TECHICAL Series MATHEMATICS • INFORMATICS • PHYSICS Series PHILOLOGY Series ECONOMIC SCIENCES Sereies EDUCATIONAL SCIENCES Series LAW AND SOCIAL SCIENCES Series
Automatic Speech Recognition: Methods and Applications for Romanian Language
(Recunoaşterea automată a vorbirii: metode şi aplicaţii pentru limba română)
Vol LXVI • No. 4/2014
Daniela Şchiopu
Universitatea Petrol-Gaze din Ploieşti, Bd. Bucureşti 39, Ploieşti e-mail: daniela_schiopu@yahoo.com

 Keywords   automatic speech recognition, dynamic time warping, hidden Markov models, mel- frequency cepstral coefficients, statistical models

 Abstract
For many reasons, speech is a convenient mean for a human to interact with a machine. Computer speech recognition (or automatic speech recognition, ASR) is the process of converting the message uttered by a person into a sequence of words. In spite of all technological advances made in the field of ASR, due to many factors that influence the recognition rate, speech recognition is still a challenging research area. In this paper, the author presents two speech recognition systems for Romanian language, one based on statistical methods, hidden Markov models, and the other one based on dynamic time warping. The systems were tested for a set of voice commands applied to control electronic devices.

 Rezumat
Vorbirea este un mijloc convenabil de interacţiune omului cu o maşină. Recunoaşterea limbii vorbite de către un computer (sau recunoaşterea automată a vorbirii, RAV) este definită ca fiind procesul de transformare a unui mesaj rostit de o persoană într-o secvenţă de cuvinte. În ciuda tuturor progreselor realizate în acest domeniu, datorită multor factori care influenţează rata de recunoaştere, RAV rămâne încă un domeniu de cercetare complex şi provocator. În acest articol, autoarea prezintă două sisteme de recunoaştere a vorbirii pentru limba română, unul bazat pe reţele Markov ascunse, iar celălalt bazat pe metoda de aliniere temporală. Sistemele au fost experimentate pentru comenzi vocale care pot controla dispozitive electronice.



Journal INFO (ISSN 1224-8495)
Vol LXVIII • No. 3/2016
Vol LXVIII • No. 2/2016
Vol LXVIII • No. 1/2016
Vol LXVII • No. 4/2015
Vol LXVII • No. 3/2015
Vol LXVII • No. 2/2015
Vol LXVII • No. 1/2015
Vol LXVI • No. 4/2014
Vol LXVI • No. 3/2014
Vol LXVI • No. 2/2014
Vol LXVI • No. 1/2014
Vol LXV • No. 4/2013
Vol LXV • No. 3/2013
Vol LXV • No. 2/2013
Vol LXV • No. 1/2013
Vol LXIV • No. 4/2012
Vol LXIV • No. 3/2012
Vol LXIV • No. 2/2012
Vol LXIV • No. 1/2012
Vol LXIII • No. 4/2011
Vol LXIII • No. 3/2011
Vol LXIII • No. 2/2011
Vol LXIII • No. 1/2011
Vol LXII • No. 4B/2010
Vol LXII • No. 4A/2010
Vol LXII • No. 3B/2010
Vol LXII • No. 3A/2010
Vol LXII • No. 2/2010 (Special Issue WELDING 2010)
Vol LXII • No. 1/2010
Vol LXI • No. 4/2009
Vol LXI • No. 3/2009 (Special Issue SPC 2009)
Vol LXI • No. 2/2009
Vol LXI • No. 1/2009
Vol LX • No. 4/2008
Vol LX • No. 3/2008
Vol LX • No. 2/2008
Vol LX • No. 1/2008
Vol LIX • No. 4/2007
Vol LIX • No. 3/2007
Vol LIX • No. 2/2007
Vol LIX • No. 1/2007
Vol LVIII • No. 4/2006
Vol LVIII • No. 3/2006
Vol LVIII • No. 2bis/2006
Vol LVIII • No. 2/2006
Signup
Forgot Password
  © copyright 2006 Universitatea Petrol - Gaze din Ploiesti