arXiv subjects

Ting Dang

Publications and source records attributed to Ting Dang.

At least 73 records · Page 4Linked to original sources

arXiv2025

Listening to the Mind: Earable Acoustic Sensing of Cognitive Load

Earable acoustic sensing offers a powerful and non-invasive modality for capturing fine-grained auditory and physiological signals directly from the ear canal, enabling continuous and context-aware monitoring of cognitive states. As earable devices become increasingly embedded in daily life, they provide a unique opportunity to sense mental effort and perceptual load in real time through auditory interactions. In this study, we present the first investigation of cognitive load inference through auditory perception using acoustic signals captured by off-the-shelf in-ear devices. We designed speech-based listening tasks to induce varying levels of cognitive load, while concurrently embedding acoustic stimuli to evoke Stimulus Frequency Otoacoustic Emission (SFOAEs) as a proxy for cochlear responsiveness. Statistical analysis revealed a significant association (p < 0.01) between increased cognitive load and changes in auditory sensitivity, with 63.2% of participants showing peak sensitivity at 3 kHz. Notably, sensitivity patterns also varied across demographic subgroups, suggesting opportunities for personalized sensing. Our findings demonstrate that earable acoustic sensing can support scalable, real-time cognitive load monitoring in natural settings, laying a foundation for future applications in augmented cognition, where everyday auditory technologies adapt to and support the users mental health.

cs.HC↗

arXiv2025

Menta: A Small Language Model for On-Device Mental Health Prediction

Mental health conditions affect hundreds of millions globally, yet early detection remains limited. While large language models (LLMs) have shown promise in mental health applications, their size and computational demands hinder practical deployment. Small language models (SLMs) offer a lightweight alternative, but their use for social media--based mental health prediction remains largely underexplored. In this study, we introduce Menta, the first optimized SLM fine-tuned specifically for multi-task mental health prediction from social media data. Menta is jointly trained across six classification tasks using a LoRA-based framework, a cross-dataset strategy, and a balanced accuracy--oriented loss. Evaluated against nine state-of-the-art SLM baselines, Menta achieves an average improvement of 15.2\% across tasks covering depression, stress, and suicidality compared with the best-performing non--fine-tuned SLMs. It also achieves higher accuracy on depression and stress classification tasks compared to 13B-parameter LLMs, while being approximately 3.25x smaller. Moreover, we demonstrate real-time, on-device deployment of Menta on an iPhone 15 Pro Max, requiring only approximately 3GB RAM. Supported by a comprehensive benchmark against existing SLMs and LLMs, Menta highlights the potential for scalable, privacy-preserving mental health monitoring. Code is available at: https://hong-labs.github.io/menta-project/

cs.AI↗

arXiv2025

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

Large Language Models (LLMs) have achieved state-of-the-art results across diverse domains, yet their development remains reliant on vast amounts of publicly available data, raising concerns about data scarcity and the lack of access to domain-specific, sensitive information. Federated Learning (FL) presents a compelling framework to address these challenges by enabling decentralized fine-tuning on pre-trained LLMs without sharing raw data. However, the compatibility and performance of pre-trained LLMs in FL settings remain largely under explored. We introduce the FlowerTune LLM Leaderboard, a first-of-its-kind benchmarking suite designed to evaluate federated fine-tuning of LLMs across four diverse domains: general NLP, finance, medical, and coding. Each domain includes federated instruction-tuning datasets and domain-specific evaluation metrics. Our results, obtained through a collaborative, open-source and community-driven approach, provide the first comprehensive comparison across 26 pre-trained LLMs with different aggregation and fine-tuning strategies under federated settings, offering actionable insights into model performance, resource constraints, and domain adaptation. This work lays the foundation for developing privacy-preserving, domain-specialized LLMs for real-world applications.

cs.CL↗

arXiv2025

Device-Guided Music Transfer

Device-guided music transfer adapts playback across unseen devices for users who lack them. Existing methods mainly focus on modifying the timbre, rhythm, harmony, or instrumentation to mimic genres or artists, overlooking the diverse hardware properties of the playback device (i.e., speaker). Therefore, we propose DeMT, which processes a speaker's frequency response curve as a line graph using a vision-language model to extract device embeddings. These embeddings then condition a hybrid transformer via feature-wise linear modulation. Fine-tuned on a self-collected dataset, DeMT enables effective speaker-style transfer and robust few-shot adaptation for unseen devices, supporting applications like device-style augmentation and quality enhancement.

cs.SD↗

arXiv2025

Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis

The limited availability of labeled brain network data makes it challenging to achieve accurate and interpretable psychiatric diagnoses. While self-supervised learning (SSL) offers a promising solution, existing methods often rely on augmentation strategies that can disrupt crucial structural semantics in brain graphs. To address this, we propose SAM-BG, a two-stage framework for learning brain graph representations with structural semantic preservation. In the pre-training stage, an edge masker is trained on a small labeled subset to capture key structural semantics. In the SSL stage, the extracted structural priors guide a structure-aware augmentation process, enabling the model to learn more semantically meaningful and robust representations. Experiments on two real-world psychiatric datasets demonstrate that SAM-BG outperforms state-of-the-art methods, particularly in small-labeled data settings, and uncovers clinically relevant connectivity patterns that enhance interpretability. Our code is available at https://github.com/mjliu99/SAM-BG.

cs.LG↗

arXiv2025

Position: Human-Robot Interaction in Embodied Intelligence Demands a Shift From Static Privacy Controls to Dynamic Learning

The reasoning capabilities of embodied agents introduce a critical, under-explored inferential privacy challenge, where the risk of an agent generate sensitive conclusions from ambient data. This capability creates a fundamental tension between an agent's utility and user privacy, rendering traditional static controls ineffective. To address this, this position paper proposes a framework that reframes privacy as a dynamic learning problem grounded in theory of Contextual Integrity (CI). Our approach enables agents to proactively learn and adapt to individual privacy norms through interaction, outlining a research agenda to develop embodied agents that are both capable and function as trustworthy safeguards of user privacy.

cs.HC↗

arXiv2025

MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation

Foundation models have become a promising paradigm for advancing medical image analysis, particularly for segmentation tasks where downstream applications often emerge sequentially. Existing fine-tuning strategies, however, remain limited: parallel fine-tuning isolates tasks and fails to exploit shared knowledge, while multi-task fine-tuning requires simultaneous access to all datasets and struggles with incremental task integration. To address these challenges, we propose MedSeqFT, a sequential fine-tuning framework that progressively adapts pre-trained models to new tasks while refining their representational capacity. MedSeqFT introduces two core components: (1) Maximum Data Similarity (MDS) selection, which identifies downstream samples most representative of the original pre-training distribution to preserve general knowledge, and (2) Knowledge and Generalization Retention Fine-Tuning (K&G RFT), a LoRA-based knowledge distillation scheme that balances task-specific adaptation with the retention of pre-trained knowledge. Extensive experiments on two multi-task datasets covering ten 3D segmentation tasks demonstrate that MedSeqFT consistently outperforms state-of-the-art fine-tuning strategies, yielding substantial performance gains (e.g., an average Dice improvement of 3.0%). Furthermore, evaluations on two unseen tasks (COVID-19-20 and Kidney) verify that MedSeqFT enhances transferability, particularly for tumor segmentation. Visual analyses of loss landscapes and parameter variations further highlight the robustness of MedSeqFT. These results establish sequential fine-tuning as an effective, knowledge-retentive paradigm for adapting foundation models to evolving clinical tasks. Code will be released.

cs.CV↗

arXiv2025

Data-Efficient Psychiatric Disorder Detection via Self-supervised Learning on Frequency-enhanced Brain Networks

Psychiatric disorders involve complex neural activity changes, with functional magnetic resonance imaging (fMRI) data serving as key diagnostic evidence. However, data scarcity and the diverse nature of fMRI information pose significant challenges. While graph-based self-supervised learning (SSL) methods have shown promise in brain network analysis, they primarily focus on time-domain representations, often overlooking the rich information embedded in the frequency domain. To overcome these limitations, we propose Frequency-Enhanced Network (FENet), a novel SSL framework specially designed for fMRI data that integrates time-domain and frequency-domain information to improve psychiatric disorder detection in small-sample datasets. FENet constructs multi-view brain networks based on the inherent properties of fMRI data, explicitly incorporating frequency information into the learning process of representation. Additionally, it employs domain-specific encoders to capture temporal-spectral characteristics, including an efficient frequency-domain encoder that highlights disease-relevant frequency features. Finally, FENet introduces a domain consistency-guided learning objective, which balances the utilization of diverse information and generates frequency-enhanced brain graph representations. Experiments on two real-world medical datasets demonstrate that FENet outperforms state-of-the-art methods while maintaining strong performance in minimal data conditions. Furthermore, we analyze the correlation between various frequency-domain features and psychiatric disorders, emphasizing the critical role of high-frequency information in disorder detection.

eess.IV↗

arXiv2025

Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal

Australian Aboriginal languages are of significant cultural and linguistic value but remain severely underrepresented in modern speech AI systems. While state-of-the-art speech foundation models and automatic speech recognition excel in high-resource settings, they often struggle to generalize to low-resource languages, especially those lacking clean, annotated speech data. In this work, we collect and clean a speech dataset for Dharawal, a low-resource Australian Aboriginal language, by carefully sourcing and processing publicly available recordings. Using this dataset, we analyze the speech similarity between Dharawal and 107 high-resource languages using a pre-trained multilingual speech encoder. Our approach combines (1) misclassification rate analysis to assess language confusability, and (2) fine-grained similarity measurements using cosine similarity and Fréchet Inception Distance (FID) in the embedding space. Experimental results reveal that Dharawal shares strong speech similarity with languages such as Latin, Māori, Korean, Thai, and Welsh. These findings offer practical guidance for future transfer learning and model adaptation efforts, and underscore the importance of data collection and embedding-based analysis in supporting speech technologies for endangered language communities.

eess.AS↗

arXiv2025

From Patient Burdens to User Agency: Designing for Real-Time Protection Support in Online Health Consultations

Online medical consultation platforms, while convenient, are undermined by significant privacy risks that erode user trust. We first conducted in-depth semi-structured interviews with 12 users to understand their perceptions of security and privacy landscapes on online medical consultation platforms, as well as their practices, challenges and expectation. Our analysis reveals a critical disconnect between users' desires for anonymity and control, and platform realities that offload the responsibility of ``privacy labor''. To bridge this gap, we present SafeShare, an interaction technique that leverages localized LLM to redact consultations in real-time. SafeShare balances utility and privacy through selectively anonymize private information. A technical evaluation of SafeShare's core PII detection module on 3 dataset demonstrates high efficacy, achieving 89.64\% accuracy with Qwen3-4B on IMCS21 dataset.

cs.HC↗

arXiv2025

Beyond Scale: Small Language Models are Comparable to GPT-4 in Mental Health Understanding

The emergence of Small Language Models (SLMs) as privacy-preserving alternatives for sensitive applications raises a fundamental question about their inherent understanding capabilities compared to Large Language Models (LLMs). This paper investigates the mental health understanding capabilities of current SLMs through systematic evaluation across diverse classification tasks. Employing zero-shot and few-shot learning paradigms, we benchmark their performance against established LLM baselines to elucidate their relative strengths and limitations in this critical domain. We assess five state-of-the-art SLMs (Phi-3, Phi-3.5, Qwen2.5, Llama-3.2, Gemma2) against three LLMs (GPT-4, FLAN-T5-XXL, Alpaca-7B) on six mental health understanding tasks. Our findings reveal that SLMs achieve mean performance within 2\% of LLMs on binary classification tasks (F1 scores of 0.64 vs 0.66 in zero-shot settings), demonstrating notable competence despite orders of magnitude fewer parameters. Both model categories experience similar degradation on multi-class severity tasks (a drop of over 30\%), suggesting that nuanced clinical understanding challenges transcend model scale. Few-shot prompting provides substantial improvements for SLMs (up to 14.6\%), while LLM gains are more variable. Our work highlights the potential of SLMs in mental health understanding, showing they can be effective privacy-preserving tools for analyzing sensitive online text data. In particular, their ability to quickly adapt and specialize with minimal data through few-shot learning positions them as promising candidates for scalable mental health screening tools.

cs.CL↗

arXiv2025

RawTFNet: A Lightweight CNN Architecture for Speech Anti-spoofing

Automatic speaker verification (ASV) systems are often affected by spoofing attacks. Recent transformer-based models have improved anti-spoofing performance by learning strong feature representations. However, these models usually need high computing power. To address this, we introduce RawTFNet, a lightweight CNN model designed for audio signals. The RawTFNet separates feature processing along time and frequency dimensions, which helps to capture the fine-grained details of synthetic speech. We tested RawTFNet on the ASVspoof 2021 LA and DF evaluation datasets. The results show that RawTFNet reaches comparable performance to that of the state-of-the-art models, while also using fewer computing resources. The code and models will be made publicly available.

eess.AS↗

arXiv2025

Token-Level Logits Matter: A Closer Look at Speech Foundation Models for Ambiguous Emotion Recognition

Emotional intelligence in conversational AI is crucial across domains like human-computer interaction. While numerous models have been developed, they often overlook the complexity and ambiguity inherent in human emotions. In the era of large speech foundation models (SFMs), understanding their capability in recognizing ambiguous emotions is essential for the development of next-generation emotion-aware models. This study examines the effectiveness of SFMs in ambiguous emotion recognition. We designed prompts for ambiguous emotion prediction and introduced two novel approaches to infer ambiguous emotion distributions: one analysing generated text responses and the other examining the internal processing of SFMs through token-level logits. Our findings suggest that while SFMs may not consistently generate accurate text responses for ambiguous emotions, they can interpret such emotions at the token level based on prior knowledge, demonstrating robustness across different prompts.

cs.SD↗

arXiv2025

MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation

Medical image reporting (MIR) aims to generate structured clinical descriptions from radiological images. Existing methods struggle with fine-grained feature extraction, multimodal alignment, and generalization across diverse imaging types, often relying on vanilla transformers and focusing primarily on chest X-rays. We propose MicarVLMoE, a vision-language mixture-of-experts model with gated cross-aligned fusion, designed to address these limitations. Our architecture includes: (i) a multiscale vision encoder (MSVE) for capturing anatomical details at varying resolutions, (ii) a multihead dual-branch latent attention (MDLA) module for vision-language alignment through latent bottleneck representations, and (iii) a modulated mixture-of-experts (MoE) decoder for adaptive expert specialization. We extend MIR to CT scans, retinal imaging, MRI scans, and gross pathology images, reporting state-of-the-art results on COVCTR, MMR, PGROSS, and ROCO datasets. Extensive experiments and ablations confirm improved clinical accuracy, cross-modal alignment, and model interpretability. Code is available at https://github.com/AI-14/micar-vl-moe.

cs.CV↗

arXiv2025

Scaling Auditory Cognition via Test-Time Compute in Audio Language Models

Large language models (LLMs) have shown exceptional versatility in natural language processing, prompting recent efforts to extend their multimodal capabilities to speech processing through the development of audio large language models (Audio LLMs). While Audio LLMs excel in tasks such as speech recognition and synthesis, it remains unclear how they perform when faced with the auditory cognitive challenges posed by real-world environments, such as audio comprehension and listening recall, particularly in the presence of background noise or overlapping speech. Unlike text-based LLMs, which have access to vast amounts of text data for pre-training, retraining Audio LLMs with diverse auditory cognitive scenes is difficult due to the limited datasets that simulate real-world auditory cognitive scenarios and the challenge of acquiring auditory cognitive labels for training. While test-time compute (TTC) methods have been shown to enhance the capabilities of text-based LLMs during inference, a key challenge lies in designing these TTC methods to improve the auditory capabilities of Audio LLMs. This study aims to address these two research gaps by: i) exploring the auditory cognitive capabilities of Audio LLMs, and ii) enhancing their capabilities using TTC approaches. We have investigated five different Audio LLMs for auditory cognition using a \textit{self-collected} database and have proposed five TTC approaches to enhance auditory cognitive capabilities during inference. Our findings reveal that Audio LLMs performance decreases in more challenging auditory cognitive tasks. The proposed TTC approaches significantly enhance cognitive auditory capabilities, advancing the development of more adaptable and resilient Audio LLMs for practical applications such as assistive listening devices, voice-based AI assistants, and communication technologies.

cs.SD↗

arXiv2025

AER-LLM: Ambiguity-aware Emotion Recognition Leveraging Large Language Models

Recent advancements in Large Language Models (LLMs) have demonstrated great success in many Natural Language Processing (NLP) tasks. In addition to their cognitive intelligence, exploring their capabilities in emotional intelligence is also crucial, as it enables more natural and empathetic conversational AI. Recent studies have shown LLMs' capability in recognizing emotions, but they often focus on single emotion labels and overlook the complex and ambiguous nature of human emotions. This study is the first to address this gap by exploring the potential of LLMs in recognizing ambiguous emotions, leveraging their strong generalization capabilities and in-context learning. We design zero-shot and few-shot prompting and incorporate past dialogue as context information for ambiguous emotion recognition. Experiments conducted using three datasets indicate significant potential for LLMs in recognizing ambiguous emotions, and highlight the substantial benefits of including context information. Furthermore, our findings indicate that LLMs demonstrate a high degree of effectiveness in recognizing less ambiguous emotions and exhibit potential for identifying more ambiguous emotions, paralleling human perceptual capabilities.

cs.CL↗

arXiv2024

StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal Contrast

Contrastive learning (CL) has emerged as a promising approach for representation learning in time series data by embedding similar pairs closely while distancing dissimilar ones. However, existing CL methods often introduce false negative pairs (FNPs) by neglecting inherent characteristics and then randomly selecting distinct segments as dissimilar pairs, leading to erroneous representation learning, reduced model performance, and overall inefficiency. To address these issues, we systematically define and categorize FNPs in time series into semantic false negative pairs and temporal false negative pairs for the first time: the former arising from overlooking similarities in label categories, which correlates with similarities in non-stationarity and the latter from neglecting temporal proximity. Moreover, we introduce StatioCL, a novel CL framework that captures non-stationarity and temporal dependency to mitigate both FNPs and rectify the inaccuracies in learned representations. By interpreting and differentiating non-stationary states, which reflect the correlation between trends or temporal dynamics with underlying data patterns, StatioCL effectively captures the semantic characteristics and eliminates semantic FNPs. Simultaneously, StatioCL establishes fine-grained similarity levels based on temporal dependencies to capture varying temporal proximity between segments and to mitigate temporal FNPs. Evaluated on real-world benchmark time series classification datasets, StatioCL demonstrates a substantial improvement over state-of-the-art CL methods, achieving a 2.9% increase in Recall and a 19.2% reduction in FNPs. Most importantly, StatioCL also shows enhanced data efficiency and robustness against label scarcity.

cs.LG↗

arXiv2024

A Joint Spectro-Temporal Relational Thinking Based Acoustic Modeling Framework

Relational thinking refers to the inherent ability of humans to form mental impressions about relations between sensory signals and prior knowledge, and subsequently incorporate them into their model of their world. Despite the crucial role relational thinking plays in human understanding of speech, it has yet to be leveraged in any artificial speech recognition systems. Recently, there have been some attempts to correct this oversight, but these have been limited to coarse utterance-level models that operate exclusively in the time domain. In an attempt to narrow the gap between artificial systems and human abilities, this paper presents a novel spectro-temporal relational thinking based acoustic modeling framework. Specifically, it first generates numerous probabilistic graphs to model the relationships among speech segments across both time and frequency domains. The relational information rooted in every pair of nodes within these graphs is then aggregated and embedded into latent representations that can be utilized by downstream tasks. Models built upon this framework outperform state-of-the-art systems with a 7.82\% improvement in phoneme recognition tasks over the TIMIT dataset. In-depth analyses further reveal that our proposed relational thinking modeling mainly improves the model's ability to recognize vowels, which are the most likely to be confused by phoneme recognizers.

eess.AS↗