Unsupervised intra-speaker variability compensation based on Gestalt and model adaptation in speaker verification with telephone speech.
Néstor Becerra YomaClaudio GarretónCarlos MolinaFernando HuenupánPublished in: Speech Commun. (2008)
Keyphrases
- speaker verification
- speaker recognition
- prosodic features
- noisy environments
- audio visual
- acoustic features
- emotion recognition
- speech recognition
- speaker diarization
- multilayer perceptron
- face verification
- noise reduction
- using artificial neural networks
- pattern recognition
- speech signal
- automatic speech recognition