ACL RD-TEC 1.0 Summarization of A97-1009
Paper Title:
NAME PRONUNCIATION IN GERMAN TEXT-TO-SPEECH SYNTHESIS
NAME PRONUNCIATION IN GERMAN TEXT-TO-SPEECH SYNTHESIS
Authors: Stefanie Jannedy and Bernd Mobius
Primarily assigned technology terms:
- algorithm
- cd-rom
- data retrieval
- database
- databases
- decomposition
- editing
- error analysis
- final state
- finite-state transducer
- frequency analysis
- fsm technology
- grapheme-to-phoneme conversion
- internet
- linguistic analysis
- listing
- morphological analysis
- morphological decomposition
- morphology
- multilingual text-to-speech system
- name analysis
- name detection
- name formation
- name tagging
- navigation
- neural networks
- pronunciation component
- reasoning
- recognition
- spelling
- stress assignment
- synthesis
- tagging
- text analysis
- text-to-speech
- text-to-speech synthesis
- text-to-speech system
- transcription
- transducer
- tts system
- weighted finite-state transducer
- word analysis
Other assigned terms:
- analogy
- analysis grammar
- annotated corpora
- approach
- community
- compounds
- corpora
- data set
- derivation
- dictionaries
- dictionary
- distribution
- empty string
- error rate
- feature
- feature space
- feature vectors
- finite-state grammar
- frequency distribution
- general-purpose lexicon
- grammar
- grapheme
- heuristics
- implementation
- infixation
- input text
- large corpora
- lexical information
- lexical items
- lexical stress
- lexicon
- linguistic
- linguistic data
- linguistic intuition
- method
- morph
- morpheme
- morpheme boundary
- morphemes
- morphological information
- morphological structure
- name pronunciation
- names
- part-of-speech
- part-of-speech information
- personal names
- probabilities
- procedure
- process
- pronunciation
- pronunciation dictionary
- proper name
- proper names
- rule set
- rule sets
- segmental structure
- stress
- sub-grammar
- substring
- suffix
- suffixes
- syllables
- symbol
- symbols
- technology
- test data
- test data set
- test material
- test set
- text
- tokens
- toolkit
- topics
- training
- training corpus
- training data
- training material
- training set
- transcriptions
- vowel
- well-formed text
- word
- word boundary
- word form
- word formation
- word model
- word types
- words
