Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding.
Seungwoo ChoiSeungju HanDongyoung KimSungjoo HaPublished in: INTERSPEECH (2020)
Keyphrases
- variable length
- text to speech
- fixed length
- speech synthesis
- programming tool
- n gram
- bitstream
- text to speech synthesis
- statistical dependencies
- text compression
- prosodic features
- video content
- visual attention
- word processing
- video data
- video sequences
- run length encoding
- data hiding
- machine learning
- multiresolution
- information retrieval