Visual Speech Recognition (VSR) aims to predict spoken content by analyzing lip movements in videos. Recently reported state-of-the-art results in VSR often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are insufficient compared to the audio data. To further enhance the VSR model using the audio data, we employed a generative model for data inflation, integrating the synthetic data with the authentic visual data. Essentially, the generative model incorporates another insight, which enhances the capabilities of the recognition model. For the cross-language issue, previous work has shown poor performance with non-Indo-European languages. We trained a multi-language-family modal fusion model, AudioVSR. Leveraging the concept of modal transfer, we achieved significant results in downstream VSR tasks under conditions of data scarcity. To the best of our knowledge, AudioVSR represents the first work on cross-language-family audio-lip alignment, achieving a new SOTA in the cross-language scenario.

A song is a combination of singing voice and accompaniment. However, existing works focus on singing voice synthesis and music generation independently. Little attention was paid to exploring song synthesis. In this work, we propose a novel task called Text-to-Song synthesis which incorporates both vocal and accompaniment generation. We develop Melodist, a two-stage text-to-song method that consists of singing voice synthesis (SVS) and vocal-to-accompaniment (V2A) synthesis. Melodist leverages tri-tower contrastive pretraining to learn more effective text representation for controllable V2A synthesis. A Chinese song dataset mined from a music website is built to alleviate data scarcity for our research. The evaluation results on our dataset demonstrate that Melodist can synthesize songs with comparable quality and style consistency. Audio samples can be found in https://text2songMelodist.github.io/Sample/.

Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA). The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at different levels of abstraction. Existing efforts mainly focus on designing sophisticated architectures while utilizing frame- or object-level visual representations. In this paper, we reconsider the multi-modal alignment problem in VideoQA from feature and sample perspectives to achieve better performance. From the view of feature, we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities. Moreover, we adopt a heterogeneous graph architecture and design a hierarchical framework to align both trajectory-level and frame-level visual feature with language feature. In addition, we found that VideoQA models are largely dependent on languagepriors and always neglect visual-language interactions. Thus, two effective yet portable training augmentation strategies are designed to strengthen the cross-modal correspondence ability of our model from the view of sample. Extensive results show that our method outperforms all the state-of the-art models on the challenging NExT-QA benchmark.