Models and Software Realization of Russian Speech Recognition based on Morphemic Analysis

Above 20% European citizens speak in Russian therefore the task of automatic recognition of Russian continuous speech has a key significance. The main problems of ASR are connected with the complex mechanism of Russian word-formation. Totally there exist above 3 million diverse valid word-forms that is very large vocabulary ASR task. The thesis presents the novel HMM-based ASR model of Russian that has morphemic levels of speech and language representation. The model includes the developed methods for decomposition of the word vocabulary into morphemes and acoustical and statistical language modelling at the training stage and the method for word synthesis at the last stage of speech decoding. The presented results of application of the ASR model for voice access to the Yellow Pages directory have shown the essential improvement (above 75%) of the real-time factor saving acceptable word recognition rate in comparison with the baseline word-based model. Besides the modified version of the morpheme-based ASR model was proposed that excludes the grammatical endings of word-forms analyzing a recognition hypothesis. Developed ASR model provides increase of the recognition accuracy in the spoken dialogue systems. The proposed morpheme-based model can be successfully applied for ASR of other inflective Slavonic languages too. (in Russian)