A Unified Approach in Speech-to-Speech Translation: Integrating Features of Speech recognition and Machine Translation.
Ruiqiang ZhangGen-ichiro KikuiHirofumi YamamotoFrank K. SoongTaro WatanabeWai Kit LoPublished in: COLING (2004)
Keyphrases
- speech recognition
- machine translation
- speech recognition systems
- speech synthesis
- speech signal
- automatic speech recognition
- statistical machine translation
- speech recognizer
- language model
- cross language information retrieval
- target language
- cepstral coefficients
- speech processing
- hidden markov models
- natural language processing
- language independent
- language resources
- information extraction
- pattern recognition
- word alignment
- speech recognition technology
- machine translation system
- cross lingual
- noisy environments
- language processing
- speaker identification
- handwriting recognition
- parallel corpora
- mel frequency cepstral coefficients
- feature extraction
- speaker independent
- speaker dependent
- source language
- acoustic models
- language modeling
- natural language
- artificial intelligence
- isolated word
- word level
- natural language generation
- query translation
- feature vectors
- speaker recognition
- finite state transducers
- speaker adaptation
- feature set
- co occurrence
- bayesian networks