ACL RD-TEC 1.0 Summarization of N04-2001
Paper Title:
MULTILINGUAL SPEECH RECOGNITION FOR INFORMATION RETRIEVAL IN INDIAN CONTEXT
MULTILINGUAL SPEECH RECOGNITION FOR INFORMATION RETRIEVAL IN INDIAN CONTEXT
Authors: N. Udhaykumar and S.K. Ramakrishnan and R. Swaminathan
Primarily assigned technology terms:
- acoustic model combination
- acoustic modeling
- adaptive signal processing
- automatic language identification
- automatic pronunciation
- automatic rule generation
- automatic speech recognition
- baum-welch training
- bootstrapping
- classification
- crosslingual bootstrapping
- data collection
- data sharing
- data-driven approach
- database
- databases
- decision tree
- decision trees
- decoding
- dictionary lookup
- environment adaptation
- expert system
- finite state
- finite state transducers
- hmms
- identification
- information retrieval
- information retrieval system
- information retrieval systems
- language identification
- language modeling
- language understanding
- length normalization
- lexical adaptation
- lexical modeling
- linear regression
- lvcsr
- machine-learning
- maximum likelihood
- model interpolation
- modeling
- modeling technique
- multilingual speech recognition
- normalization
- one-to-one mapping
- parameter reduction
- processing
- pronunciation modeling
- pruning
- recognition
- recognition framework
- recognition system
- recognizer
- regression
- regression trees
- retrieval system
- retrieval systems
- rule generation
- rule-based system
- signal processing
- speaker adaptation
- speech recognition
- speech recognition framework
- speech recognizer
- speech synthesis
- speech-tospeech translation
- spoken language systems
- spoken language understanding
- state tying
- statistical methods
- statistical modeling
- synthesis
- transcription
- transducers
Other assigned terms:
- acoustic model
- acoustic models
- acronym
- alphabet
- american english
- approach
- background noise
- bigram
- case
- clusters
- continuous speech
- conversation
- density function
- dictionary
- disk
- english corpus
- entropy
- estimation
- fact
- generation
- grapheme
- heuristic
- hindi
- interpolation
- ipa mapping
- knowledge
- language data
- language database
- language information
- language models
- large training
- lexicon
- likelihood
- linguistic
- linguistic knowledge
- linguists
- mapping
- mappings
- maps
- measure
- memory space
- method
- model combination
- model parameters
- multilingual speech
- n-best list
- names
- network timit corpus
- noise
- ogi multilanguage telephone speech
- ogi multilanguage telephone speech corpus
- orthography
- out-of-vocabulary word
- parameter values
- pauses
- phoneme
- phonemes
- phonemic transcription
- phonetic association
- phonological rules
- probability
- probability density
- probability density function
- process
- pronunciation
- proper names
- recognition accuracy
- relation
- representations
- seed
- sentences
- set membership
- signal
- speaking rate
- speech corpus
- speech data
- speech database
- spoken language
- system performance
- target language
- technique
- terms
- test data
- text
- timit corpus
- timit database
- training
- training and test data
- training data
- tree
- trees
- triphone
- understanding
- user
- vocabulary
- vocal tract
- word
- word error rates
- words
