Mel-Scale Frequency Extraction and Classification of Dialect-Speech Signals With 1D CNN Based Classifier for Gender and Region Recognition.
Hsiang-Yueh LaiChia-Chieh HuChia-Hung WenJian-Xing WuNeng-Sheng PaiCheng-Yu YehChia-Hung LinPublished in: IEEE Access (2024)
Keyphrases
- cepstral coefficients
- speech signal
- convolutional neural network
- feature set
- feature extraction and classification
- classification method
- classification algorithm
- speech recognition
- pattern recognition
- high recognition rate
- feature extraction
- class labels
- support vector machine
- feature selection
- decision trees
- automatic speech recognition systems
- support vector
- classification accuracy
- feature space
- training set
- mel frequency cepstral coefficients
- automatic speech recognition
- recognition rate
- object recognition
- noisy environments
- non stationary
- feature vectors
- face detection
- machine learning
- text classification
- image processing
- training data
- probabilistic neural network
- hidden markov models
- information retrieval
- background noise
- linear prediction
- spectral features
- speech quality
- image classification
- blind source separation
- speech sounds
- neural network