Speaker identification based on frequency distribution of vector-quantized spectra.
Katsuhiko ShiraiKazunori ManoShunichi IshigePublished in: Systems and Computers in Japan (1988)
Keyphrases
- speaker identification
- frequency distribution
- vector quantized
- vector quantization
- gaussian mixture model
- visual words
- image compression
- speech recognition
- progressive transmission
- speech signal
- noisy environments
- broadcast news
- feature extraction
- image classification
- non stationary
- neural network
- spatial information
- em algorithm
- co occurrence
- probabilistic model
- information retrieval