Title :
HMM-neural network monophone models for computer based articulation training for the hearing impaired
Author :
Devarajan, Mukund ; Meng, Fansheng ; Hix, Penny ; Zahorian, Stephen A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
Abstract :
A visual speech training aids for persons with hearing impairments has been developed using a Windows-based multimedia computer. In previous papers, the signal processing steps and display options have been described for giving real-time feedback about the quality of pronunciation for 10 steady-state American English monopthong vowels (/aa/, /iy/, /uw/, /ae/, /er/, /ih/, /eh/, /ao/, /ah/, and /uh/). This vowel training aid is thus referred to as a vowel articulation training aid (VATA). In the present paper, methods are described to develop a monophone-based hidden Markov model/neural network recognizer such the real-time visual feedback can be given about the quality of pronunciation of short words and phrases. Experimental results are reported which indicate a high degree of accuracy for labeling and segmenting the CVC database developed for "training" the display.
Keywords :
handicapped aids; hearing aids; hidden Markov models; multimedia systems; natural language interfaces; neural nets; speech processing; speech recognition; speech-based user interfaces; CVC database; HMM-neural network monophone model; Windows-based multimedia computer; computer based articulation; monophone-based hidden Markov model; neural network recognizer; real-time feedback; signal processing steps; steady-state American English monopthong vowels; vowel articulation training aid; Auditory system; Computer displays; Computer networks; Hidden Markov models; Labeling; Neural networks; Neurofeedback; Signal processing; Speech recognition; Steady-state;
Conference_Titel :
Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
Print_ISBN :
0-7803-7965-9
DOI :
10.1109/ICME.2003.1221282
