ACL RD-TEC 1.0 Summarization of H92-1034
Paper Title:
SUBPHONETIC MODELING FOR SPEECH RECOGNITION
SUBPHONETIC MODELING FOR SPEECH RECOGNITION
Authors: Mei-Yuh Hwang and Xuedong Huang
Primarily assigned technology terms:
- acoustic modeling
- algorithm
- clustering
- clustering technique
- continuous speech recognition
- database
- dictating
- distribution clustering
- error reduction
- forward-backward algorithm
- hidden markov
- hidden markov models
- hmms
- large-vocabulary continuous speech recognition
- large-vocabulary speech recognition
- learning
- modeling
- new word learning
- optimization
- phonetic transcription
- processor
- pronunciation learning
- pronunciation optimization
- recognition
- recognition systems
- reestimation
- resource management
- searching
- smoothing
- smoothing techniques
- speaker-independent continuous speech recognition
- speaker-independent resource management
- speaker-independent speech recognition
- speaker-independent training
- speech recognition
- speech recognition systems
- spelling
- sphinx-ii
- transcription
- viterbi
- viterbi algorithm
- viterbi alignment
- weighting
- word learning
Other assigned terms:
- acronym
- alphabet
- approach
- cluster
- clustering procedure
- clusters
- co-articulation
- codebook
- continuous speech
- convergence
- density function
- distribution
- duration
- entropy
- error rate
- euclidean distance
- events
- fact
- grammar
- large-vocabulary speech
- markov models
- measure
- names
- nouns
- performance evaluation
- perplexity
- person names
- phonemes
- probability
- probability density
- probability density function
- procedure
- pronunciation
- relation
- resource management task
- sentences
- speaker-independent continuous spelling task
- suffix
- technique
- technologies
- terms
- test set
- testing data
- tokens
- topology
- training
- training and testing data
- training data
- training database
- training examples
- training set
- transcriptions
- triphone
- user
- utterance
- vocabulary
- word
- word error rate
- word error rates
- word model
- word pronunciation
- word-pair grammar
- words
