FuzzyGCP: A deep learning architecture for automatic spoken language identification from speech signals.
Avishek GarainPawan Kumar SinghRam SarkarPublished in: Expert Syst. Appl. (2021)
Keyphrases
- speech signal
- deep learning
- language identification
- speaker identification
- speech recognition
- automatic speech recognition
- noisy environments
- unsupervised learning
- machine learning
- broadcast news
- speech sounds
- hidden markov models
- non stationary
- language model
- multi modal
- document images
- pattern recognition
- maximum likelihood
- noisy images
- image classification
- weakly supervised
- training data
- feature selection
- neural network