6 papers
Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space
Thanh V. T. Tran, Ngoc-Son Nguyen, Luong Tran +4
The paper introduces Flowley, an end‑to‑end model that generates synchronized audio directly from silent video using a novel progressive soft‑masked cross‑attention mechanism, and…
DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching
Ngoc-Son Nguyen, Thanh V. T. Tran, Hieu-Nghia Huynh-Nguyen +2
Zero-shot text-to-speech (TTS) has made significant progress in replicating unseen voices, yet balancing generation quality and inference efficiency remains challenging. Autoregres…
DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction
Cuong Tran Van, Trong-Thang Pham, Ngoc-Son Nguyen +2
Sparse-view Cone-Beam Computed Tomography reconstruction from limited X-ray projections remains a challenging problem in medical imaging due to the inherent undersampling of fine-g…
DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi +3
Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To addres…
Flamed-TTS: Flow Matching Attention-Free Models for Efficient Generating and Dynamic Pacing Zero-shot Text-to-Speech
Hieu-Nghia Huynh-Nguyen, Huynh Nguyen Dang, Ngoc-Son Nguyen +1
Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voic…
OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching
Hieu-Nghia Huynh-Nguyen, Ngoc Son Nguyen, Huynh Nguyen Dang +3
Text-to-speech (TTS) systems have seen significant advancements in recent years, driven by improvements in deep learning and neural network architectures. Viewing the output speech…