An embedded English synthesis approach based on speech concatenation and smoothing.
Gui-Lin ChenDong-Jian YueYi-Qing ZuZhen-Li YuPublished in: ISCSLP (2004)
Keyphrases
- text to speech
- broadcast news
- english text
- spoken language
- natural language
- english language
- program synthesis
- speech recognition
- machine translation
- speech synthesis
- speech recognition technology
- facial animation
- automatic speech recognition systems
- automatic transcription
- smoothing algorithm
- automatic speech recognition
- speech signal
- cross language information retrieval
- preprocessing step
- cross language
- cross lingual
- regular expressions
- target language
- video search
- language acquisition
- watermarking algorithm
- embedded systems
- spontaneous speech
- language learning
- language model
- machine learning