Adaptation of an isolated word speech recognition system to continuous speech using multisection LVQ codebook modification and prosodic parameter transformation.
Anastasios TsopanoglouJohn MourjopoulosGeorge K. KokkinakisPublished in: Speech Communication (1994)
Keyphrases
- speech recognition
- isolated word
- speaker adaptation
- vector quantization
- automatic speech recognition
- hidden markov models
- learning vector quantization
- language model
- pattern recognition
- supervised learning
- parameter values
- bag of words
- neural network
- speech synthesis
- input parameters
- feature vectors
- information retrieval
- visual words
- image compression
- parameter space
- machine learning
- parameter settings
- image representation
- linear transformation
- semi supervised
- adaptation process
- multiresolution
- computer vision