Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis.
John DinesHui LiangLakshmi SaheerMatthew GibsonWilliam ByrneKeiichiro OuraKeiichi TokudaJunichi YamagishiSimon KingMirjam WesterTeemu HirsimäkiReima KarhilaMikko KurimoPublished in: Comput. Speech Lang. (2013)
Keyphrases
- speech synthesis
- speech recognition
- cross lingual
- speaker adaptation
- vocal tract
- hidden markov models
- text to speech
- machine translation
- language model
- speech recognizer
- language modeling
- cross lingual information retrieval
- speaker independent
- automatic speech recognition
- speech signal
- translation model
- cross language
- pattern recognition
- speech recognition systems
- speaker identification
- parallel corpora
- parallel corpus
- machine translation system
- statistical machine translation
- noisy environments
- query translation
- semi supervised
- news articles
- language independent
- language processing
- machine learning
- image acquisition
- unsupervised learning
- text classification