Thanh V. T. Tran

Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video dubbing framework built upon a discrete flow matching backbone with a novel two-stage training strategy. In the first stage, a zero-shot text-to-speech (TTS) system is pre-trained on large-scale corpora, where a deterministic architecture captures linguistic structures, and the Discrete Flow-based Prosody-Acoustic (DFPA) module models expressive prosody and realistic acoustic characteristics. In the second stage, we propose the Content-Consistent Temporal Adaptation (CCTA) to transfer TTS knowledge to the dubbing domain: its Synchronizer enforces cross-modal alignment for lip-synchronized speech. Complementarily, the Face-to-Prosody Mapper (FaPro) conditions prosody on facial expressions, whose outputs are then fused with those of the Synchronizer to construct rich, fine-grained multimodal embeddings that capture prosody-content correlations, guiding the DFPA to generate expressive prosody and acoustic tokens for content-consistent speech. Experiments on two benchmark datasets demonstrate that DiFlowDubber outperforms prior methods across multiple evaluation metrics.

Lip-to-speech (L2S) synthesis, which reconstructs speech from visual cues, faces challenges in accuracy and naturalness due to limited supervision in capturing linguistic content, accents, and prosody. In this paper, we propose RESOUND, a novel L2S system that generates intelligible and expressive speech from silent talking face videos. Leveraging source-filter theory, our method involves two components: an acoustic path to predict prosody and a semantic path to extract linguistic features. This separation simplifies learning, allowing independent optimization of each representation. Additionally, we enhance performance by integrating speech units, a proven unsupervised speech representation technique, into waveform generation alongside mel-spectrograms. This allows RESOUND to synthesize prosodic speech while preserving content and speaker identity. Experiments conducted on two standard L2S benchmarks confirm the effectiveness of the proposed method across various metrics.

Emotion Recognition in Conversations (ERC) facilitates a deeper understanding of the emotions conveyed by speakers in each utterance within a conversation. Recently, Graph Neural Networks (GNNs) have demonstrated their strengths in capturing data relationships, particularly in contextual information modeling and multimodal fusion. However, existing methods often struggle to fully capture the complex interactions between multiple modalities and conversational context, limiting their expressiveness. To overcome these limitations, we propose ConxGNN, a novel GNN-based framework designed to capture contextual information in conversations. ConxGNN features two key parallel modules: a multi-scale heterogeneous graph that captures the diverse effects of utterances on emotional changes, and a hypergraph that models the multivariate relationships among modalities and utterances. The outputs from these modules are integrated into a fusion layer, where a cross-modal attention mechanism is applied to produce a contextually enriched representation. Additionally, ConxGNN tackles the challenge of recognizing minority or semantically similar emotion classes by incorporating a re-weighting scheme into the loss functions. Experimental results on the IEMOCAP and MELD benchmark datasets demonstrate the effectiveness of our method, achieving state-of-the-art performance compared to previous baselines.

Latent space optimization (LSO) is a powerful method for designing discrete, high-dimensional biological sequences that maximize expensive black-box functions, such as wet lab experiments. This is accomplished by learning a latent space from available data and using a surrogate model fΦ to guide optimization algorithms toward optimal outputs. However, existing methods struggle when labeled data is limited, as training fΦ with few labeled data points can lead to subpar outputs, offering no advantage over the training data itself. We address this challenge by introducing GROOT, a GRaph-based Latent SmOOThing for Biological Sequence Optimization. In particular, GROOT generates pseudo-labels for neighbors sampled around the training latent embeddings. These pseudo-labels are then refined and smoothed by Label Propagation. Additionally, we theoretically and empirically justify our approach, demonstrate GROOT’s ability to extrapolate to regions beyond the training set while maintaining reliability within an upper bound of their expected distances from the training regions. We evaluate GROOT on various biological sequence design tasks, including protein optimization (GFP and AAV) and three tasks with exact oracles from Design-Bench. The results demonstrate that GROOT equalizes and surpasses existing methods without requiring access to black-box oracles or vast amounts of labeled data, highlighting its practicality and effectiveness.