An Ensemble Learning-Based Language Identification System

Speech recognition from multilingual voice signals is a challenging task. It is essential to distinguish the language of the spoken phrases prior to recognizing them. This is known as automatic language identification. Automatic language identification is very much important for multilingual countries like India as people often use more than a single language while talking. In this paper, a language identification system for seven different languages from the IIIT-H Indic Speech Databases is presented. We have used line spectral frequency-based features for modelling the languages. The highest accuracy of 99.71% has been obtained with ensemble learning-based classification technique.

[1]  Antanas Verikas,et al.  Agreeing to disagree: active learning with noisy labels without crowdsourcing , 2017, International Journal of Machine Learning and Cybernetics.

[2]  Santanu Phadikar,et al.  An Ensemble Learning-Based Bangla Phoneme Recognition System Using LPCC-2 Features , 2018 .

[3]  C. Jeyalakshmi,et al.  Perceptual Features Based Rapid and Robust Language Identification System for Various Indian Classical Languages , 2018 .

[4]  David A. Ross,et al.  Automatic Language Identification in music videos with low level audio and visual features , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[6]  Sunil Kumar Kopparapu,et al.  Spoken Indian language classification using artificial neural network — An experimental study , 2017, 2017 4th International Conference on Signal Processing and Integrated Networks (SPIN).

[7]  Sanghamitra Mohanty,et al.  Phonotactic Model for Spoken Language Identification in Indian Language Perspective , 2011 .

[8]  Santanu Phadikar,et al.  Line spectral frequency-based features and extreme learning machine for voice activity detection from audio signal , 2018, Int. J. Speech Technol..

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  Santanu Phadikar,et al.  RECAL — A language identification system , 2017, 2017 International Conference on Signal Processing and Communication (ICSPC).

[11]  Shashidhar G. Koolagudi,et al.  Identification of Language using Mel-Frequency Cepstral Coefficients (MFCC) , 2012 .

[12]  Nikunj C. Oza,et al.  Online Ensemble Learning , 2000, AAAI/IAAI.

[13]  Jacob Goldberger,et al.  Intra-cluster training strategy for deep learning with applications to language identification , 2016, 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP).

[14]  F. Itakura.  Line spectrum representation of linear predictor coefficients of speech signals , 1975 .