On the use of pitch contour of Mandarin speech in text-independent speaker identification.
Sin-Horng ChenMin-Tau LinPublished in: ICASSP (1987)
Keyphrases
- speech recognition
- broadcast news
- emotion recognition
- prosodic features
- speaker independent
- formant frequencies
- speech synthesis
- spoken document retrieval
- fundamental frequency
- text to speech
- automatic speech recognition
- speech signal
- speaker identification
- acoustic features
- contour detection
- speaker verification
- hidden markov models
- speech recognizer
- active contours
- speech recognition systems
- audio visual
- pattern recognition
- contour tracking
- speaker recognition
- spoken language
- polygonal approximation
- boundary extraction
- image segmentation
- contour extraction
- language model
- image structure
- human computer interaction
- vocal tract
- digit recognition
- spontaneous speech
- multi modal
- control points
- noisy environments