arXiv subjects

Joon-Hyuk Chang

Publications and source records attributed to Joon-Hyuk Chang.

14 recordsLinked to original sources

arXiv2026

Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition

Large language model (LLM)-based audio-visual speech recognition (AVSR) systems are robust under noise. Contrastive decoding (CD), originally introduced to stabilize LLM generation by contrasting a weaker model against a stronger one at inference time, adjusts predictions without additional training. In this work, we apply CD to AVSR by contrasting audio-only conditioning with full audio-visual conditioning within the same underlying model. However, using a fixed contrastive strength introduces a trade-off across noise levels: stronger intervention helps under severe noise but may over-correct reliable predictions in clean conditions. We propose reliability-aware scaling of CD for AVSR. Instead of using a fixed strength, we adaptively modulate the contrastive influence at each token based on reliability signals derived from attention dynamics and inter-model predictive divergence. Experiments on LRS3 show consistent improvements across clean and low-SNR conditions.

cs.SD↗

arXiv2026

A Dual-Branch Parallel Network for Speech Enhancement and Restoration

We present a novel general speech restoration model, DBP-Net (dual-branch parallel network), designed to effectively handle complex real-world distortions including noise, reverberation, and bandwidth degradation. Unlike prior approaches that rely on a single processing path or separate models for enhancement and restoration, DBP-Net introduces a unified architecture with dual parallel branches-a masking-based branch for distortion suppression and a mapping-based branch for spectrum reconstruction. A key innovation behind DBP-Net lies in the parameter sharing between the two branches and a cross-branch skip fusion, where the output of the masking branch is explicitly fused into the mapping branch. This design enables DBP-Net to simultaneously leverage complementary learning strategies-suppression and generation-within a lightweight framework. Experimental results show that DBP-Net significantly outperforms existing baselines in comprehensive speech restoration tasks while maintaining a compact model size. These findings suggest that DBP-Net offers an effective and scalable solution for unified speech enhancement and restoration in diverse distortion scenarios.

eess.AS↗

arXiv2026

Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognition

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent recognition improvements due to residual distortions and mismatches with the latent space of the ASR encoder. In this letter, we introduce a complementary strategy termed latent-level enhancement, where distorted representations are refined during ASR inference. Specifically, we propose a plug-and-play Flow Matching Refinement module (FM-Refiner) that operates on the output latents of a pretrained CTC-based ASR encoder. Trained to map imperfect latents-either directly from noisy inputs or from enhanced-but-imperfect speech-toward their clean counterparts, the FM-Refiner is applied only at inference, without fine-tuning ASR parameters. Experiments show that FM-Refiner consistently reduces word error rate, both when directly applied to noisy inputs and when combined with conventional SE front-ends. These results demonstrate that latent-level refinement via flow matching provides a lightweight and effective complement to existing SE approaches for robust ASR.

eess.AS↗

arXiv2025

Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion

Robust audio-visual speech recognition (AVSR) in noisy environments remains challenging, as existing systems struggle to estimate audio reliability and dynamically adjust modality reliance. We propose router-gated cross-modal feature fusion, a novel AVSR framework that adaptively reweights audio and visual features based on token-level acoustic corruption scores. Using an audio-visual feature fusion-based router, our method down-weights unreliable audio tokens and reinforces visual cues through gated cross-attention in each decoder layer. This enables the model to pivot toward the visual modality when audio quality deteriorates. Experiments on LRS3 demonstrate that our approach achieves an 16.51-42.67% relative reduction in word error rate compared to AV-HuBERT. Ablation studies confirm that both the router and gating mechanism contribute to improved robustness under real-world acoustic noise.

cs.CV↗

arXiv2025

FLOWER: Flow-Based Estimated Gaussian Guidance for General Speech Restoration

We introduce FLOWER, a novel conditioning method designed for speech restoration that integrates Gaussian guidance into generative frameworks. By transforming clean speech into a predefined prior distribution (e.g., Gaussian distribution) using a normalizing flow network, FLOWER extracts critical information to guide generative models. This guidance is incorporated into each block of the generative network, enabling precise restoration control. Experimental results demonstrate the effectiveness of FLOWER in improving performance across various general speech restoration tasks.

eess.AS↗

arXiv2025

Trainable Adaptive Score Normalization for Automatic Speaker Verification

Adaptive S-norm (AS-norm) calibrates automatic speaker verification (ASV) scores by normalizing them utilize the scores of impostors which are similar to the input speaker. However, AS-norm does not involve any learning process, limiting its ability to provide appropriate regularization strength for various evaluation utterances. To address this limitation, we propose a trainable AS-norm (TAS-norm) that leverages learnable impostor embeddings (LIEs), which are used to compose the cohort. These LIEs are initialized to represent each speaker in a training dataset consisting of impostor speakers. Subsequently, LIEs are fine-tuned by simulating an ASV evaluation. We utilize a margin penalty during top-scoring IEs selection in fine-tuning to prevent non-impostor speakers from being selected. In our experiments with ECAPA-TDNN, the proposed TAS-norm observed 4.11% and 10.62% relative improvement in equal error rate and minimum detection cost function, respectively, on VoxCeleb1-O trial compared with standard AS-norm without using proposed LIEs. We further validated the effectiveness of the TAS-norm on additional ASV datasets comprising Persian and Chinese, demonstrating its robustness across different languages.

eess.AS↗

arXiv2024

Team HYU ASML ROBOVOX SP Cup 2024 System Description

This report describes the submission of HYU ASML team to the IEEE Signal Processing Cup 2024 (SP Cup 2024). This challenge, titled "ROBOVOX: Far-Field Speaker Recognition by a Mobile Robot," focuses on speaker recognition using a mobile robot in noisy and reverberant conditions. Our solution combines the result of deep residual neural networks and time-delay neural network-based speaker embedding models. These models were trained on a diverse dataset that includes French speech. To account for the challenging evaluation environment characterized by high noise, reverberation, and short speech conditions, we focused on data augmentation and training speech duration for the speaker embedding model. Our submission achieved second place on the SP Cup 2024 public leaderboard, with a detection cost function of 0.5245 and an equal error rate of 6.46%.

eess.AS↗

arXiv2023

Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training effectiveness of SA-EEND models, we propose the use of auxiliary losses for the SA heads of the transformer layers. Specifically, we assume that the attention weight matrices of an SA layer are redundant if their patterns are similar to those of the identity matrix. We then explicitly constrain such matrices to exhibit specific speaker activity patterns relevant to voice activity detection or overlapped speech detection tasks. Consequently, we expect the proposed auxiliary losses to guide the transformer layers to exhibit more diverse patterns in the attention weights, thereby reducing the assumed redundancies in the SA heads. The effectiveness of the proposed method is demonstrated using the simulated and CALLHOME datasets for two-speaker diarization tasks, reducing the diarization error rate of the conventional SA-EEND model by 32.58% and 17.11%, respectively.

eess.AS↗

arXiv2022

Instance-level loss based multiple-instance learning framework for acoustic scene classification

In the acoustic scene classification (ASC) task, an acoustic scene consists of diverse sounds and is inferred by identifying combinations of distinct attributes among them. This study aims to extract and cluster these attributes effectively using an improved multiple-instance learning (MIL) framework for ASC. MIL, known as a weakly supervised learning method, is a strategy for extracting an instance from a bundle of frames composing an input audio clip and inferring a scene corresponding to the input data using these unlabeled instances. However, many studies pointed out an underestimation problem of MIL. In this study, we develop a MIL framework more suitable for ASC systems by defining instance-level labels and loss to extract and cluster instances effectively. Furthermore, we design a fully separated convolutional module, which is a lightweight neural network comprising pointwise, frequency-sided depthwise, and temporal-sided depthwise convolutional filters. As a result, compared to vanilla MIL, the confidence and proportion of positive instances increase significantly, overcoming the underestimation problem and improving the classification accuracy up to 11%. The proposed system achieved a performance of 81.1% and 72.3% on the TAU urban acoustic scenes 2019 and 2020 mobile datasets with 139 K parameters, respectively. Especially, it achieves the highest performance among the systems having under the 1 M parameters on the TAU urban acoustic scenes 2019 dataset.

cs.SD↗

arXiv2021

Task-specific Optimization of Virtual Channel Linear Prediction-based Speech Dereverberation Front-End for Far-Field Speaker Verification

Developing a single-microphone speech denoising or dereverberation front-end for robust automatic speaker verification (ASV) in noisy far-field speaking scenarios is challenging. To address this problem, we present a novel front-end design that involves a recently proposed extension of the weighted prediction error (WPE) speech dereverberation algorithm, the virtual acoustic channel expansion (VACE)-WPE. It is demonstrated experimentally in this study that unlike the conventional WPE algorithm, the VACE-WPE can be explicitly trained to cancel out both late reverberation and background noise. To build the front-end, the VACE-WPE is first independently (pre)trained to produce "noisy" dereverberated signals. Subsequently, given a pretrained speaker embedding model, the VACE-WPE is additionally fine-tuned within a task-specific optimization (TSO) framework, causing the speaker embedding extracted from the processed signal to be similar to that extracted from the "noise-free" target signal. Moreover, to extend the application of the proposed front-end to more general, unconstrained "in-the-wild" ASV scenarios beyond controlled far-field conditions, we propose a distortion regularization method for the VACE-WPE within the TSO framework. The effectiveness of the proposed approach is verified on both far-field and in-the-wild ASV benchmarks, demonstrating its superiority over fully neural front-ends and other TSO methods in various cases.

eess.AS↗

arXiv2021

Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach

The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech recognition systems with massive deep learning-based LMs is a major topic of speech recognition research. Among the various methods of applying LMs to speech recognition systems, in this paper, we focus on a cross-modal knowledge distillation method that transfers knowledge between two types of deep neural networks with different modalities. We propose an acoustic model structure with multiple auxiliary output layers for cross-modal distillation and demonstrate that the proposed method effectively compensates for the shortcomings of the existing label-interpolation-based distillation method. In addition, we extend the proposed method to a hierarchical distillation method using LMs trained in different units (senones, monophones, and subwords) and reveal the effectiveness of the hierarchical distillation method through an ablation study.

cs.LG↗

arXiv2021

Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs

Attribution methods calculate attributions that visually explain the predictions of deep neural networks (DNNs) by highlighting important parts of the input features. In particular, gradient-based attribution (GBA) methods are widely used because they can be easily implemented through automatic differentiation. In this study, we use the attributions that filter out irrelevant parts of the input features and then verify the effectiveness of this approach by measuring the classification accuracy of a pre-trained DNN. This is achieved by calculating and applying an \textit{attribution mask} to the input features and subsequently introducing the masked features to the DNN, for which the mask is designed to recursively focus attention on the parts of the input related to the target label. The accuracy is enhanced under a certain condition, i.e., \textit{no implicit bias}, which can be derived based on our theoretical insight into compressing the DNN into a single-layer neural network. We also provide Gradient\,*\,Sign-of-Input (GxSI) to obtain the attribution mask that further improves the accuracy. As an example, on CIFAR-10 that is modified using the attribution mask obtained from GxSI, we achieve the accuracy ranging from 99.8\% to 99.9\% without additional training.

cs.LG↗

arXiv2021

VACE-WPE: Virtual Acoustic Channel Expansion Based On Neural Networks for Weighted Prediction Error-Based Speech Dereverberation

Speech dereverberation is an important issue for many real-world speech processing applications. Among the techniques developed, the weighted prediction error (WPE) algorithm has been widely adopted and advanced over the last decade, which blindly cancels out the late reverberation component from the reverberant mixture of microphone signals. In this study, we extend the neural-network-based virtual acoustic channel expansion (VACE) framework for the WPE-based speech dereverberation, a variant of the WPE that we recently proposed to enable the use of dual-channel WPE algorithm in a single-microphone speech dereverberation scenario. Based on the previous study, some ablation studies are conducted regarding the constituents of the VACE-WPE in an offline processing scenario. These studies help understand the dynamics of the system, thereby simplifying the architecture and leading to the introduction of new strategies for training the neural network for the VACE. Experimental results in noisy reverberant environments reveal that VACE-WPE considerably outperforms its single-channel counterpart in terms of objective speech quality and is complementary to the single-channel WPE when employed as the front-end for the far-field automatic speech recognizer.

eess.AS↗

arXiv2016

Ensemble of Jointly Trained Deep Neural Network-Based Acoustic Models for Reverberant Speech Recognition

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in real-world situations, we present novel approaches for acoustic modeling including an ensemble of deep neural networks (DNNs) and an ensemble of jointly trained DNNs. First, multiple DNNs are established, each of which corresponds to a different reverberation time 60 (RT60) in a setup step. Also, each model in the ensemble of DNN acoustic models is further jointly trained, including both feature mapping and acoustic modeling, where the feature mapping is designed for the dereverberation as a front-end. In a testing phase, the two most likely DNNs are chosen from the DNN ensemble using maximum a posteriori (MAP) probabilities, computed in an online fashion by using maximum likelihood (ML)-based blind RT60 estimation and then the posterior probability outputs from two DNNs are combined using the ML-based weights as a simple average. Extensive experiments demonstrate that the proposed approach leads to substantial improvements in speech recognition accuracy over the conventional DNN baseline systems under diverse reverberant conditions.

cs.CL↗