Spontaneous speech synthesis with linguistic-speech consistency training using pseudo-filled pauses.
Yuta MatsunagaTakaaki SaekiShinnosuke TakamichiHiroshi SaruwatariPublished in: CoRR (2022)
Keyphrases
- n gram
- spontaneous speech
- linguistic features
- human machine interaction
- spoken language
- text classification
- automatic speech recognition
- speech signal
- prosodic features
- spoken document retrieval
- conversational speech
- automatic transcription
- speech recognition
- speech synthesis
- training set
- natural language
- focus of attention
- text to speech
- dialogue system
- language processing
- natural language processing