Voice Commands Recognition Method that Uses Special Spectral Density Transform

This article discusses new approach to solving specific problem of speech recognition. The problem is formulated as problem of command recognition. Commands have equal lengths (in words). Each word position has its own set of word candidates. There were developed the models for solving this problem. The models consist of spectral density estimator, convolutional neural networks and naive Bayes classifier. The author performed a comparative analysis of the models and selected the best. There was developed a graphical user interface for interacting with the best model. The result can be used as a base for creation speech recognition methods for voice user interfaces.

1. Sak, Haşim, et al. "Fast and accurate recurrent neural network acoustic models for speech recognition." arXiv preprint arXiv:1507.06947 (2015).
2. L. S. Kuravskii, S. N. Baranov Komp'yuternoe modelirovanie i analiz dannykh. Konspekty lektsii i uprazhneniya: Ucheb. posobie. – M.: RUSAVIA, 2012. – 218 p.
3. Dumoulin, Vincent, and Francesco Visin. "A guide to convolution arithmetic for deep learning." arXiv preprint arXiv:1603.07285 (2016).
4. Ch, Read, and ML MAP. "Bayesian learning." book: Machine Learning. McGraw-Hill Science/Engineering/Math (1997): 154-200.
5. Virbel, Mathieu, Thomas Hansen, and Oleksandr Lobunets. "Kivy–a framework for rapid creation of innovative user interfaces." Workshop-Proceedings der Tagung Mensch & Computer 2011. überMEDIEN| ÜBERmorgen. Universitätsverlag Chemnitz, 2011.