Non-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics.
Yuji OshimaShinnosuke TakamichiTomoki TodaGraham NeubigSakriani SaktiSatoshi NakamuraPublished in: INTERSPEECH (2015)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- automatic speech recognition
- hidden markov models
- pattern recognition
- speech signal
- text to speech
- noisy environments
- speaker independent
- speech recognizer
- speaker identification
- language model
- acoustic models
- speaker adaptation
- speech corpus
- speech sounds
- error correction
- video sequences
- data sets