arXiv subjects

Hong Kook Kim

Publications and source records attributed to Hong Kook Kim.

14 recordsLinked to original sources

arXiv2026

Parameter isolation with domain-specific experts for incremental audio classification

To successfully deploy a model in time-varying environments such as streaming data prediction and sensing control, domain-incremental learning (DIL) has attracted attention since it aims to adapt a previously trained model to newly arriving domains, while reserving knowledge from earlier domains without accessing their data. Incremental learning across domains can be regarded as a recurrent update, in which the current model is obtained by updating the model carried over from previous domains. Conventional DIL approaches that rely on domain-invariant feature learning and weight regularization gradually overwrite or constrain parameters learned in previous domains, leading to catastrophic forgetting. Instead, this paper proposes a new domain-specific parameter-isolation architecture that retains all past domains. The proposed architecture mitigates catastrophic forgetting through a full-order recurrent update, constructing a new expert using domain-specific data conditioned on all previously frozen models. To achieve this, we incorporate data-free generative replay to reconstruct previous-domain data and cross-domain feature generation to recover later expert features missing from earlier domain samples. Finally, we apply the proposed model architecture to domain-agnostic incremental learning for audio classification, as defined in the DCASE 2026 Challenge Task 7. Consequently, we achieve micro and macro accuracies of 78.4% and 78.9%, respectively, representing increases of 33 and 25 percentage points over the Challenge baseline. Ablation studies are conducted to examine the effectiveness of each processing component in terms of classification accuracy.

eess.AS↗

arXiv2026

Domain-incremental audio classification using domain-specific experts and prototype classifier

This technical report presents submission systems for Task 7(domain-incremental audio classification) of the DCASE 2026 Challenge. The main obstacle is that, the system is unable to access to past or future domain's data at once. We approached domain-incremental learning (DIL) as a frozen-feature replay problem. At each incremental stage, one or two compact experts are trained and then kept fixed; at the final stage, the penultimate features from all frozen experts are concatenated and used to train a lightweight per-class prototype classifier solely on cached features. This design prevents catastrophic forgetting by preserving each expert models at inference. To retain earlier-domain knowledge without storing raw audio, some experts were trained with DeepInversion-based generative replay. A cross-stage regression imputer was trained to fill the expert feature slots that did not yet exist at an ealier stage. We submit four fully DIL-compliant systems: three systems based on diverse frozen five-expert backbones and their cross-stack ensemble achieving 78.15% micro / 77.03% macro on the development set, outperforming every individual backbone on both evaluations.

eess.AS↗

arXiv2026

PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing

Recently, artificial intelligence-based dubbing technology has advanced, enabling automated dubbing (AD) to convert the source speech of a video into target speech in different languages. However, natural AD still faces synchronization challenges such as duration and lip-synchronization (lip-sync), which are crucial for preserving the viewer experience. Therefore, this paper proposes a synchronization method for AD processes that paraphrases translated text, comprising two steps: isochrony for timing constraints and phonetic synchronization (PS) to preserve lip-sync. First, we achieve isochrony by paraphrasing the translated text with a language model, ensuring the target speech duration matches that of the source speech. Second, we introduce PS, which employs dynamic time warping (DTW) with local costs of vowel distances measured from training data so that the target text composes vowels with pronunciations similar to source vowels. Third, we extend this approach to PSComet, which jointly considers semantic and phonetic similarity to preserve meaning better. The proposed methods are incorporated into text-to-speech systems, PS-TTS and PS-Comet TTS. The performance evaluation using Korean and English lip-reading datasets and a voice-actor dubbing dataset demonstrates that both systems outperform TTS without PS on several objective metrics and outperform voice actors in Korean-to-English and English-to-Korean dubbing. We extend the experiments to French, testing all pairs among these languages to evaluate cross-linguistic applicability. Across all language pairs, PS-Comet performed best, balancing lip-sync accuracy with semantic preservation, confirming that PS-Comet achieves more accurate lip-sync with semantic preservation than PS alone.

eess.AS↗

arXiv2026

MolDA: Molecular Understanding and Generation via Large Language Diffusion Model

Large Language Models (LLMs) have significantly advanced molecular discovery, but existing multimodal molecular architectures fundamentally rely on autoregressive (AR) backbones. This strict left-to-right inductive bias is sub-optimal for generating chemically valid molecules, as it struggles to account for non-local global constraints (e.g., ring closures) and often accumulates structural errors during sequential generation. To address these limitations, we propose MolDA (Molecular language model with masked Diffusion with mAsking), a novel multimodal framework that replaces the conventional AR backbone with a discrete Large Language Diffusion Model. MolDA extracts comprehensive structural representations using a hybrid graph encoder, which captures both local and global topologies, and aligns them into the language token space via a Q-Former. Furthermore, we mathematically reformulate Molecular Structure Preference Optimization specifically for the masked diffusion. Through bidirectional iterative denoising, MolDA ensures global structural coherence, chemical validity, and robust reasoning across molecule generation, captioning, and property prediction.

cs.AI↗

arXiv2025

Unlocking Robust Semantic Segmentation Performance via Label-only Elastic Deformations against Implicit Label Noise

While previous studies on image segmentation focus on handling severe (or explicit) label noise, real-world datasets also exhibit subtle (or implicit) label imperfections. These arise from inherent challenges, such as ambiguous object boundaries and annotator variability. Although not explicitly present, such mild and latent noise can still impair model performance. Typical data augmentation methods, which apply identical transformations to the image and its label, risk amplifying these subtle imperfections and limiting the model's generalization capacity. In this paper, we introduce NSegment+, a novel augmentation framework that decouples image and label transformations to address such realistic noise for semantic segmentation. By introducing controlled elastic deformations only to segmentation labels while preserving the original images, our method encourages models to focus on learning robust representations of object structures despite minor label inconsistencies. Extensive experiments demonstrate that NSegment+ consistently improves performance, achieving mIoU gains of up to +2.29, +2.38, +1.75, and +3.39 in average on Vaihingen, LoveDA, Cityscapes, and PASCAL VOC, respectively-even without bells and whistles, highlighting the importance of addressing implicit label noise. These gains can be further amplified when combined with other training tricks, including CutMix and Label Smoothing.

cs.CV↗

arXiv2025

Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4

This technical report presents submission systems for Task 4 of the DCASE 2025 Challenge. This model incorporates additional audio features (spectral roll-off and chroma features) into the embedding feature extracted from the mel-spectral feature to im-prove the classification capabilities of an audio-tagging model in the spatial semantic segmentation of sound scenes (S5) system. This approach is motivated by the fact that mixed audio often contains subtle cues that are difficult to capture with mel-spectrograms alone. Thus, these additional features offer alterna-tive perspectives for the model. Second, an agent-based label correction system is applied to the outputs processed by the S5 system. This system reduces false positives, improving the final class-aware signal-to-distortion ratio improvement (CA-SDRi) metric. Finally, we refine the training dataset to enhance the classi-fication accuracy of low-performing classes by removing irrele-vant samples and incorporating external data. That is, audio mix-tures are generated from a limited number of data points; thus, even a small number of out-of-class data points could degrade model performance. The experiments demonstrate that the submit-ted systems employing these approaches relatively improve CA-SDRi by up to 14.7% compared to the baseline of DCASE 2025 Challenge Task 4.

eess.AS↗

arXiv2024

Performance Improvement of Language-Queried Audio Source Separation Based on Caption Augmentation From Large Language Models for DCASE Challenge 2024 Task 9

We present a prompt-engineering-based text-augmentation approach applied to a language-queried audio source separation (LASS) task. To enhance the performance of LASS, the proposed approach utilizes large language models (LLMs) to generate multiple captions corresponding to each sentence of the training dataset. To this end, we first perform experiments to identify the most effective prompts for caption augmentation with a smaller number of captions. A LASS model trained with these augmented captions demonstrates improved performance on the DCASE 2024 Task 9 validation set compared to that trained without augmentation. This study highlights the effectiveness of LLM-based caption augmentation in advancing language-queried audio source separation.

eess.AS↗

arXiv2024

Sound event detection based on auxiliary decoder and maximum probability aggregation for DCASE Challenge 2024 Task 4

In this report, we propose three novel methods for developing a sound event detection (SED) model for the DCASE 2024 Challenge Task 4. First, we propose an auxiliary decoder attached to the final convolutional block to improve feature extraction capabilities while reducing dependency on embeddings from pre-trained large models. The proposed auxiliary decoder operates independently from the main decoder, enhancing performance of the convolutional block during the initial training stages by assigning a different weight strategy between main and auxiliary decoder losses. Next, to address the time interval issue between the DESED and MAESTRO datasets, we propose maximum probability aggregation (MPA) during the training step. The proposed MPA method enables the model's output to be aligned with soft labels of 1 s in the MAESTRO dataset. Finally, we propose a multi-channel input feature that employs various versions of logmel and MFCC features to generate time-frequency pattern. The experimental results demonstrate the efficacy of these proposed methods in a view of improving SED performance by achieving a balanced enhancement across different datasets and label types. Ultimately, this approach presents a significant step forward in developing more robust and flexible SED models

eess.AS↗

arXiv2023

GIST-AiTeR Speaker Diarization System for VoxCeleb Speaker Recognition Challenge (VoxSRC) 2023

This report describes the submission system by the GIST-AiTeR team for the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23) Track 4. Our submission system focuses on implementing diverse speaker diarization (SD) techniques, including ResNet293 and MFA-Conformer with different combinations of segment and hop length. Then, those models are combined into an ensemble model. The ResNet293 and MFA-Conformer models exhibited the diarization error rates (DERs) of 3.65% and 3.83% on VAL46, respectively. The submitted ensemble model provided a DER of 3.50% on VAL46, and consequently, it achieved a DER of 4.88% on the VoxSRC-23 test set.

eess.AS↗

arXiv2023

Semi-supervsied Learning-based Sound Event Detection using Freuqency Dynamic Convolution with Large Kernel Attention for DCASE Challenge 2023 Task 4

This report proposes a frequency dynamic convolution (FDY) with a large kernel attention (LKA)-convolutional recurrent neural network (CRNN) with a pre-trained bidirectional encoder representation from audio transformers (BEATs) embedding-based sound event detection (SED) model that employs a mean-teacher and pseudo-label approach to address the challenge of limited labeled data for DCASE 2023 Task 4. The proposed FDY with LKA integrates the FDY and LKA module to effectively capture time-frequency patterns, long-term dependencies, and high-level semantic information in audio signals. The proposed FDY with LKA-CRNN with a BEATs embedding network is initially trained on the entire DCASE 2023 Task 4 dataset using the mean-teacher approach, generating pseudo-labels for weakly labeled, unlabeled, and the AudioSet. Subsequently, the proposed SED model is retrained using the same pseudo-label approach. A subset of these models is selected for submission, demonstrating superior F1-scores and polyphonic SED score performance on the DCASE 2023 Challenge Task 4 validation dataset.

eess.AS↗

arXiv2022

GIST-AiTeR System for the Diarization Task of the 2022 VoxCeleb Speaker Recognition Challenge

This report describes the submission system of the GIST-AiTeR team at the 2022 VoxCeleb Speaker Recognition Challenge (VoxSRC) Track 4. Our system mainly includes speech enhancement, voice activity detection , multi-scaled speaker embedding, probabilistic linear discriminant analysis-based speaker clustering, and overlapped speech detection models. We first construct four different diarization systems according to different model combinations with the best experimental efforts. Our final submission is an ensemble system of all the four systems and achieves a diarization error rate of 5.12% on the challenge evaluation set, ranked third at the diarization track of the challenge.

eess.AS↗

arXiv2022

Auxiliary Loss of Transformer with Residual Connection for End-to-End Speaker Diarization

End-to-end neural diarization (EEND) with self-attention directly predicts speaker labels from inputs and enables the handling of overlapped speech. Although the EEND outperforms clustering-based speaker diarization (SD), it cannot be further improved by simply increasing the number of encoder blocks because the last encoder block is dominantly supervised compared with lower blocks. This paper proposes a new residual auxiliary EEND (RX-EEND) learning architecture for transformers to enforce the lower encoder blocks to learn more accurately. The auxiliary loss is applied to the output of each encoder block, including the last encoder block. The effect of auxiliary loss on the learning of the encoder blocks can be further increased by adding a residual connection between the encoder blocks of the EEND. Performance evaluation and ablation study reveal that the auxiliary loss in the proposed RX-EEND provides relative reductions in the diarization error rate (DER) by 50.3% and 21.0% on the simulated and CALLHOME (CH) datasets, respectively, compared with self-attentive EEND (SA-EEND). Furthermore, the residual connection used in RX-EEND further relatively reduces the DER by 8.1% for CH dataset.

eess.AS↗

arXiv2021

Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4

This report proposes a polyphonic sound event detection (SED) method for the DCASE 2021 Challenge Task 4. The proposed SED model consists of two stages: a mean-teacher model for providing target labels regarding weakly labeled or unlabeled data and a self-training-based noisy student model for predicting strong labels for sound events. The mean-teacher model, which is based on the residual convolutional recurrent neural network (RCRNN) for the teacher and student model, is first trained using all the training data from a weakly labeled dataset, an unlabeled dataset, and a strongly labeled synthetic dataset. Then, the trained mean-teacher model predicts the strong label to each of the weakly labeled and unlabeled datasets, which is brought to the noisy student model in the second stage of the proposed SED model. Here, the structure of the noisy student model is identical to the RCRNN-based student model of the mean-teacher model in the first stage. Then, it is self-trained by adding feature noises, such as time-frequency shift, mixup, SpecAugment, and dropout-based model noise. In addition, a semi-supervised loss function is applied to train the noisy student model, which acts as label noise injection. The performance of the proposed SED model is evaluated on the validation set of the DCASE 2021 Challenge Task 4, and then, several ensemble models that combine five-fold validation models with different hyperparameters of the semi-supervised loss function are finally selected as our final models.

cs.SD↗

arXiv2020

Polyphonic sound event detection based on convolutional recurrent neural networks with semi-supervised loss function for DCASE challenge 2020 task 4

This report proposes a polyphonic sound event detection (SED) method for the DCASE 2020 Challenge Task 4. The proposed SED method is based on semi-supervised learning to deal with the different combination of training datasets such as weakly labeled dataset, unlabeled dataset, and strongly labeled synthetic dataset. Especially, the target label of each audio clip from weakly labeled or unlabeled dataset is first predicted by using the mean teacher model that is the DCASE 2020 baseline. The data with predicted labels are used for training the proposed SED model, which consists of CNNs with skip connections and self-attention mechanism, followed by RNNs. In order to compensate for the erroneous prediction of weakly labeled and unlabeled data, a semi-supervised loss function is employed for the proposed SED model. In this work, several versions of the proposed SED model are implemented and evaluated on the validation set according to the different parameter setting for the semi-supervised loss function, and then an ensemble model that combines five-fold validation models is finally selected as our final model.

eess.AS↗