GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints.
Ji-Hoon KimSang-Hoon LeeJi-Hyun LeeHonggyu JungSeong-Whan LeePublished in: SMC (2021)
Keyphrases
- geometric constraints
- speaker adaptation
- speech recognition
- text to speech
- maximum likelihood
- speech synthesis
- automatic speech recognition
- vocal tract
- video sequences
- camera calibration
- video shots
- speech recognizer
- geometric consistency
- epipolar geometry
- key frames
- hidden markov models
- multiple images
- speaker independent
- video content
- video data
- visual features
- pattern recognition
- news video
- low level
- viewpoint
- multiscale
- speech signal
- feature selection
- language model
- image features