Predicting Formant Frequencies from MFCC Vectors.
Jonathan DarchBen MilnerXu ShaoSaeed VaseghiQin YanPublished in: ICASSP (1) (2005)
Keyphrases
- formant frequencies
- speech signal
- feature vectors
- speech recognition
- vector space
- feature extraction
- hidden markov models
- automatic speech recognition
- vowel phonemes
- speaker identification
- non stationary
- noisy environments
- spectral analysis
- maximum likelihood
- vocal tract
- mel frequency cepstral coefficients
- input data
- high dimensional