Finding word boundaries in Indian English-accented speech.
Kara HawthorneJuhani JärvikiviBenjamin V. TuckerPublished in: J. Phonetics (2018)
Keyphrases
- english text
- text to speech
- spoken language
- speech recognizer
- speech recognition
- broadcast news
- word level
- automatic transcription
- prosodic features
- co occurrence
- spoken document retrieval
- english words
- spontaneous speech
- unknown words
- speech recognition systems
- compound words
- natural language
- n gram
- statistical machine translation
- speech synthesis
- automatic speech recognition
- computing semantic relatedness
- named entity recognizer
- language specific
- lexical information
- word error rate
- dialogue system
- information retrieval
- spoken documents
- natural language processing
- recognition errors
- cross language
- bilingual dictionaries
- stop words
- word sense
- word pairs
- parallel corpus
- training corpus
- language identification