ACL RD-TEC 1.0 Summarization of W99-0402

Paper Title:
ELICITING NATURAL SPEECH FROM NON-NATIVE USERS: COLLECTING SPEECH DATA FOR LVCSR

Authors: Laura Mayfield Tomokiyo and Susanne Burger

Other assigned terms:

  • approach
  • bigram
  • case
  • cognitive
  • community
  • comprehension
  • conversational speech
  • corpora
  • corpus size
  • data set
  • dialogues
  • english sentence
  • fact
  • feature
  • french
  • grammar
  • hypothesis
  • language model
  • language models
  • language use
  • lexical choice
  • linguistic
  • meaning
  • method
  • methodology
  • names
  • native speech
  • natural speech
  • noise
  • non-native speech
  • nouns
  • number agreement
  • perplexity
  • phrase
  • predictive power
  • pronunciation
  • qualitative analysis
  • queries
  • query
  • sentence
  • sentence level
  • sentences
  • signal
  • singular noun
  • speech data
  • speech recognition performance
  • spontanous speech
  • statistical language model
  • style
  • syntax
  • target language
  • technique
  • term
  • terms
  • test corpora
  • text
  • tokens
  • training
  • training data
  • transcript
  • translation task
  • trigram
  • tutoring
  • understanding
  • user
  • utterance
  • vocabulary
  • vocabulary growth
  • vocabulary size
  • word
  • word choice
  • words
  • writing system

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***