Exploration of multi-source discriminative acoustic feature for speaker recognition with short-duration audio signal.
Yunfei ZiShengwu XiongPublished in: Multim. Tools Appl. (2023)
Keyphrases
- audio signal
- speaker recognition
- multi source
- speaker identification
- gaussian mixture model
- data fusion
- feature extraction
- speech recognition
- information fusion
- noisy environments
- speech signal
- mel frequency cepstral coefficients
- music information retrieval
- feature vectors
- speaker verification
- feature set
- data sources
- audio features
- broadcast news
- pattern recognition
- expectation maximization
- text classification
- noise reduction
- extracted features
- dimensionality reduction
- semi supervised
- low level
- neural network
- data sets