An improved MMSE estimator based modified group delay spectrum for Forensic Automatic Speaker Recognition.
Salim DjeghiourMhania GuertiPublished in: Int. J. Speech Technol. (2021)
Keyphrases
- speaker recognition
- gaussian mixture model
- speaker verification
- vector quantization
- probabilistic neural network
- speaker identification
- minimum mean squared error
- gaussian process regression
- speech recognition
- maximum likelihood
- speech signal
- least squares
- maximum a posteriori
- denoising
- feature space
- genetic algorithm
- information retrieval