arXiv subjects

Hyun Ah Kim

Publications and source records attributed to Hyun Ah Kim.

3 recordsLinked to original sources

arXiv2024

MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling

In the mental health domain, Large Language Models (LLMs) offer promising new opportunities, though their inherent complexity and low controllability have raised questions about their suitability in clinical settings. We present MindfulDiary, a mobile journaling app incorporating an LLM to help psychiatric patients document daily experiences through conversation. Designed in collaboration with mental health professionals (MHPs), MindfulDiary takes a state-based approach to safely comply with the experts' guidelines while carrying on free-form conversations. Through a four-week field study involving 28 patients with major depressive disorder and five psychiatrists, we found that MindfulDiary supported patients in consistently enriching their daily records and helped psychiatrists better empathize with their patients through an understanding of their thoughts and daily contexts. Drawing on these findings, we discuss the implications of leveraging LLMs in the mental health domain, bridging the technical feasibility and their integration into clinical settings.

cs.HC↗

arXiv2020

ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers

Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services. Despite the advancement of ASR, however, most publicly available call-based speech corpora such as Switchboard are old-fashioned. Also, most existing call corpora are in English and mainly focus on open domain dialog or general scenarios such as audiobooks. Here we introduce a new large-scale Korean call-based speech corpus under a goal-oriented dialog scenario from more than 11,000 people, i.e., ClovaCall corpus. ClovaCall includes approximately 60,000 pairs of a short sentence and its corresponding spoken utterance in a restaurant reservation domain. We validate the effectiveness of our dataset with intensive experiments using two standard ASR models. Furthermore, we release our ClovaCall dataset and baseline source codes to be available via https://github.com/ClovaAI/ClovaCall.

cs.LG↗

arXiv1998

An atom optics experiment to investigate faster-than-light tunneling

We describe a series of atom optics experiments underway at Toronto for investigating tunnelling interaction times of various sorts. We begin by discussing some outstanding issues and confusions related to the question of whether or not superluminal tunnelling can be construed as true faster-than-light ``signal propagation,'' a question which we answer in the negative. We then argue that atom optics is an arena ideally suited for addressing a variety of remaining questions about how, where, and for how long a particle interacts with a tunnel barrier. We present recent results on a modified ``delta-kick cooling'' scheme which we have used to prepare Rubidium atoms with one-dimensional de Broglie wavelengths on the order of an optical wavelength, along with simulations showing that from these temperatures, we will be able to use acousto-optically modulated dipole-force barriers to velocity-select ultracold atom samples ideal for future tunnelling experiments.

quant-ph↗