In this paper we focus on automatic segmentation of recordings, which will be used for triphone synthesis unit database creation.
M. Kroul 2007, 'Automatic Speech Segmentation Based on HMM', Radioengineeringwww.radioeng.cz/fulltexts/2007/07_02_56_61.pdf. Retrieved from DOAJ CC BY 4.0 (https://creativecommons.org/licenses/by-sa/4.0/legalcode)
The problems of insufficiency of speech databases for triphone training which lead to state tying methods are explained.
I. B. Tampel 2015, 'AUTOMATIC SPEECH RECOGNITION – THE MAIN STAGES OVER LAST 50 YEARS', Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optikihttp://ntv.ifmo.ru/file/article/14070.pdf. Retrieved from DOAJ CC BY 4.0 (https://creativecommons.org/licenses/by-sa/4.0/legalcode)