ACL RD-TEC 1.0 Summarization of J01-3002
Paper Title:
A STATISTICAL MODEL FOR WORD DISCOVERY IN TRANSCRIBED SPEECH
A STATISTICAL MODEL FOR WORD DISCOVERY IN TRANSCRIBED SPEECH
Primarily assigned technology terms:
- algorithm
- approximation
- c + +
- computational linguistics
- computing
- dynamic programming
- dynamic programming algorithm
- dynamic programming method
- grouping
- identification
- illustration
- incremental algorithm
- language acquisition
- learner
- learning
- learning algorithm
- likelihood approach
- maximum likelihood
- maximum likelihood approach
- normalization
- optimization
- optimization algorithm
- parsing
- programming algorithm
- programming method
- scoring
- search
- segmentation
- supervised learning
- text segmentation
- unsupervised learning
- unsupervised learning algorithm
- viterbi
- viterbi search
- word discovery
Other assigned terms:
- approach
- association for computational linguistics
- bigram
- case
- characters
- child language acquisition
- child-directed speech
- cognitive
- cognitive perspective
- computational complexity
- continuous speech
- data corpus
- distribution
- english speech
- events
- fact
- heuristic
- implementation
- incremental approach
- kanji
- knowledge
- language model
- language models
- large corpus
- lexicon
- likelihood
- linear time
- linguistics
- method
- minimum description length
- n-gram
- n-grams
- noise
- permutation
- phoneme
- phonemes
- phonemic representation
- precision
- probabilities
- probability
- procedure
- pronunciation
- recursion
- relative frequency
- running time
- speech corpus
- statistical model
- statistics
- stress
- switchboard telephone speech
- syllables
- technique
- text
- theory
- training
- training data
- transcribed speech
- transcripts
- transitional probability
- trigram
- uniform distribution
- unigram
- unigram language model
- unigram model
- utterance
- vocabulary
- word
- word boundaries
- word boundary
- word sequence
- words
