SpeechAlign: Aligning Speech Generation to Human Preferences.
Dong ZhangZhaowei LiShimin LiXin ZhangPengyu WangYaqian ZhouXipeng QiuPublished in: CoRR (2024)
Keyphrases
- language acquisition
- human communication
- speech recognition
- decision making
- speech signal
- automatic speech recognition
- human centered
- computer vision
- image registration
- audio visual
- soft constraints
- individual preferences
- genetic algorithm
- hand movements
- human language
- speaker recognition
- human interaction
- human subjects
- language model
- image sequences
- artificial intelligence