Shikhar Bharadwaj, Chin-Jou Li, Yoonjae Kim, Kwanghee Choi, Eunjung Yeo, Ryan Soh-Eun Shim, Hanyu Zhou, Brendon Boldt, Karen Rosero, Kalvin Chang, Darsh Agrawal, Keer Xu, Chao-Han Huck Yang, Jian Zhu, Shinji Watanabe, David R. Mortensen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Chin-Jou Li, Kalvin Chang, Shikhar Bharadwaj, Eunjung Yeo, Kwanghee Choi, Jian Zhu, David R. Mortensen, Shinji Watanabe. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Automatic speech recognition (ASR) for dysarthric speech remains challenging due to data scarcity, particularly in non-English languages. To address this, we fine-tune a voice conversion model on English dysarthric speech (UASpeech) to encode both speaker characteristics and prosodic distortions, then apply it to convert healthy non-English speech (FLEURS) into non-English dysarthric-like speech. The generated data is then used to fine-tune a multilingual ASR model, Massively Multilingual Speech (MMS), for improved dysarthric speech recognition. Evaluation on PC-GITA (Spanish), EasyCall (Italian), and SSNCE (Tamil) demonstrates that VC with both speaker and prosody conversion significantly outperforms the off-the-shelf MMS performance and conventional augmentation techniques such as speed and tempo perturbation. Objective and subjective analyses of the generated data further confirm that the generated speech simulates dysarthric characteristics.

Kwanghee Choi, Eunjung Yeo, Kalvin Chang, Shinji Watanabe, David R Mortensen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Taiqi He, Kwanghee Choi, Lindia Tjuatja, Nathaniel Robinson, Jiatong Shi, Shinji Watanabe, Graham Neubig, David Mortensen, Lori Levin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the subsequent model. However, they can still be redundant. Recent investigations proposed the use of discrete speech units derived from self-supervised learning representations, which significantly compresses the size of speech data. Applying various methods, such as de-duplication and subword modeling, can further compress the speech sequence length. Hence, training time is significantly reduced while retaining notable performance. In this study, we undertake a comprehensive and systematic exploration into the application of discrete units within end-to-end speech processing models. Experiments on 12 automatic speech recognition, 3 speech translation, and 1 spoken language understanding corpora demonstrate that discrete units achieve reasonably good results in almost all the settings. Our configurations and trained models are released in ESPnet to foster future research efforts.

With the success of self-supervised representations, researchers seek a better understanding of the information encapsulated within a representation. Among various interpretability methods, we focus on classification-based linear probing. We aim to foster a solid understanding and provide guidelines for linear probing by constructing a novel mathematical framework leveraging information theory. First, we connect probing with the variational bounds of mutual information (MI) to relax the probe design, equating linear probing with fine-tuning. Then, we investigate empirical behaviors and practices of probing through our mathematical framework. We analyze the layer-wise performance curve being convex, which seemingly violates the data processing inequality. However, we show that the intermediate representations can have the biggest MI estimate because of the tradeoff between better separability and decreasing MI. We further suggest that the margin of linearly separable representations can be a criterion for measuring the "goodness of representation." We also compare accuracy with MI as the measuring criteria. Finally, we empirically validate our claims by observing the self-supervised speech models on retaining word and phoneme information.

As maintaining road networks is labor-intensive, many au- tomatic road extraction approaches have been introduced to solve this real-world problem, fueled by the abundance of large-scale high-resolution satellite imagery and advances in computer vision. However, their performance is limited for fully automating the road map extraction in real-world ser- vices. Hence, many services employ the two-step human-in- the-loop system to post-process the extracted road maps: er- ror localization and automatic mending for faulty road maps. Our paper exclusively focuses on the latter step, introduc- ing a novel image inpainting approach for fixing road maps with complex road geometries without custom-made heuris- tics, yielding a method that is readily applicable to any road geometry extraction model. We demonstrate the effectiveness of our method on various real-world road geometries, such as straight and curvy roads, T-junctions, and intersections.

Inspired by humans comprehending speech in a multi-modal manner, various audio-visual datasets have been constructed. However, most existing datasets focus on English, developed from pre-existing videos using various prediction models, and have only a small number of multi-view videos. To mitigate the limitations, we constructed the Open Large-scale Korean Audio-Visual Speech (OLKAVS) dataset, which is the largest among publicly available audio-visual speech datasets. The dataset contains 1,150 hours of transcribed audio from 1,107 Korean speakers in a studio setup with nine different viewpoints and various noise situations. We also provide the pre-trained baseline models for two tasks: audiovisual speech recognition and lip reading. We conducted experiments based on the models to verify the effectiveness of multi-modal and multi-view training over uni-modal and frontal-view-only training. We expect the OLKAVS dataset to facilitate multi-modal research in broader areas.

We introduce ESPnet-EZ, an extension of the open-source speech processing toolkit ESPnet, aimed at quick and easy development of speech models. ESPnet-EZ focuses on two major aspects: (i) easy fine-tuning and inference of existing ESPnet models on various tasks and (ii) easy integration with popular deep neural network frameworks such as PyTorch-Lightning, Hugging Face transformers and datasets, and Lhotse. By replacing ESPnet design choices inherited from Kaldi with a Python-only, Bash-free interface, we dramatically reduce the effort required to build, debug, and use a new model. For example, to fine-tune a speech foundation model, ESPnet-EZ, compared to ESPnet, reduces the number of newly written code by 2.7x and the amount of dependent code by 6.7x while dramatically reducing the Bash script dependencies. The codebase of ESPnet-EZ is publicly available.1

Automatic assessment of dysarthric speech is essential for sustained treatments and rehabilitation. However, obtaining atypical speech is challenging, often leading to data scarcity issues. To tackle the problem, we propose a novel automatic severity assessment method for dysarthric speech, using the self-supervised model in conjunction with multi-task learning. Wav2vec 2.0 XLS-R is jointly trained for two different tasks: severity classification and auxiliary automatic speech recognition (ASR). For the baseline experiments, we employ hand-crafted acoustic features and machine learning classifiers such as SVM, MLP, and XGBoost. Explored on the Korean dysarthric speech QoLT database, our model out-performs the traditional baseline methods, with a relative percentage increase of 1.25% for F1-score. In addition, the proposed model surpasses the model trained without ASR head, achieving 10.61% relative percentage improvements. Furthermore, we present how multi-task learning affects the severity classification performance by analyzing the latent representations and regularization effect.

Active learning (AL) aims to select the most useful data samples from an unlabeled data pool and annotate them to expand the labeled dataset under a limited budget. Especially, uncertainty-based methods choose the most uncertain samples, which are known to be effective in improving model performance. However, previous methods often overlook training dynamics (TD), defined as the ever-changing model behavior during optimization via stochastic gradient descent, even though other research areas have empirically shown that TD provides important clues for measuring the data uncertainty. In this paper, we first provide theoretical and empirical evidence to argue the usefulness of utilizing the ever-changing model behavior rather than the fully trained model snapshot. We then propose a novel AL method, Training Dynamics for Active Learning (TiDAL), which efficiently predicts the training dynamics of unlabeled data to estimate their uncertainty. Experimental results show that our TiDAL achieves better or comparable performance on both balanced and imbalanced benchmark datasets compared to state-of-the-art AL methods, which estimate data uncertainty using only static information after model training.

This paper proposes an improved Goodness of Pronunciation (GoP) that utilizes Uncertainty Quantification (UQ) for automatic speech intelligibility assessment for dysarthric speech. Current GoP methods rely heavily on neural network-driven overconfident predictions, which is unsuitable for assessing dysarthric speech due to its significant acoustic differences from healthy speech. To alleviate the problem, UQ techniques were used on GoP by 1) normalizing the phoneme prediction (entropy, margin, maxlogit, logit-margin) and 2) modifying the scoring function (scaling, prior normalization). As a result, prior-normalized maxlogit GoP achieves the best performance, with a relative increase of 5.66%, 3.91%, and 23.65% compared to the baseline GoP for English, Korean, and Tamil, respectively. Furthermore, phoneme analysis is conducted to identify which phoneme scores significantly correlate with intelligibility scores in each language.

Social media platforms struggle to protect users from harmful content through content moderation. These platforms have recently leveraged machine learning models to cope with the vast amount of user-generated content daily. Since moderation policies vary depending on countries and types of products, it is common to train and deploy the models per policy. However, this approach is highly inefficient, especially when the policies change, requiring dataset re-labeling and model re-training on the shifted data distribution. To alleviate this cost inefficiency, social media platforms often employ third-party content moderation services that provide prediction scores of multiple subtasks, such as predicting the existence of underage personnel, rude gestures, or weapons, instead of directly providing final moderation decisions. However, making a reliable automated moderation decision from the prediction scores of the multiple subtasks for a specific target policy has not been widely explored yet. In this study, we formulate real-world scenarios of content moderation and introduce a simple yet effective threshold optimization method that searches the optimal thresholds of the multiple subtasks to make a reliable moderation decision in a cost-effective way. Extensive experiments demonstrate that our approach shows better performance in content moderation compared to existing threshold optimization methods and heuristics.

Improving the performance of on-device audio classification models remains a challenge given the computational limits of the mobile environment. Many studies leverage knowledge distillation to boost predictive performance by transferring the knowledge from large models to on-device models. However, most lack a mechanism to distill the essence of the temporal information, which is crucial to audio classification tasks, or similar architecture is often required. In this paper, we propose a new knowledge distillation method designed to incorporate the temporal knowledge embedded in attention weights of large transformer-based models into on-device models. Our distillation method is applicable to various types of architectures, including the non-attention-based architectures such as CNNs or RNNs, while retaining the original network architecture during inference. Through extensive experiments on both an audio event detection dataset and a noisy keyword spotting dataset, we show that our proposed method improves the predictive performance across diverse on-device architectures.

Notable progress has been made in numerous fields of machine learning based on neural network-driven mutual information (MI) bounds. However, utilizing the conventional MI-based losses is often challenging due to their practical and mathematical limitations. In this work, we first identify the symptoms behind their instability: (1) the neural network not converging even after the loss seemed to converge, and (2) saturating neural network outputs causing the loss to diverge. We mitigate both issues by adding a novel regularization term to the existing losses. We theoretically and experimentally demonstrate that added regularization stabilizes training. Finally, we present a novel benchmark that evaluates MI-based losses on both the MI estimation power and its capability on the downstream tasks, closely following the pre-existing supervised and contrastive learning settings. We evaluate six different MI-based losses and their regularized counterparts on multiple benchmarks to show that our approach is simple yet effective.

The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable practicality since the target may also be long-tailed. Therefore, we formulate long-tailed visual recognition as a label shift problem where the tar-get and source label distributions are different. One of the significant hurdles in dealing with the label shift problem is the entanglement between the source label distribution and the model prediction. In this paper, we focus on disentangling the source label distribution from the model prediction. We first introduce a simple but over-looked baseline method that matches the target label distribution by post-processing the model prediction trained by the cross-entropy loss and the Softmax function. Al-though this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase. Thus, we propose a novel method, LAbel distribution DisEntangling (LADE) loss based on the optimal bound of Donsker-Varadhan representation. LADE achieves state-of-the-art performance on benchmark datasets such as CIFAR-100-LT, Places-LT, ImageNet-LT, and iNaturalist 2018. Moreover, LADE out-performs existing methods on various shifted target label distributions, showing the general adaptability of our pro-posed method.