A novel approach of speaker authentication by fusion of speech and image features using Artificial Neural Networks.
Anupam ShuklaRitu TiwariPublished in: Int. J. Inf. Commun. Technol. (2008)
Keyphrases
- using artificial neural networks
- speaker verification
- image features
- speaker recognition
- speech recognition
- audio visual
- automatic speech recognition
- prosodic features
- multimodal biometrics
- speaker identification
- artificial neural networks
- speaker diarization
- speech signal
- vocal tract
- speaker dependent
- identity verification
- automatic speech recognition systems
- data fusion
- acoustic features
- fusion method
- information fusion
- gaussian mixture model
- biometric authentication
- speech sounds
- image classification
- speech synthesis
- multi modal
- speaker adaptation
- automatic transcription
- speech recognizer
- neural network model
- security systems
- noisy environments
- image content
- image fusion
- object recognition
- computer vision
- broadcast news
- texture features
- mel frequency cepstral coefficients
- neural network
- keypoints
- synthesized speech
- emotion recognition
- audio stream
- friction coefficient
- visual speech
- text to speech
- user authentication
- scale space
- feature vectors
- feature extraction
- face recognition
- genetic algorithm