Extracting formants from short segments of speech using group delay functions.

Joseph M. Anand S. Guruprasad B. Yegnanarayana

Published in: INTERSPEECH (2006)

Keyphrases

speech signal
vocal tract
fundamental frequency
speech recognition
speech synthesis
text to speech
automatic speech recognition systems
formant frequencies
pattern recognition
equal length
neural network
human computer interaction
non stationary
line segments
endpoint detection