A 450 b.p.s. vocoder with natural-sounding speech.

Yan Ming Cheng Douglas D. O'Shaughnessy

Published in: ICASSP (1990)

Keyphrases

speech recognition
audio visual
text to speech
error rate
speech signal
spoken language
endpoint detection
real time
recognition engine
spontaneous speech
speech recognizer
emotion recognition
automatic speech recognition
video sequences
image processing
machine learning
data mining
neural network