Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS 2007" for the Blizzard Challenge 2007.
Junichi YamagishiTakashi NoseHeiga ZenTomoki TodaKeiichi TokudaPublished in: ICASSP (2008)
Keyphrases
- speech synthesis
- speech recognition
- speaker independent
- hidden markov models
- speaker dependent
- speech recognizer
- vocal tract
- speaker identification
- speech recognition systems
- automatic speech recognition
- language model
- prosodic features
- speech signal
- speaker adaptation
- pattern recognition
- noisy environments
- machine learning
- maximum likelihood
- text to speech
- multi modal
- acoustic models