Acoustic model-based subword tokenization and prosodic-context extraction without language knowledge for text-to-speech synthesis.
Masashi AsoShinnosuke TakamichiNorihiro TakamuneHiroshi SaruwatariPublished in: Speech Commun. (2020)
Keyphrases
- text to speech synthesis
- text to speech
- knowledge extraction
- domain knowledge
- knowledge representation
- knowledge acquisition
- contextual information
- information extraction
- knowledge based systems
- knowledge base
- hidden markov models
- conceptual model
- knowledge retrieval
- prosodic features
- explicit knowledge
- global knowledge
- n gram
- context dependent
- conceptual framework
- user model
- context aware
- prior knowledge
- expert systems