Hyeongseop Rha

Jeong Hun Yeo, Minsu Kim, Hyeongseop Rha et al.

While LLM-based Automatic Speech Recognition (ASR) achieves high accuracy, its speed is limited by sequential autoregressive decoding. Diffusion Language Models (DLMs) offer a parallel alternative, yet their decoding strategies remain under-explored in ASR contexts. This paper analyzes three decoding schemes for DLM-based ASR: fixed-number, static confidence threshold, and dynamic confidence threshold. We propose measuring round-wise accuracy using Negative Log-Likelihood-based uncertainty as a proxy for decoding progress. Our results show that both threshold-based strategies significantly outperform fixed-number schemes in accuracy and speed. We attribute this to a property unique to ASR: most tokens reach high confidence early, allowing reliable ones to be harvested aggressively while leaving only difficult tokens for later rounds. Notably, the static-threshold strategy matches the accuracy of autoregressive decoding while offering superior efficiency.

Jeong Hun Yeo, Chae Won Kim, Hyeongseop Rha et al.

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the best of our knowledge, the first Diffusion Large Language Model (DLLM)-based VSR framework, formulating transcription as iterative masked denoising with flexible-order decoding. With confidence-based unmasking, DLLM-VSR commits high-confidence positions early and uses the committed tokens as bidirectional context to refine ambiguous ones. To adapt DLLMs to VSR, we introduce a two-stage masked-denoising training strategy that separates visual-to-text content alignment from length modeling. We further observe a performance gap with oracle-length decoding, which assumes access to the true transcript length, indicating that reducing target-length uncertainty can improve DLLM-based VSR. To reduce this gap, we develop length-guided candidate decoding, which uses video duration to construct plausible transcript-length hypotheses, decodes under multiple hypotheses, and reranks candidates using length plausibility and decoding confidence. The proposed method achieves a state-of-the-art WER of 19.5\% on LRS3 using only its labeled training data.

Jeong Hun Yeo, Chae Won Kim, Hyunjun Kim et al.

Lip reading aims to predict spoken language by analyzing lip movements. Despite advancements in lip reading technologies, performance degrades when models are applied to unseen speakers due to their sensitivity to variations in visual information such as lip appearances. To address this challenge, speaker adaptive lip reading technologies have advanced by focusing on effectively adapting a lip reading model to target speakers in the visual modality. However, the effectiveness of adapting language information, such as vocabulary choice, of the target speaker has not been explored in previous works. Additionally, existing datasets for speaker adaptation have limited vocabulary sizes and pose variations, which restrict the validation of previous speaker-adaptive methods in real-world scenarios. To address these issues, we propose a novel speaker-adaptive lip reading method that adapts a pre-trained model to target speakers at both vision and language levels. Specifically, we integrate prompt tuning and the LoRA approach, applying them to a pre-trained lip reading model to effectively adapt the model to target speakers. Furthermore, to validate its effectiveness in real-world scenarios, we introduce a new dataset, VoxLRS-SA, derived from VoxCeleb2 and LRS3. It contains a vocabulary of approximately 100K words, offers diverse pose variations, and enables the validation of adaptation methods in the wild, sentence-level lip reading for the first time in English. Through various experiments, we demonstrate that the existing speaker-adaptive method also improves performance in the wild at the sentence level. Moreover, we show that the proposed method achieves larger improvements compared to the previous works.

Hyeongseop Rha, Jeong Hun Yeo, Junil Won et al.

In this paper, we present Modality-Importance-Guided Reasoning (MIGR), a framework designed to improve the reliability of reasoning-based multimodal emotion understanding in multimodal large language models. Although existing methods have advanced emotion understanding, they often suffer from reasoning drift: models gradually rely on their own generated text instead of multimodal evidence, and their explanations are overly shaped by visually initiated reasoning paths. To address these issues, we introduce Modality Importance (MI), a simple yet effective mechanism for identifying the emotion-dominant modality. Using MI, MIGR reorganizes reasoning sequences so that explanations begin from the modality most critical to the target emotion, preventing early reasoning from being misled by less informative cues. Our two-stage framework-comprising modality-aligned supervised fine-tuning and modality-aware reward optimization-encourages models to generate emotionally grounded, causally relevant, and coherence-preserving explanations. Experimental results on the DFEW benchmark show that MIGR substantially improves reasoning reliability, decreasing instances of correct predictions accompanied by emotionally inconsistent explanations from 18.10% to 7.37%. These results confirm the benefit of initiating reasoning from the emotion-dominant modality.

Se Jin Park, Chae Won Kim, Hyeongseop Rha et al.

In this paper, we introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response, marking the initial step towards creating an avatar chatbot system without relying on intermediate text. To this end, we newly introduce MultiDialog, the first large-scale multimodal (i.e., audio and visual) spoken dialogue corpus containing 340 hours of approximately 9,000 dialogues, recorded based on the open domain dialogue dataset, TopicalChat. The MultiDialog contains parallel audio-visual recordings of conversation partners acting according to the given script with emotion annotations, which we expect to open up research opportunities in multimodal synthesis. Our Face-to-Face spoken dialogue model incorporates a textually pretrained large language model and adapts it into the audio-visual spoken dialogue domain by incorporating speech-text joint pretraining. Through extensive experiments, we validate the effectiveness of our model in facilitating a face-to-face conversation. Demo and data are available at https://multidialog.github.io and https://huggingface.co/datasets/IVLLab/MultiDialog, respectively.

Jeong Hun Yeo, Hyeongseop Rha, Se Jin Park et al.

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due to the high temporal resolution of audio-visual speech processed by LLMs. In this work, we introduce an efficient multimodal speech LLM framework that minimizes token length while preserving essential linguistic content. Our approach employs an early AV-fusion module for streamlined feature integration, an audio-visual speech Q-Former that dynamically allocates tokens based on input duration, and a refined query allocation strategy with a speech rate predictor to adjust token allocation according to speaking speed of each audio sample. Extensive experiments on the LRS3 dataset show that our method achieves state-of-the-art performance with a WER of 0.72% while using only 3.5 tokens per second. Moreover, our approach not only reduces token usage by 86% compared to the previous multimodal speech LLM framework, but also improves computational efficiency by reducing FLOPs by 35.7%.

Minsu Kim, Jee-weon Jung, Hyeongseop Rha et al.

The capability to jointly process multi-modal information is becoming an essential task. However, the limited number of paired multi-modal data and the large computational requirements in multi-modal learning hinder the development. We propose a novel Tri-Modal Translation (TMT) model that translates between arbitrary modalities spanning speech, image, and text. We introduce a novel viewpoint, where we interpret different modalities as different languages, and treat multi-modal translation as a well-established machine translation problem. To this end, we tokenize speech and image data into discrete tokens, which provide a unified interface across modalities and significantly decrease the computational cost. In the proposed TMT, a multi-modal encoder-decoder conducts the core translation, whereas modality-specific processing is conducted only within the tokenization and detokenization stages. We evaluate the proposed TMT on all six modality translation tasks. TMT outperforms single model counterparts consistently, demonstrating that unifying tasks is beneficial not only for practicality but also for performance.

Se Jin Park, Yeonju Kim, Hyeongseop Rha et al.

In human communication, both verbal and non-verbal cues play a crucial role in conveying emotions, intentions, and meaning beyond words alone. These non-linguistic information, such as facial expressions, eye contact, voice tone, and pitch, are fundamental elements of effective interactions, enriching conversations by adding emotional and contextual depth. Recognizing the importance of non-linguistic content in communication, we present AV-EmoDialog, a dialogue system designed to exploit verbal and non-verbal information from users' audio-visual inputs to generate more responsive and empathetic interactions. AV-EmoDialog systematically exploits the emotional cues in audio-visual dialogues; extracting speech content and emotional tones from speech, analyzing fine-grained facial expressions from visuals, and integrating these cues to generate emotionally aware responses in an end-to-end manner. Through extensive experiments, we validate that the proposed AV-EmoDialog outperforms existing multimodal LLMs in generating not only emotionally appropriate but also contextually appropriate responses.

Hyeongseop Rha, Jeong Hun Yeo, Yeonju Kim et al.

The recent advancement of Multimodal Large Language Models (MLLMs) is transforming human-computer interaction (HCI) from surface-level exchanges into more nuanced and emotionally intelligent communication. To realize this shift, emotion understanding becomes essential allowing systems to capture subtle cues underlying user intent. Furthermore, providing faithful explanations for predicted emotions is crucial to ensure interpretability and build user trust. However, current MLLM-based methods often generate emotion explanations that diverge from the target labels and sometimes even contradict their own predicted emotions. This inconsistency poses a critical risk for misunderstanding and erodes reliability in interactive settings. To address this, we propose a novel approach: the Emotional Rationale Verifier (ERV) and an Explanation Reward. Our method guides the model to produce reasoning that is explicitly consistent with the target emotion during multimodal emotion recognition without modifying the model architecture or requiring additional paired video-description annotations. Our method significantly improves faithful explanation-prediction consistency and explanation emotion accuracy on the MAFW and DFEW datasets. Through extensive experiments and human evaluations, we show that our approach not only enhances alignment between explanation and prediction but also empowers MLLMs to deliver emotionally coherent, trustworthy interactions, marking a key step toward truly human-like HCI systems.

Jeong Hun Yeo, Hyeongseop Rha, Sungjune Park et al.

Audio is the primary modality for human communication and has driven the success of Automatic Speech Recognition (ASR) technologies. However, such audio-centric systems inherently exclude individuals who are deaf or hard of hearing. Visual alternatives such as sign language and lip reading offer effective substitutes, and recent advances in Sign Language Translation (SLT) and Visual Speech Recognition (VSR) have improved audio-less communication. Yet, these modalities have largely been studied in isolation, and their integration within a unified framework remains underexplored. In this paper, we propose the first unified framework capable of handling diverse combinations of sign language, lip movements, and audio for spoken-language text generation. We focus on three main objectives: (i) designing a unified, modality-agnostic architecture capable of effectively processing heterogeneous inputs; (ii) exploring the underexamined synergy among modalities, particularly the role of lip movements as non-manual cues in sign language comprehension; and (iii) achieving performance on par with or superior to state-of-the-art models specialized for individual tasks. Building on this framework, we achieve performance on par with or better than task-specific state-of-the-art models across SLT, VSR, ASR, and Audio-Visual Speech Recognition. Furthermore, our analysis reveals a key linguistic insight: explicitly modeling lip movements as a distinct modality significantly improves SLT performance by capturing critical non-manual cues.

Minsu Kim, Jeong Hun Yeo, Se Jin Park et al.

This paper explores sentence-level multilingual Visual Speech Recognition (VSR) that can recognize different languages with a single trained model. As the massive multilingual modeling of visual data requires huge computational costs, we propose a novel training strategy, processing with visual speech units. Motivated by the recent success of the audio speech unit, we propose to use a visual speech unit that can be obtained by discretizing the visual speech features extracted from the self-supervised visual speech model. Through analysis, we verify that the visual speech units mainly contain viseme information while suppressing non-linguistic information. By using the visual speech units as the inputs of our system, we propose to pre-train a VSR model to predict corresponding text outputs on multilingual data constructed by merging several VSR databases. As both the inputs (i.e., visual speech units) and outputs (i.e., text) are discrete, we can greatly improve the training efficiency compared to the standard VSR training. Specifically, the input data size is reduced to 0.016% of the original video inputs. In order to complement the insufficient visual information in speech recognition, we apply curriculum learning where the inputs of the system begin with audio-visual speech units and gradually change to visual speech units. After pre-training, the model is finetuned on continuous features. We set new state-of-the-art multilingual VSR performances by achieving comparable performances to the previous language-specific VSR models, with a single trained model.