Adapting the acoustic model of a speech recognizer for varied proficiency non-native spontaneous speech using read speech with language-specific pronunciation difficulty.
Klaus ZechnerDerrick HigginsRené LawlessYoko FutagiSarah OhlsGeorge IvanovPublished in: INTERSPEECH (2009)
Keyphrases
- spontaneous speech
- speech recognizer
- spoken language
- out of vocabulary
- spoken document retrieval
- broadcast news
- automatic speech recognition
- speech recognition
- dialogue system
- language processing
- word segmentation
- semantic analysis
- language model
- n gram
- language independent
- cross language information retrieval
- machine translation
- named entity recognition
- natural language
- linguistic knowledge
- query terms
- natural language processing
- labor intensive