Systolic codebook generation [speech recognition].
Bryan Beresford-SmithJens BrecklingHeiko SchröderPeter F. SummonsPublished in: IEEE Trans. Speech Audio Process. (1993)
Keyphrases
- speech recognition
- codebook generation
- image classification
- vector quantization
- sparse coding
- hidden markov models
- speech synthesis
- speech signal
- pattern recognition
- speech recognition technology
- automatic speech recognition
- language model
- sparse representation
- speech recognition systems
- speech recognizer
- speaker identification
- image compression
- feature extraction
- bag of visual words
- visual features
- speaker independent
- bayesian networks
- image search
- natural images
- machine learning
- high dimensional
- multi modal
- visual words
- speaker adaptation
- linear combination
- face recognition