Unsupervised Speech Representation Pooling Using Vector Quantization.
Jeongkyun ParkKwanghee ChoiHyunjun HeoHyung-Min ParkPublished in: CoRR (2023)
Keyphrases
- vector quantization
- speaker recognition
- image compression
- vector quantizer
- reduced complexity
- distortion measure
- fractal image compression
- input vector
- speech recognition
- vector quantized
- codebook design
- neural gas
- unsupervised learning
- memory based learning
- joint source and channel coding
- index table
- supervised learning
- speaker identification
- entropy constrained
- fractal image coding
- face recognition
- image processing
- computer vision
- finite state vector quantization
- neural network