Extrinsic normalization of vowel formant values based on cardinal vowels mapping.
Maria-Gabriella Di BenedettoJean-Sylvain LiénardPublished in: ICSLP (1992)
Keyphrases
- vocal tract
- speech signal
- speech recognition
- formant frequencies
- speech synthesis
- speech recognition systems
- linear prediction
- automatic speech recognition
- image acquisition
- speaker independent
- vowel phonemes
- hidden markov models
- preprocessing
- camera calibration
- noisy environments
- speaker identification
- normalization method
- fundamental frequency
- speech sounds
- databases
- pixel values
- standard deviation
- user defined
- relational databases
- pattern recognition
- information retrieval
- database