Further optimisations of constant Q cepstral processing for integrated utterance and text-dependent speaker verification.
Héctor DelgadoMassimiliano TodiscoMd. SahidullahAchintya Kumar SarkarNicholas W. D. EvansTomi KinnunenZheng-Hua TanPublished in: SLT (2016)
Keyphrases
- speaker verification
- noisy environments
- speech recognition
- speaker recognition
- prosodic features
- language identification
- audio visual
- emotion recognition
- text mining
- multilayer perceptron
- information retrieval
- using artificial neural networks
- visual data
- speech signal
- face verification
- principal component analysis
- information extraction
- multiscale
- image sequences
- high level