arXiv subjects

Jihwan Lee

Publications and source records attributed to Jihwan Lee.

At least 37 records · Page 2Linked to original sources

arXiv2026

Interpretable Modeling of Articulatory Temporal Dynamics from real-time MRI for Phoneme Recognition

Real-time Magnetic Resonance Imaging (rtMRI) visualizes vocal tract action, offering a comprehensive window into speech articulation. However, its signals are high dimensional and noisy, hindering interpretation. We investigate compact representations of spatiotemporal articulatory dynamics for phoneme recognition from midsagittal vocal tract rtMRI videos. We compare three feature types: (1) raw video, (2) optical flow, and (3) six linguistically-relevant regions of interest (ROIs) for articulator movements. We evaluate models trained independently on each representation, as well as multi-feature combinations. Results show that multi-feature models consistently outperform single-feature baselines, with the lowest phoneme error rate (PER) of 0.34 obtained by combining ROI and raw video. Temporal fidelity experiments demonstrate a reliance on fine-grained articulatory dynamics, while ROI ablation studies reveal strong contributions from tongue and lips. Our findings highlight how rtMRI-derived features provide accuracy and interpretability, and establish strategies for leveraging articulatory data in speech processing.

eess.IV↗

arXiv2026

Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis

Many spoken languages, including English, exhibit wide variation in dialects and accents, making accent control an important capability for flexible text-to-speech (TTS) models. Current TTS systems typically generate accented speech by conditioning on speaker embeddings associated with specific accents. While effective, this approach offers limited interpretability and controllability, as embeddings also encode traits such as timbre and emotion. In this study, we analyze the interaction between speaker embeddings and linguistically motivated phonological rules in accented speech synthesis. Using American and British English as a case study, we implement rules for flapping, rhoticity, and vowel correspondences. We propose the phoneme shift rate (PSR), a novel metric quantifying how strongly embeddings preserve or override rule-based transformations. Experiments show that combining rules with embeddings yields more authentic accents, while embeddings can attenuate or overwrite rules, revealing entanglement between accent and speaker identity. Our findings highlight rules as a lever for accent control and a framework for evaluating disentanglement in speech generation.

cs.CL↗

arXiv2026

ARTI-6: Towards Six-dimensional Articulatory Speech Encoding

We propose ARTI-6, a compact six-dimensional articulatory speech encoding framework derived from real-time MRI data that captures crucial vocal tract regions including the velum, tongue root, and larynx. ARTI-6 consists of three components: (1) a six-dimensional articulatory feature set representing key regions of the vocal tract; (2) an articulatory inversion model, which predicts articulatory features from speech acoustics leveraging speech foundation models, achieving a prediction correlation of 0.87; and (3) an articulatory synthesis model, which reconstructs intelligible speech directly from articulatory features, showing that even a low-dimensional representation can generate natural-sounding speech. Together, ARTI-6 provides an interpretable, computationally efficient, and physiologically grounded framework for advancing articulatory inversion, synthesis, and broader speech technology applications. The source code and speech samples are publicly available.

eess.AS↗

arXiv2025

Neural Codecs as Biosignal Tokenizers

Neurophysiological recordings such as electroencephalography (EEG) offer accessible and minimally invasive means of estimating physiological activity for applications in healthcare, diagnostic screening, and even immersive entertainment. However, these recordings yield high-dimensional, noisy time-series data that typically require extensive pre-processing and handcrafted feature extraction to reveal meaningful information. Recently, there has been a surge of interest in applying representation learning techniques from large pre-trained (foundation) models to effectively decode and interpret biosignals. We discuss the challenges posed for incorporating such methods and introduce BioCodec, an alternative representation learning framework inspired by neural codecs to capture low-level signal characteristics in the form of discrete tokens. Pre-trained on thousands of EEG hours, BioCodec shows efficacy across multiple downstream tasks, ranging from clinical diagnostic tasks and sleep physiology to decoding speech and motor imagery, particularly in low-resource settings. Additionally, we provide a qualitative analysis of codebook usage and estimate the spatial coherence of codebook embeddings from EEG connectivity. Notably, we also document the suitability of our method to other biosignal data, i.e., electromyographic (EMG) signals. Overall, the proposed approach provides a versatile solution for biosignal tokenization that performs competitively with state-of-the-art models. The source code and model checkpoints are shared.

cs.LG↗

arXiv2025

A long-form single-speaker real-time MRI speech dataset and benchmark

We release the USC Long Single-Speaker (LSS) dataset containing real-time MRI video of the vocal tract dynamics and simultaneous audio obtained during speech production. This unique dataset contains roughly one hour of video and audio data from a single native speaker of American English, making it one of the longer publicly available single-speaker datasets of real-time MRI speech data. Along with the articulatory and acoustic raw data, we release derived representations of the data that are suitable for a range of downstream tasks. This includes video cropped to the vocal tract region, sentence-level splits of the data, restored and denoised audio, and regions-of-interest timeseries. We also benchmark this dataset on articulatory synthesis and phoneme recognition tasks, providing baseline performance for these tasks on this dataset which future research can aim to improve upon.

cs.SD↗

arXiv2025

Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe

We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian. Our study used over 2 million training utterances from 30 publicly available speech corpora that are provided with dialectal information. We evaluate the performance of several widely used speech foundation models in classifying speech dialects. We assess the robustness of the dialectal models under noisy conditions and present an error analysis that highlights modeling results aligned with geographic continuity. In addition to benchmarking dialect classification, we demonstrate several downstream applications enabled by Voxlect. Specifically, we show that Voxlect can be applied to augment existing speech recognition datasets with dialect information, enabling a more detailed analysis of ASR performance across dialectal variations. Voxlect is also used as a tool to evaluate the performance of speech generation systems. Voxlect is publicly available with the license of the RAIL family at: https://github.com/tiantiaf0627/voxlect.

cs.SD↗

arXiv2025

On the Relationship between Accent Strength and Articulatory Features

This paper explores the relationship between accent strength and articulatory features inferred from acoustic speech. To quantify accent strength, we compare phonetic transcriptions with transcriptions based on dictionary-based references, computing phoneme-level difference as a measure of accent strength. The proposed framework leverages recent self-supervised learning articulatory inversion techniques to estimate articulatory features. Analyzing a corpus of read speech from American and British English speakers, this study examines correlations between derived articulatory parameters and accent strength proxies, associating systematic articulatory differences with indexed accent strength. Results indicate that tongue positioning patterns distinguish the two dialects, with notable differences inter-dialects in rhotic and low back vowels. These findings contribute to automated accent analysis and articulatory modeling for speech processing applications.

eess.AS↗

arXiv2025

Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones

Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most consumer devices. Furthermore, most of the broad FM knowledge may actually be irrelevant for a specific task at hand. Here we explore a technique for mapping parameters of a large Transformer to parameters of a smaller specialized model. By making this transformation task-specific, we aim to capture a narrower scope of the knowledge needed for performing a specific task by a smaller model. We study our method on image modeling tasks, showing that performance of generated models exceeds that of universal conditional models.

cs.LG↗

arXiv2025

Contextually Guided Transformers via Low-Rank Adaptation

Large Language Models (LLMs) based on Transformers excel at text processing, but their reliance on prompts for specialized behavior introduces computational overhead. We propose a modification to a Transformer architecture that eliminates the need for explicit prompts by learning to encode context into the model's weights. Our Contextually Guided Transformer (CGT) model maintains a contextual summary at each sequence position, allowing it to update the weights on the fly based on the preceding context. This approach enables the model to self-specialize, effectively creating a tailored model for processing information following a given prefix. We demonstrate the effectiveness of our method on synthetic in-context learning tasks and language modeling benchmarks. Furthermore, we introduce techniques for enhancing the interpretability of the learned contextual representations, drawing connections to Variational Autoencoders and promoting smoother, more consistent context encoding. This work offers a novel direction for efficient and adaptable language modeling by integrating context directly into the model's architecture.

cs.LG↗

arXiv2025

Articulatory Feature Prediction from Surface EMG during Speech Production

We present a model for predicting articulatory features from surface electromyography (EMG) signals during speech production. The proposed model integrates convolutional layers and a Transformer block, followed by separate predictors for articulatory features. Our approach achieves a high prediction correlation of approximately 0.9 for most articulatory features. Furthermore, we demonstrate that these predicted articulatory features can be decoded into intelligible speech waveforms. To our knowledge, this is the first method to decode speech waveforms from surface EMG via articulatory features, offering a novel approach to EMG-based speech synthesis. Additionally, we analyze the relationship between EMG electrode placement and articulatory feature predictability, providing knowledge-driven insights for optimizing EMG electrode configurations. The source code and decoded speech samples are publicly available.

eess.AS↗

arXiv2025

Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition

Although many previous studies have carried out multimodal learning with real-time MRI data that captures the audio-visual kinematics of the vocal tract during speech, these studies have been limited by their reliance on multi-speaker corpora. This prevents such models from learning a detailed relationship between acoustics and articulation due to considerable cross-speaker variability. In this study, we develop unimodal audio and video models as well as multimodal models for phoneme recognition using a long-form single-speaker MRI corpus, with the goal of disentangling and interpreting the contributions of each modality. Audio and multimodal models show similar performance on different phonetic manner classes but diverge on places of articulation. Interpretation of the models' latent space shows similar encoding of the phonetic space across audio and multimodal models, while the models' attention weights highlight differences in acoustic and articulatory timing for certain phonemes.

cs.LG↗

arXiv2025

Enhancing Listened Speech Decoding from EEG via Parallel Phoneme Sequence Prediction

Brain-computer interfaces (BCI) offer numerous human-centered application possibilities, particularly affecting people with neurological disorders. Text or speech decoding from brain activities is a relevant domain that could augment the quality of life for people with impaired speech perception. We propose a novel approach to enhance listened speech decoding from electroencephalography (EEG) signals by utilizing an auxiliary phoneme predictor that simultaneously decodes textual phoneme sequences. The proposed model architecture consists of three main parts: EEG module, speech module, and phoneme predictor. The EEG module learns to properly represent EEG signals into EEG embeddings. The speech module generates speech waveforms from the EEG embeddings. The phoneme predictor outputs the decoded phoneme sequences in text modality. Our proposed approach allows users to obtain decoded listened speech from EEG signals in both modalities (speech waveforms and textual phoneme sequences) simultaneously, eliminating the need for a concatenated sequential pipeline for each modality. The proposed approach also outperforms previous methods in both modalities. The source code and speech samples are publicly available.

eess.AS↗

arXiv2024

Narrowing the Focus: Learned Optimizers for Pretrained Models

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of the training process. Learned optimizers have shown some initial promise, but are generally unsuccessful as a general optimization mechanism applicable to every problem. In this work we explore a different direction: instead of learning general optimizers, we instead specialize them to a specific training environment. We propose a novel optimizer technique that learns a layer-specific linear combination of update directions provided by a set of base optimizers, effectively adapting its strategy to the specific model and dataset. When evaluated on image classification tasks, this specialized optimizer significantly outperforms both traditional off-the-shelf methods such as Adam, as well as existing general learned optimizers. Moreover, it demonstrates robust generalization with respect to model initialization, evaluating on unseen datasets, and training durations beyond its meta-training horizon.

cs.LG↗

arXiv2024

Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL

This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks.

cs.AI↗

arXiv2024

ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning

This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based on these insights, we propose several research directions and motivations for using ARCLE, including MAML, GFlowNets, and World Models.

cs.AI↗

arXiv2024

Toward Fully-End-to-End Listened Speech Decoding from EEG Signals

Speech decoding from EEG signals is a challenging task, where brain activity is modeled to estimate salient characteristics of acoustic stimuli. We propose FESDE, a novel framework for Fully-End-to-end Speech Decoding from EEG signals. Our approach aims to directly reconstruct listened speech waveforms given EEG signals, where no intermediate acoustic feature processing step is required. The proposed method consists of an EEG module and a speech module along with a connector. The EEG module learns to better represent EEG signals, while the speech module generates speech waveforms from model representations. The connector learns to bridge the distributions of the latent spaces of EEG and speech. The proposed framework is both simple and efficient, by allowing single-step inference, and outperforms prior works on objective metrics. A fine-grained phoneme analysis is conducted to unveil model characteristics of speech decoding. The source code is available here: github.com/lee-jhwn/fesde.

eess.SP↗

arXiv2022

Into-TTS : Intonation Template Based Prosody Control System

Intonations play an important role in delivering the intention of a speaker. However, current end-to-end TTS systems often fail to model proper intonations. To alleviate this problem, we propose a novel, intuitive method to synthesize speech in different intonations using predefined intonation templates. Prior to TTS model training, speech data are grouped into intonation templates in an unsupervised manner. Two proposed modules are added to the end-to-end TTS framework: an intonation predictor and an intonation encoder. The intonation predictor recommends a suitable intonation template to the given text. The intonation encoder, attached to the text encoder output, synthesizes speech abiding the requested intonation template. Main contributions of our paper are: (a) an easy-to-use intonation control system covering a wide range of users; (b) better performance in wrapping speech in a requested intonation with improved objective and subjective evaluation; and (c) incorporating a pre-trained language model for intonation modelling. Audio samples are available at https://srtts.github.io/IntoTTS.

eess.AS↗

arXiv2022

An Empirical Study on L2 Accents of Cross-lingual Text-to-Speech Systems via Vowel Space

With the recent developments in cross-lingual Text-to-Speech (TTS) systems, L2 (second-language, or foreign) accent problems arise. Moreover, running a subjective evaluation for such cross-lingual TTS systems is troublesome. The vowel space analysis, which is often utilized to explore various aspects of language including L2 accents, is a great alternative analysis tool. In this study, we apply the vowel space analysis method to explore L2 accents of cross-lingual TTS systems. Through the vowel space analysis, we observe the three followings: a) a parallel architecture (Glow-TTS) is less L2-accented than an auto-regressive one (Tacotron); b) L2 accents are more dominant in non-shared vowels in a language pair; and c) L2 accents of cross-lingual TTS systems share some phenomena with those of human L2 learners. Our findings imply that it is necessary for TTS systems to handle each language pair differently, depending on their linguistic characteristics such as non-shared vowels. They also hint that we can further incorporate linguistics knowledge in developing cross-lingual TTS systems.

eess.AS↗