ACL RD-TEC 1.0 Summarization of H91-1011
Paper Title:
MODELLING CONTEXT DEPENDENCY IN ACOUSTIC-PHONETIC AND LEXICAL REPRESENTATIONS
MODELLING CONTEXT DEPENDENCY IN ACOUSTIC-PHONETIC AND LEXICAL REPRESENTATIONS
Authors: Michael Phillips and James Glass and Victor Zue
Primarily assigned technology terms:
- algorithm
- classification
- classifier
- classifiers
- components analysis
- continuous-speech recognition
- corrective training
- corrective training procedure
- hierarchical segmentation
- linear discriminant
- modelling
- n-best search
- normalization
- optimization
- optimization procedure
- processing
- recognition
- recognition system
- recognition system \
- recognition systems
- recognizer
- resource management
- scoring
- search
- segmentation
- segmentation algorithm
- speech recognition
- speech recognition systems
- speech-recognition
- splitting
- training procedure
- tree growing
- tree splitting
- viterbi
- viterbi search
- word recognition
Other assigned terms:
- 109-speaker training set
- acoustic model
- approach
- benchmark
- case
- classification problem
- codebook
- context dependency
- contextual information
- continuous-speech
- distance metric
- distribution
- duration
- duration model
- error rate
- fact
- feature
- hypotheses
- intention
- language model
- language model score
- leaf
- lexical representation
- lexicon
- linear combination
- local constraints
- local context
- meaning
- measure
- mechanisms
- natural language
- nist
- noise
- optimization criterion
- optimization problem
- perplexity
- probabilities
- probability
- probability distributions
- procedure
- pronunciation
- reordering
- representations
- resource management task
- search strategy
- segments
- sentence
- signal
- speaker-independent test set
- speech signal
- statistics
- stress
- telephone network
- test set
- text
- training
- training data
- training samples
- training set
- transformation
- transformation rules
- tree
- trees
- utterance
- vowel
- word
- word boundary
- word error rate
- word sequence
- word sequences
- word strings
- word-pair language model
- words
