Inexactness and robustness in cepstral-to-formant transformation of spoken and sung vowels.
Frantz ClermontThomas John MillhousePublished in: INTERSPEECH (2004)
Keyphrases
- speech recognition
- automatic speech recognition
- speech signal
- speaker adaptation
- hidden markov models
- language model
- speaker dependent
- speech recognition systems
- pattern recognition
- speech synthesis
- speech recognizer
- speaker identification
- cross correlation
- speaker independent
- high robustness
- real time
- information retrieval systems
- vocal tract
- feature selection
- information retrieval