A novel hybrid feature method based on Caelen auditory model and gammatone filterbank for robust speaker recognition under noisy environment and speech coding distortion.
Ahmed KrobbaMohamed DebyecheSid-Ahmed SelouaniPublished in: Multim. Tools Appl. (2023)
Keyphrases
- speaker recognition
- noisy environments
- speaker verification
- probabilistic model
- similarity measure
- hybrid method
- noisy speech
- pattern recognition
- computational complexity
- computationally efficient
- speech signal
- vector quantization
- probabilistic neural network
- input data
- feature set
- artificial neural networks
- pattern classification
- gaussian mixture model
- speech recognition
- machine learning
- image processing