Data-driven speech segmentation for language identification and speaker verification.
Dijana Petrovska-DelacrétazMarcos AbaloAsmaa El HannaniGérard CholletPublished in: NOLISP (2003)
Keyphrases
- speaker verification
- language identification
- speaker recognition
- speaker identification
- prosodic features
- noisy environments
- image segmentation
- document images
- level set
- speech signal
- audio visual
- text lines
- multiscale
- neural network
- emotion recognition
- automatic speech recognition
- web information retrieval
- non stationary
- image sequences
- computer vision