ACL RD-TEC 1.0 Summarization of P98-2237
Paper Title:
USING CHUNK BASED PARTIAL PARSING OF SPONTANEOUS SPEECH IN UNRESTRICTED DOMAINS FOR REDUCING WORD ERROR RATE IN SPEECH RECOGNITION
USING CHUNK BASED PARTIAL PARSING OF SPONTANEOUS SPEECH IN UNRESTRICTED DOMAINS FOR REDUCING WORD ERROR RATE IN SPEECH RECOGNITION
Authors: Klaus Zechner and Alex Waibel
Primarily assigned technology terms:
- adaptive training
- chunk parser
- chunk parsing
- chunking
- cutoff
- frame parsing
- janus speech recognizer
- length normalization
- list reranking
- lvcsr
- modeling
- neural net
- neural network
- normalization
- parser
- parsing
- parsing speech
- parsing system
- partial parsing
- pos tagger
- predictor
- preprocessing
- ranking
- reading
- recognition
- recognizer
- reranking
- rescoring
- score calculation
- search
- segmentation
- speech recognition
- speech recognizer
- speech tagger
- subcategorization
- system training
- tagger
- taggers
- tagging
Other assigned terms:
- acoustic models
- ambiguity
- approach
- argument structure
- brown corpus
- case
- chunk
- chunk representation
- chunks
- concepts
- conversational speech
- corpora
- data set
- data sets
- error rate
- evaluations
- fact
- frame
- grammar
- head noun
- heuristics
- hypotheses
- hypothesis
- knowledge
- language model
- language models
- lattice
- lattices
- likelihood
- linguistic
- meaning
- n-gram
- n-gram model
- natural language
- noise
- oracle
- part of speech
- phrase
- pos sequence
- procedure
- process
- random order
- representations
- runtime
- segment boundaries
- selectional restrictions
- semantic
- semantic frame
- sentence
- silence
- spoken language
- statistics
- subcategorization frames
- switchboard corpus
- syntactic constituents
- syntax
- system architecture
- system evaluation
- system performance
- tags
- tagset
- terms
- test set
- tokens
- training
- training data
- training set
- utterance
- verb
- word
- word error rate
- word error rates
- word sequences
- words
- written corpora
