AdaptiveFormer: A Few-shot Speaker Adaptive Speech Synthesis Model based on FastSpeech2.
Dengfeng KeRuixin HuQi LuoLiangjie HuangWenhan YaoWentao ShuJinsong ZhangYanlu XiePublished in: ISCSLP (2022)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- automatic speech recognition
- video sequences
- data driven
- hidden markov models
- language model
- computer vision
- noise reduction
- speaker verification
- speaker recognition
- speech signal
- speech corpus
- noisy environments
- video shots
- key frames
- pattern recognition
- image processing