Computer Identification of Phonemes in Continuous Speech.
AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OHIO SCHOOL OF ENGINEERING
Pagination or Media Count:
An approach to computer recognition of continuous speech through phoneme identification is presented. Speech data is digitally processed through correlation, recognition, and location programs. Methods of phoneme prototype production were explored using multiple speaker discrete and average prototypes. The identification process presents a rank ordering of probable phonemic occurances at each time period. The method is used to attain an average recognition rate of 81 for discrete speech and 61 for continuous speech spoken by dissimilar speakers. Author
- Computer Hardware
- Voice Communications