal, "Automatic recognition of speakers from their voices," Proc. IEEE, vol. 64(4), pp. 460475, Apr. 1976.
- H. S. Jayanna and S. R. Mahadeva Prasanna, "Analysis, Feature extraction, modeling and Testing techniques for Speaker Recognition," IETE Technical Review, vol. 26, pp. 181190, 2009.
- J. P. Campbell, Jr. ,"Speaker recognition: A tutorial," Proc. IEEE, vol. 85(9), pp. 14371462, Sep. 1997.
- Bipul Pandey, Alok ranjan, Rajeev Kumar and Anupam Shukla, "Multilingual Speaker Recognition Using ANFIS," in Proc. IEEE Int. Conf. Signal Processing Systems (ICSPS), (Dalian), pp. 714718, 2010.
- H. S. Jayanna, Limited data speaker recognition. PhD thesis, Indian Institute of Technology Guwahati, Dept. of Electronics and Communication Engg. , Guwahati, India, Nov. 2009.
- P. H. Arjun, Speaker recognition in Indian languages: A feature based approach. PhD thesis, Indian Institute of Technology Kharagpur, Dept. of Electrical Engg. , Kharagpur, India, Jul. 2005.
- Hemant A Patil, Sunayana Sitaram and Esha Sharma, "DA-IICT Crosslingual and Multilingual Corpora for Speaker Recognition," Proc. IEEE, Advances in Pattern Recognition, (Kolkata), pp. 187190, 2009.
- Rama Murty and Yegnanarayana, "Combining Evidence from residual phase and MFCC features for Speaker Recognmition," IEEE Signal Processing Letters. , vol. 13(1), pp. 5255, Jan. 2006.
- Zhi-Yi LI, Liang HE,Wei-Qiang ZHANG and Jia LIU, "Multi-Feature Combination for Speaker Recognition," Proc. IEEE, Chinese Spoken Language processing, (Tainan), pp. 318321, Dec. 2010.
- Xia Wang, Yang Cao, Feng Ding and Yuezhong Tang, "An embedded Multilingual speech recognition system for Mandarin, Cantonese, and English," Proc. IEEE, Chinese Spoken Language processing, (Beijing, China), pp. 758764, Oct. 2003.
- Ulrike Halsband, "Bilingual and multilingual language processing," Elseviers Journal of Physiology, (Paris), pp. 355369, 2006.
- Rajesh Ranjan, Sanjay Kumar Singh, Anupam Shukla and Ritu Tiwari, "Text-Dependent Multilingual Speaker Identification for Indian Languages using Artificial Neural Network," Proc. Third International Conference on Emerging Trends in Engg. and Tech. , (Goa), pp. 632 635, 2010.
- Geoffrey Durou, "Multilingual text-independent speaker identification," Proc. MIST99 Workshop, (Leusden, Netherlands), pp. 115118, 1999.
- Prateek Agrawal, Anupam Shukla and Ritu Tiwari, "Multilingual speaker recognition using Artificial Neural network," Advances in Intelligent and Soft Computing, vol. 116, pp. 19, 2009.
- Danoush Hosseinzadeh and Sridhar Krishnan, "Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs," Proc. IEEE, MMSP-2007, (Crete), pp. 365368, Oct. 2007.
- Martine Adda Decker, "Towards the Multilingual interoperability concepts in automatic speech recognition," Elseviers Speech communications, vol. 35, pp. 520, 2001.
- Olli Viikki, Imre Kiss and Jilei Tian, "speaker- and languageindependent speech recognition in Mobile communication systems," Proc. IEEE, ICASSP01, vol. 1, (Salt Lake City, UT), pp. 58, 2001.
- Nagaraja B. G. and H. S. Jayanna, "Mono and Cross Lingual Speaker Identification with the constraint of Limited data," Proc. IEEE, PRIME-2012, (Salem), pp. 439443, 2012.
- H. S. Jayanna and S. R. M. Prasanna, "Variable segmental analysis based speaker recognition in limited data conditions," IEEE-Int. Conf. Signal, Image Process. , vol. 2, (Karnataka, India), Dec. 2006.
- Picone J. W. , "Signal modeling techniques in speech recognition," Proc. IEEE, vol. 81(9), pp. 12151247, 1993.
- A comparison of speech recognition ability between LPCC and MFCC. Proc. of the National Systems Conference, NSC 95-2221-E-451-014.
- S. R. M. Prasanna, C. S. Gupta and B. Yegnanarayana, "Extraction of speaker-specific excitation information from linear prediction residual of speech," Speech Communication, vol. 48, pp. 12431261, 2006.
- G. Senthil Raja, Feature analysis and compensation for speaker recognition under stressed condition. PhD thesis, Indian Institute of Technology Guwahati, Dept. of Electronics and Communication Engg. , Guwahati, India, Jul. 2007.
Index Terms
Keywords