Speech inpainting: Context-based speech synthesis guided by video.
Juan Felipe MontesinosDaniel MichelsantiGloria HaroZheng-Hua TanJesper JensenPublished in: INTERSPEECH (2023)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- vocal tract
- prosodic features
- speech corpus
- video data
- video streams
- video frames
- multimedia
- video content
- video processing
- video sequences
- real time
- video database
- automatic speech recognition
- speech signal
- video analysis
- video stabilization
- video retrieval
- video clips
- video surveillance
- language model
- multimedia data
- space time
- resolution enhancement
- context sensitive
- digital video
- key frames
- image restoration
- hidden markov models
- bayesian networks
- information retrieval