Login / Signup
Incorporation of temporal structure into a vector-quantization-based preprocessor for speaker-independent, isolated-word recognition.
A. F. Bergh
Frank K. Soong
Lawrence R. Rabiner
Published in:
AT&T Tech. J. (1985)
Keyphrases
</>
vector quantization
temporal structure
speech recognition
image compression
spatio temporal
video data
human activities
speaker identification
speaker recognition
bag of features
hidden markov models
pattern recognition
multiscale
probabilistic model
object recognition
word segmentation
multimedia
machine learning