Audio enhancing with DNN autoencoder for speaker recognition.
Oldrich PlchotLukás BurgetHagai AronowitzPavel MatejkaPublished in: ICASSP (2016)
Keyphrases
- speaker recognition
- speaker identification
- gaussian mixture model
- mel frequency cepstral coefficients
- vector quantization
- speaker verification
- speech recognition
- probabilistic neural network
- speech signal
- broadcast news
- audio visual
- noisy environments
- emotion recognition
- language identification
- feature extraction
- multimedia
- audio features
- visual information
- visual data
- machine learning
- acoustic features
- particle swarm optimization
- feature vectors