Adapting machine translation models toward misrecognized speech with text-to-speech pronunciation rules and acoustic confusability.
Nicholas RuizQin GaoWilliam LewisMarcello FedericoPublished in: INTERSPEECH (2015)
Keyphrases
- machine translation
- text to speech
- speech recognition
- speech synthesis
- acoustic models
- prosodic features
- finite state transducers
- information extraction
- statistical translation models
- text to speech synthesis
- word sense disambiguation
- language independent
- speaker independent
- cross lingual
- hidden markov models
- natural language processing
- statistical machine translation
- statistical models
- word alignment
- automatic speech recognition
- speech recognition systems
- spontaneous speech
- cross language information retrieval
- natural language generation
- query translation
- language resources
- word processing
- machine translation system