Institution profile

Institute for Infocomm Research

Academic institutionasia · sg
Official website
Research library201linked papers
Opportunities0open roles
Selected work

Representative Papers

Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages

Jun 17, 2025

This study addresses the challenge of code-switching (CS) automatic speech recognition (ASR) for low-resource language pairs in Singapore—Malay–English, Mandarin–Malay, and Tamil–English—using monolingual data only. We propose a novel phrase-level natural-pattern CS data synthesis method that requires no authentic CS annotations. Leveraging this approach, we construct the first comprehensive CS-ASR benchmark covering Southeast Asian multilingual scenarios. By fine-tuning large pre-trained models—including Whisper, MMS, and SeamlessM4T—with our synthetic CS data and monolingual data augmentation, we achieve significant improvements in both CS and monolingual ASR performance, with the largest gains observed for Malay–English. Our work establishes a cost-effective, high-fidelity, purely synthetic-data-driven paradigm for low-resource CS-ASR, eliminating reliance on scarce and expensive annotated CS speech data.

1 citations1 influentialRead paper

Visual Prompting for One-shot Controllable Video Editing without Inversion

Apr 19, 2025

This paper addresses the challenge of propagating user edits applied solely to the first frame consistently across an entire video sequence while preserving both spatial content fidelity and temporal coherence—without requiring DDIM inversion. To this end, we propose One-shot Controllable Video Editing (OCVE), the first inversion-free framework driven by visual prompts. Our method introduces Content-Consistent Sampling (CCS) to enforce intra-frame semantic fidelity, and Temporal-Content Consistent Sampling (TCS), built upon Stein Variational Gradient Descent, to explicitly model inter-frame dynamic constraints. Extensive experiments demonstrate that OCVE significantly outperforms existing inversion-based approaches across multiple benchmarks, achieving state-of-the-art performance in editing accuracy, source-content consistency, and temporal coherence.

1 citationsRead paper

How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions

Sep 04, 2026

As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes critical. Humans possess moral agency, the capacity to make ethically guided decisions and bear responsibility for their consequences, a well-established construct in moral psychology. Yet as artificial agents (AAs) such as robots, drones, and disembodied AI systems become increasingly embedded in smart city environments, the question of whether and how moral agency is attributed to them takes on new urgency. This paper presents, to the best of our knowledge, the first empirical study comparing how humans and LLMs evaluate perceived moral agency (PMA) across human and autonomous artificial agents varying in embodiment, situated in plausible smart city scenarios. Using an adaptation of a validated PMA scale, we applied a protocol to 190 human participants as well as various LLMs. Our evaluation reveals higher perceptions of moral agency in humans than in AAs. However, when facing moral dilemmas in concrete scenarios, LLMs reason outward from the situation, prioritizing harm severity and contextual urgency over any stable assessment of the agent itself, amplifying a context-sensitivity also present in human raters. These findings are particularly relevant as LLMs become increasingly involved in everyday moral decisions.

0 citationsRead paper
Recent publications

Latest Papers

How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions

Sep 04, 2026

As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes critical. Humans possess moral agency, the capacity to make ethically guided decisions and bear responsibility for their consequences, a well-established construct in moral psychology. Yet as artificial agents (AAs) such as robots, drones, and disembodied AI systems become increasingly embedded in smart city environments, the question of whether and how moral agency is attributed to them takes on new urgency. This paper presents, to the best of our knowledge, the first empirical study comparing how humans and LLMs evaluate perceived moral agency (PMA) across human and autonomous artificial agents varying in embodiment, situated in plausible smart city scenarios. Using an adaptation of a validated PMA scale, we applied a protocol to 190 human participants as well as various LLMs. Our evaluation reveals higher perceptions of moral agency in humans than in AAs. However, when facing moral dilemmas in concrete scenarios, LLMs reason outward from the situation, prioritizing harm severity and contextual urgency over any stable assessment of the agent itself, amplifying a context-sensitivity also present in human raters. These findings are particularly relevant as LLMs become increasingly involved in everyday moral decisions.

0 citationsRead paper

Bitstream Action Recognition is Byte Modeling

Aug 16, 2026

This study addresses action recognition failures caused by bitstream corruption and the dependency on pixel-level decoding. We propose BRACE, a dual-branch byte modeling framework that achieves corruption-resistant recognition in the representation space through repair-free anchor alignment and unreliable anchor suppression mechanisms. Furthermore, we construct a realistic bitstream corruption simulator and introduce BAR, the first large-scale benchmark dataset for this domain. Experimental results demonstrate that BRACE significantly outperforms existing methods in robustness under bitstream corruption scenarios. These findings effectively validate the superiority of byte-level modeling and alignment strategies, establishing a novel paradigm for understanding corrupted videos without relying on traditional pixel reconstruction.

0 citationsRead paper