Login / Signup

Recognition of highly imbalanced code-mixed bilingual speech with frame-level language detection based on blurred posteriorgram.

Ching-feng YehAaron HeidelHung-yi LeeLin-Shan Lee
Published in: ICASSP (2012)
Keyphrases
  • highly imbalanced
  • text to speech
  • class distribution
  • parallel corpus
  • target language
  • object recognition
  • prior knowledge
  • speech recognition
  • data sets
  • feature extraction
  • benchmark datasets
  • machine translation