← Search

Keyu An

2 accepted papers

2026

MELA-TTS: JOINT TRANSFORMER-DIFFUSION MODEL WITH REPRESENTATION ALIGNMENT FOR SPEECH SYNTHESIS

ICASSP 2026poster

This work introduces MELA-TTS, a novel joint transformer-diffusion framework for end-to-end text-to-speech synthesis. By autoregressively generating continuous mel-spectrogram frames from linguistic and speaker conditions, our architecture eliminates the need for speech tokenization and multi-stage…

Cited by 0SourcePDFScholar
2020

Sequential Deformation for Accurate Scene Text Detection

ECCV 2020poster

Scene text detection has been significantly advanced over recent years, especially after the emergence of deep neural network. However, due to high diversity of scene texts in scale, orientation, shape and aspect ratio, as well as the inherent limitation of convolutional neural network for geometric…

Cited by 35SourcePDFScholar