GRaNN: feature selection with golden ratio-aided neural network for emotion, gender and speaker identification from voice signals.
Avishek GarainBiswarup RayFabio GiampaoloJuan D. VelásquezPawan Kumar SinghRam SarkarPublished in: Neural Comput. Appl. (2022)
Keyphrases
- speaker identification
- feature selection
- neural network
- noisy environments
- mel frequency cepstral coefficients
- probabilistic neural network
- feature extraction
- emotion recognition
- speech recognition
- gaussian mixture model
- speaker recognition
- speech signal
- audio signal
- signal processing
- text categorization
- feature set
- broadcast news
- pattern recognition
- text classification
- noise reduction
- support vector
- audio features
- machine learning
- emotional state
- knn
- face recognition
- facial expressions
- multiscale
- unsupervised learning
- sound source
- dimensionality reduction
- feature space
- high level