Sungwoo Cho

Sungnyun Kim, Sungwoo Cho, Sangmin Bae et al.

Audio-visual speech recognition (AVSR) incorporates auditory and visual modalities to improve recognition accuracy, particularly in noisy environments where audio-only speech systems are insufficient. While previous research has largely addressed audio disruptions, few studies have dealt with visual corruptions, e.g., lip occlusions or blurred videos, which are also detrimental. To address this real-world challenge, we propose CAV2vec, a novel self-supervised speech representation learning framework particularly designed to handle audio-visual joint corruption. CAV2vec employs a self-distillation approach with a corrupted prediction task, where the student model learns to predict clean targets, generated by the teacher model, with corrupted input frames. Specifically, we suggest a unimodal multi-task learning, which distills cross-modal knowledge and aligns the corrupted modalities, by predicting clean audio targets with corrupted videos, and clean video targets with corrupted audios. This strategy mitigates the dispersion in the representation space caused by corrupted modalities, leading to more reliable and robust audio-visual fusion. Our experiments on robust AVSR benchmarks demonstrate that the corrupted representation learning method significantly enhances recognition accuracy across generalized environments involving various types of corruption. Our code is available at https://github.com/sungnyun/cav2vec.

Beomsoo Kim, Changho Choi, Dohyun Kim et al.

We present Raon-Speech, a top-performing 9B-parameter speech language model (SpeechLM) for English and Korean speech understanding, answering, and generation, and Raon-SpeechChat, a high-performing full-duplex extension for natural real-time conversation. Raon-Speech successfully transforms a pre-trained LLM into a SpeechLM that both understands and generates speech while preserving strong text capabilities. It trains on 1.38M hours of highly curated English and Korean speech and text datasets with the following training stages: (1) speech modules alignment, (2) end-to-end SpeechLM pre-training with knowledge distillation, and (3) multi-task preference optimization-based post-training. Across 42 English and Korean speech and text benchmarks, Raon-Speech establishes the strongest overall profile on speech-centric tasks in our comparison against eight similarly sized recent audio foundation models, including Qwen2.5-Omni and Fun-Audio-Chat, while preserving strong text question answering performance. Building upon it, Raon-SpeechChat enables natural full-duplex conversation by continual training on 119K hours of time-aligned real and synthetic dialogue data. It proceeds through three complementary training stages: (1) causal encoder adaptation, (2) full-duplex pre-training, (3) full-duplex fine-tuning for voice and role-control. On multiple full-duplex benchmarks, Raon-SpeechChat shows its clearest strengths on the turn-taking and interruption-sensitive behaviors covered by FDB v1.0, and remains competitive across the broader full-duplex evaluation suite. We open-source all model checkpoints, the training and inference pipeline, and an interactive demo.

Sungnyun Kim, Kangwook Jang, Sungwoo Cho et al.

This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR) that reasons over modality-specific evidences directly in the language space. Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models. To maximize the effectiveness of DualHyp, we further introduce RelPrompt, a noise-aware guidance mechanism that provides modality-grounded prompts to the LLM. RelPrompt offers the temporal reliability of each modality stream, guiding the model to dynamically switch its focus between ASR and VSR hypotheses for an accurate correction. Under various corruption scenarios, our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain. To facilitate research within our DualHyp framework, we release the code and the dataset comprising ASR and VSR hypotheses at https://github.com/sungnyun/dualhyp.

Sungwoo Cho, Jeongsoo Choi, Sungnyun Kim et al.

Despite recent advances in text-to-speech (TTS) models, audio-visual-to-audio-visual (AV2AV) translation still faces a critical challenge: maintaining speaker consistency between the original and translated vocal and facial features. To address this issue, we propose a conditional flow matching (CFM) zero-shot audio-visual renderer that utilizes strong dual guidance from both audio and visual modalities. By leveraging multimodal guidance with CFM, our model robustly preserves speaker-specific characteristics and enhances zero-shot AV2AV translation abilities. For the audio modality, we enhance the CFM process by integrating robust speaker embeddings with x-vectors, which serve to bolster speaker consistency. Additionally, we convey emotional nuances to the face rendering module. The guidance provided by both audio and visual cues remains independent of semantic or linguistic content, allowing our renderer to effectively handle zero-shot translation tasks for monolingual speakers in different languages. We empirically demonstrate that the inclusion of high-quality mel-spectrograms conditioned on facial information not only enhances the quality of the synthesized speech but also positively influences facial generation, leading to overall performance improvements in LSE and FID score. Our code is available at https://github.com/Peter-SungwooCho/MAVFlow.

Jihyeon Seo, Kyusam Oh, Chanho Min et al.

Many existing studies on knowledge distillation have focused on methods in which a student model mimics a teacher model well. Simply imitating the teacher's knowledge, however, is not sufficient for the student to surpass that of the teacher. We explore a method to harness the knowledge of other students to complement the knowledge of the teacher. We propose deep collective knowledge distillation for model compression, called DCKD, which is a method for training student models with rich information to acquire knowledge from not only their teacher model but also other student models. The knowledge collected from several student models consists of a wealth of information about the correlation between classes. Our DCKD considers how to increase the correlation knowledge of classes during training. Our novel method enables us to create better performing student models for collecting knowledge. This simple yet powerful method achieves state-of-the-art performances in many experiments. For example, for ImageNet, ResNet18 trained with DCKD achieves 72.27\%, which outperforms the pretrained ResNet18 by 2.52\%. For CIFAR-100, the student model of ShuffleNetV1 with DCKD achieves 6.55\% higher top-1 accuracy than the pretrained ShuffleNetV1.

Sungnyun Kim, Kangwook Jang, Sangmin Bae et al.

Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, existing AVSR systems struggle to scale up without compromising computational efficiency. In this study, we introduce MoHAVE (Mixture of Hierarchical Audio-Visual Experts), a novel robust AVSR framework designed to address these scalability constraints. By leveraging a Mixture-of-Experts (MoE) architecture, MoHAVE activates modality-specific expert groups, ensuring dynamic adaptation to various audio-visual inputs with minimal computational overhead. Key contributions of MoHAVE include: (1) a sparse MoE framework that efficiently scales AVSR model capacity, (2) a hierarchical gating mechanism that dynamically utilizes the expert groups based on input context, enhancing adaptability and robustness, and (3) remarkable performance across robust AVSR benchmarks, including LRS3 and MuAViC transcription and translation tasks, setting a new standard for scalable speech recognition systems.

Jongwoo Ko, Sungnyun Kim, Sungwoo Cho et al.

Human-generated reward signals are critical for aligning generative models with human preferences, guiding both training and inference-time evaluations. While large language models (LLMs) employed as proxy evaluators, i.e., LLM-as-a-Judge, significantly reduce the costs associated with manual annotations, they typically require extensive modality-specific training data and fail to generalize well across diverse multimodal tasks. In this paper, we propose Flex-Judge, a reasoning-guided multimodal judge model that leverages minimal textual reasoning data to robustly generalize across multiple modalities and evaluation formats. Our core intuition is that structured textual reasoning explanations inherently encode generalizable decision-making patterns, enabling an effective transfer to multimodal judgments, e.g., with images or videos. Empirical results demonstrate that Flex-Judge, despite being trained on significantly fewer text data, achieves competitive or superior performance compared to state-of-the-art commercial APIs and extensively trained multimodal evaluators. Notably, Flex-Judge presents broad impact in modalities like molecule, where comprehensive evaluation benchmarks are scarce, underscoring its practical value in resource-constrained domains. Our framework highlights reasoning-based text supervision as a powerful, cost-effective alternative to traditional annotation-intensive approaches, substantially advancing scalable multimodal model-as-a-judge.

Seongyoon Kim, Minchan Jeong, Sungnyun Kim et al.

Federated Learning (FL) has emerged as a pivotal framework for the development of effective global models (global FL) or personalized models (personalized FL) across clients with heterogeneous, non-iid data distribution. A key challenge in FL is client drift, where data heterogeneity impedes the aggregation of scattered knowledge. Recent studies have tackled the client drift issue by identifying significant divergence in the last classifier layer. To mitigate this divergence, strategies such as freezing the classifier weights and aligning the feature extractor accordingly have proven effective. Although the local alignment between classifier and feature extractor has been studied as a crucial factor in FL, we observe that it may lead the model to overemphasize the observed classes within each client. Thus, our objectives are twofold: (1) enhancing local alignment while (2) preserving the representation of unseen class samples. This approach aims to effectively integrate knowledge from individual clients, thereby improving performance for both global and personalized FL. To achieve this, we introduce a novel algorithm named FedDr+, which empowers local model alignment using dot-regression loss. FedDr+ freezes the classifier as a simplex ETF to align the features and improves aggregated global models by employing a feature distillation mechanism to retain information about unseen/missing classes. Consequently, we provide empirical evidence demonstrating that our algorithm surpasses existing methods that use a frozen classifier to boost alignment across the diverse distribution.

Ahnjae Shin, Dong-Jin Shin, Sungwoo Cho et al.

As deep learning techniques advance more than ever, hyper-parameter optimization is the new major workload in deep learning clusters. Although hyper-parameter optimization is crucial in training deep learning models for high model performance, effectively executing such a computation-heavy workload still remains a challenge. We observe that numerous trials issued from existing hyper-parameter optimization algorithms share common hyper-parameter sequence prefixes, which implies that there are redundant computations from training the same hyper-parameter sequence multiple times. We propose a stage-based execution strategy for efficient execution of hyper-parameter optimization algorithms. Our strategy removes redundancy in the training process by splitting the hyper-parameter sequences of trials into homogeneous stages, and generating a tree of stages by merging the common prefixes. Our preliminary experiment results show that applying stage-based execution to hyper-parameter optimization algorithms outperforms the original trial-based method, saving required GPU-hours and end-to-end training time by up to 6.60 times and 4.13 times, respectively.

Eunji Jeong, Sungwoo Cho, Gyeong-In Yu et al.

The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the requirement of quickly executing large computations, but also to support straightforward programming models for quickly implementing and experimenting with complex network structures. However, existing frameworks fail to excel in both departments simultaneously, leading to diverged efforts for optimizing performance and improving usability. This paper presents JANUS, a system that combines the advantages from both sides by transparently converting an imperative DL program written in Python, the de-facto scripting language for DL, into an efficiently executable symbolic dataflow graph. JANUS can convert various dynamic features of Python, including dynamic control flow, dynamic types, and impure functions, into elements of a symbolic dataflow graph. Experiments demonstrate that JANUS can achieve fast DL training by exploiting the techniques imposed by symbolic graph-based DL frameworks, while maintaining the simple and flexible programmability of imperative DL frameworks at the same time.