Discriminative segmental cues to vowel height and consonantal place and voicing in whispered speech.
Luis M. T. JesusSara CastilhoAníbal FerreiraMaria Conceição CostaPublished in: J. Phonetics (2023)
Keyphrases
- prosodic features
- speech synthesis
- endpoint detection
- text to speech
- speech signal
- speaker verification
- vocal tract
- speech recognition
- formant frequencies
- hidden markov models
- spontaneous speech
- speaker independent
- mid level
- fundamental frequency
- speaker recognition
- speech recognition systems
- semi supervised
- automatic speech recognition
- discriminative training
- discriminative features
- discriminative information
- feature extraction
- object recognition
- spoken language
- language model
- noisy environments
- visual cues
- low level
- linear prediction
- speech recognizer
- speaker identification
- information retrieval
- discriminative learning
- action recognition
- non stationary
- high level