Speech Personality Recognition Based on Annotation Classification Using Log-Likelihood Distance and Extraction of Essential Audio Features.
Zhen-Tao LiuAbdul RehmanMin WuWeihua CaoMan HaoPublished in: IEEE Trans. Multim. (2021)
Keyphrases
- probabilistic model
- log likelihood
- audio features
- mel frequency cepstral coefficients
- pattern recognition
- feature set
- feature extraction
- density estimation
- audio visual
- speaker identification
- machine learning
- decision trees
- acoustic features
- scoring function
- classification accuracy
- speech recognition
- object recognition
- feature vectors
- visual features
- image classification
- maximum likelihood
- supervised learning
- speech signal
- low level
- computer vision
- music information retrieval
- em algorithm
- data sets
- visual information
- knn
- information retrieval
- training set
- feature space