Authors: Shweta Sinha; Aruna Jain; S.S. Agrawal
Addresses: Department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Ranchi, India ' Department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Ranchi, India ' KIIT Group of Colleges, KIIT Campus, Sohna Road, Gurgaon, Haryana, India
Abstract: Speech pattern produced by individuals are unique. This uniqueness is due to the accent influenced by individual's native dialect. Prior knowledge of spoken dialect provides valuable information for speaker profiling and incorporating them in the decision parameter can improve the system performance. In this paper, an auto-associative neural network model has been proposed to model intrinsic characteristics of speech features for dialect classification. This paper highlights the sufficiency of few spectral and prosodic features for identification of Hindi dialects. Experimental results show that system performance is the best when both spectral and prosodic features are combined to use as input. In the presence of noise, performance of a conventional ASR starts to degrade. The NOISEX-92 database is used to add white noise to the recorded utterances in the range of 0 dB to 20 dB. This paper evaluates the dialect classification system's performance for SNRs in this range.
Keywords: speech pattern identification; dialect classification; auto-associative neural networks; AANNs; feature compression; Hindi dialects; speech features; prosodic features; spectral features; speech patterns; speech classification; native dialects; India.
International Journal of Applied Pattern Recognition, 2015 Vol.2 No.1, pp.96 - 110
Received: 27 Aug 2014
Accepted: 06 Jan 2015
Published online: 21 Apr 2015 *