4 papers
Timed text extraction from Taiwanese Kua-á-hì TV series
Tzu-Hung Huang, Yun-En Tsai, Yun-Ning Hung +3
Taiwanese opera (Kua-á-hì), a major form of local theatrical tradition, underwent extensive television adaptation notably by pioneers like Iûnn Lē-hua. These videos, while potentia…
LargeSHS: A large-scale dataset of music adaptation
Chih-Pin Tan, Hsuan-Kai Kao, Li Su +1
Recent advances in AI-based music generation have focused heavily on text-conditioned models, with less attention given to reference-based generation such as song adaptation. To su…
SynthCloner: Synthesizer-style Audio Transfer via Factorized Codec with ADSR Envelope Control
Jeng-Yue Liu, Ting-Chao Hsu, Yen-Tung Yeh +2
Electronic synthesizer sounds are controlled by parameter settings that yield complex timbral characteristics and ADSR envelopes, making synthesizer-style audio transfer particular…
TextDoctor: Unified Document Image Inpainting via Patch Pyramid Diffusion Models
Wanglong Lu, Lingming Su, Jingjing Zheng +6
Digital versions of real-world text documents often suffer from issues like environmental corrosion of the original document, low-quality scanning, or human interference. Existing…