ENCS5344 | SPOKEN LANGUAGE PROCESSING

Speech production, hearing and perception, speech sounds (phonemes and phones), speech production models, short-time time-frequency analysis, basics features extraction, Mel-frequency Cepstral coefficients, linear predictive coding, audio pattern recognition, automatic speech recognition, hidden Markov models, Viterbi decoding and Baum Welch algorithms, speaker and dialect recognition, language identification.

Parent Business Unit ID: 
Prerequisite: 
ENCS3340 | ARTIFICIAL INTELLIGENCE
ENCS4310 | DIGITAL SIGNAL PROCESSING (DSP)