ACL RD-TEC 1.0 Summarization of H89-1016
Paper Title:
RECENT PROGRESS IN THE SPHINX SPEECH RECOGNITION SYSTEM
RECENT PROGRESS IN THE SPHINX SPEECH RECOGNITION SYSTEM
Authors: Kai-Fu Lee and Hsiao-Wuen Hon and Mei-Yuh Hwang
Primarily assigned technology terms:
- algorithm
- beam search
- clustering
- clustering algorithm
- context generalization
- continuous speech recognition
- corrective training
- cross-validation
- data collection
- database
- dynamic programming
- dynamic programming algorithm
- error correction
- error-correction
- forward-backward algorithm
- hidden markov
- hidden markov model
- hidden markov models
- hmms
- learning
- learning algorithm
- lpc analysis
- markov model
- matching
- maximum-likelihood
- measuring
- modeling
- parsing
- programming algorithm
- recognition
- recognition algorithm
- recognition system
- recognition systems
- recognizer
- reinforcement learning
- reinforcement training
- resource management
- search
- segmentation
- speaker-independent continuous speech recognition
- speech recognition
- speech recognition system
- speech recognition systems
- subword modeling
- text-to-text alignment
- training algorithm
- training procedure
- triphone clustering
- viterbi
- viterbi search
- word recognition
Other assigned terms:
- beam
- between-word coarticulation
- case
- clustering procedure
- clusters
- co-articulation
- codebook
- coefficient
- continuous speech
- convergence
- derivational equivalence
- distance metric
- distribution
- duration
- duration model
- entropy
- error rate
- evaluations
- feature
- feature sets
- frame
- function word
- function words
- gaussian distribution
- generation
- grammar
- grammars
- implementation
- interpolation
- knowledge
- large training
- learning paradigm
- markov models
- maximum-likelihood procedure
- measures
- model parameters
- null grammar
- ordered list
- perplexity
- phonological rules
- phrase
- probabilities
- probability
- procedure
- pronunciation
- recognition rate
- representations
- resource management task
- sentence
- sentences
- silence
- speaker-independent task
- speech representation
- symbol
- symbols
- technique
- test data
- testing data
- training
- training and testing data
- training corpus
- training data
- training phase
- training set
- transition probabilities
- triphone
- utterance
- vocabulary
- word
- word boundary
- word duration
- word pair
- word pair grammar
- word-pair grammar
- words
