Related papers: INSURE-Dial: A Phase-Aware Conversational Dataset …
Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In particular, there are not…
The growing capabilities of large language models and multimodal systems have spurred interest in voice-first AI assistants, yet existing benchmarks are inadequate for evaluating the full range of these systems' capabilities. We introduce…
We present CallShield, the first caller identity authentication system that operates entirely at the audio layer, without relying on speech transcription, internet connectivity, or trusted infrastructure. CallShield introduces a real-time…
Incomplete or inconsistent discharge documentation is a primary driver of care fragmentation and avoidable readmissions. Despite its critical role in patient safety, auditing discharge summaries relies heavily on manual review and is…
Autonomous agents that address day-to-day digital tasks (e.g., ordering groceries for a household), must not only operate multiple apps (e.g., notes, messaging, shopping app) via APIs, but also generate rich code with complex control flow…
As AI coding agents evolve from autocomplete tools to autonomous "AI workforce" teammates, they introduce a critical new bottleneck: human maintainers must now manage complex interaction loops rather than just reviewing code. Analyzing…
Serious illness conversations (SICs) align care with patients' values, goals, and preferences, yet they rarely occur in emergency departments (EDs), where time constraints and emotional burden often leave clinicians making high-stakes…
Messaging patients is a critical part of healthcare communication, helping to improve things like medication adherence and healthy behaviors. However, traditional mobile message design has significant limitations due to its inability to…
The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…
Failure indexing is a longstanding crux in software testing and debugging, the goal of which is to automatically divide failures (e.g., failed test cases) into distinct groups according to the culprit root causes, as such multiple faults in…
Dialogue systems have been widely applied in many scenarios and are now more powerful and ubiquitous than ever before. With large neural models and massive available data, current dialogue systems have access to more knowledge than any…
Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for accurate human hand-off - particularly in domains that depend…
Ensuring accurate call prioritisation is essential for optimising the efficiency and responsiveness of mental health helplines. Currently, call operators rely entirely on the caller's statements to determine the priority of the calls. It…
Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tracking from electronic health records (EHRs). Existing systems typically rely on manually…
As generative AI enters enterprise workflows, ensuring compliance with legal, ethical, and reputational standards becomes a pressing challenge. In beauty tech, where biometric and personal data are central, traditional reviews are often…
Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…
Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods continue to suffer from residual interference in complex…
Voice-activated systems are integrated into a variety of desktop, mobile, and Internet-of-Things (IoT) devices. However, voice spoofing attacks, such as impersonation and replay attacks, in which malicious attackers synthesize the voice of…
The US federal government spends more than a trillion dollars per year on health care, largely provided by private third parties and reimbursed by the government. A major concern in this system is overbilling, waste and fraud by providers,…
While smart mobile health apps that adapt to users' progressive individual needs are proliferating, many of them struggle to fulfill their promises due to an inferior user experience. Understanding the concerns of real-world users related…