In this paper, a deep neural network (DNN)-based poetic meter classification scheme is proposed using a fusion of musical texture features (MTF) and i-vectors. The experiment is performed in two phases. Initially, the mel-frequency cepstral coefficient (MFCC) features are fused with MTF and classification is done using DNN. MTF include timbral, rhythmic, and melodic features. Later, in the second phase, the MTF is fused with i-vectors and classification is performed. The performance is evaluated using a newly created poetic corpus in Malayalam, one of the prominent languages in India. While the MFCC-MTF/DNN system reports an overall accuracy of 80.83%, the i-vector/MTF fusion reports an overall accuracy of 86.66%. The performance is also compared with a baseline support vector machine (SVM)-based classifier. The results show that the architectural choice of i-vector fusion with MTF on DNN has merit in recognizing meters from recited poems.
Cite as: Rajan, R., Kumar, A.V., Babu, B.P. (2020) Poetic Meter Classification Using i-Vector-MTF Fusion. Proc. Interspeech 2020, 145-149, doi: 10.21437/Interspeech.2020-1794
@inproceedings{rajan20_interspeech,
author={Rajeev Rajan and Aiswarya Vinod Kumar and Ben P. Babu},
title={{Poetic Meter Classification Using i-Vector-MTF Fusion}},
year=2020,
booktitle={Proc. Interspeech 2020},
pages={145--149},
doi={10.21437/Interspeech.2020-1794}
}