5 papers
SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation
Haoyu Zhang, Yuta Oshima, Xingjian Du +4
Video-to-audio (V2A) generation must jointly satisfy audiovisual alignment, semantic consistency, temporal synchronization, and perceptual quality. While prior work has mainly focu…
Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech
Dong Yang, Yiyi Cai, Haoyu Zhang +2
Metric-induced discrete flow matching (MI-DFM) exploits token-latent geometry for discrete generation, but its practical use is limited by two issues: heuristic schedulers requirin…
AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Haoyu Zhang, Jiaxian Guo, Dong Yang +2
Large Audio Language Models (LALMs) exhibit strong capabilities in general audio understanding but remain static after deployment, limiting their adaptability to real-world data. S…
GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech
Yahuan Cong, Haoyu Zhang, Haopeng Lin +5
Cross-lingual timbre and style generalizable text-to-speech (TTS) aims to synthesize speech with a specific reference timbre or style that is never trained in the target language.…
LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversion
Chunfeng Wang, Peisong Huang, Yuxiang Zou +4
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their correspo…