June-Woo Kim

Postdoctoral Research Fellow, Ph.D.

Email: kaen2891@gmail.com
CV, Linkedin, Github

Welcome to my page! I am a Postdoctoral Research Fellow at Wonkwang University Hospital. My primary research focus lies in Speech Recognition and Audio in Medical AI, but I have also explored various AI domains, including LLMs, audio, and video, with the aim of expanding my understanding and skills. I am particularly interested in Medical AI, including psychiatry analysis and mental health detection, respiratory sound classification, and developing an ASR system that ensures fair and unbiased speech recognition performance regardless of the speaker's personal characteristics. I'd love to explore potential collaboration with you. Please feel free to reach out to me via email if you're interested. News

Feb. 2025: A journal paper on 'Adaptive Metadata-Guided Contrastive Learning' accepted at IEEE JBHI 2025 (IF 6.7).

Dec. 2024: A paper on 'Call-for-Help Keyword Spotting' accepted at ICASSP 2025.

Dec. 2024: I passed my PhD defense and I will be graduating with my PhD February 2025!

Jul. 2024: A journal paper on 'DL-based Quantitative Analysis of Exosomes from Cancers' accepted at Sensors and Actuators B: Chemical 2024 (IF 8.0).

Jun. 2024: A journal paper on 'Military Audio Dataset for Situational Awareness and Surveillance' accepted at Scientific Data 2024 (IF 9.8).

Education

Ph.D. in Department of Artificial Intelligence, Kyungpook National University. Advised by Prof. Ho-Young Jung. Feb. 2025

M.S. in Department of Artificial Intelligence, Kyungpook National University. Advised by Prof. Minho Lee. Feb. 2021

B.S. in Department of Information and Communication Convergence Engineering, Mokwon University. Feb. 2017

Work Experience

Applied Scientist Intern at Amazon; Improving Alexa shopping customers' ASR performance using synthetic speech based on TTS. Advised by Federica Cerina and Dhruv Agarwal. May - Sep 2024

Research Ph.D internship at NAVER AI; Improving speech recognition performance in doctor-patient conversations utilizing speaker verification model, improving respiratory sound classification using prompted metadata as text description, psychiatry voice analysis. Advised by Seong-Eun Moon. Jan - Apr 2024

Publications Google Scholar *: 1st co-authors, ^†: corresponding authors, C: conferences, J: journals, W: workshops, P: preprints

2025

	[P6] Miika Toikkanen, June-Woo Kim^†. Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles. Preprint.
	[P5] June-Woo Kim, Wonkyo Oh, Haram Yoon, Sung-Hoon Yoon, Dae-Jin Kim, Dong-Ho Lee, Sang-Yeol Lee, Chan-Mo Yang^†. Language-Agnostic Suicidal Risk Detection Using Large Language Models. Preprint.
	[P4] June-Woo Kim, Haram Yoon, Wonkyo Oh, Dawoon Jung, Sung-Hoon Yoon, Dae-Jin Kim, Dong-Ho Lee, Sang-Yeol Lee, Chan-Mo Yang^†. Domain Adversarial Training for Mitigating Gender Bias in Speech-based Mental Health Detection. Preprint.
	[P3] June-Woo Kim, Sanghoon Lee, Miika Toikkanen, Daehwan Hwang, Kyunghoon Kim^†. Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosis. Preprint.
	[J8] June-Woo Kim, Miika Toikkanen, Amin Jalali, Minseok Kim, Hye-Ji Han, Hyunwoo Kim, Wonwoo Shin, Ho-Young Jung^†, Kyunghoon Kim^†. Adaptive Metadata-Guided Supervised Contrastive Learning for Domain Adaptation on Respiratory Sound Classification. IEEE Journal of Biomedical and Health Informatics, To be appeared (JBHI) 2025. [webpage]
	[C7] Myeonghoon Ryu^†, June-Woo Kim^†, Minseok Oh, Suji Lee, Han Park. Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025.
	[P2] June-Woo Kim, Dhruv Agarwal^†, Federica Cerina. Understanding Frechet Speech Distance for Synthetic Speech Quality Evaluation. Preprint

2024

	[P1] June-Woo Kim, Haram Yoon, Bung-Nyun Kim, Sang-Yeol Lee, Dae-Jin Kim, Seong-Eun Moon, Yera Choi^†, Chan-Mo Yang^†. Deep Learning Analysis of Voice Biomarkers for Treatment Response in Adolescent MDD. Preprint
	[J7] Dong-Uk Han, Subin Park, June-Woo Kim, Chan-Hyeong Lee, Ju-Hyun Bae, Ho-Young Jung, Moon-Chang Baek^†, Young Ki Han^†. Multiplexed Detection Platform Implemented with Magnetic Encoding and Deep Learning-based Decoding for Quantitative Analysis of Exosomes from Cancers. Sensors and Actuators B: Chemical 2024. [webpage]
	[J6] June-Woo Kim, Chihyeon Yoon, Ho-Young Jung^†. A Military Audio Dataset for Situational Awareness and Surveillance. Scientific Data 2024. [code] [webpage]
	[C6] June-Woo Kim, Miika Toikkanen, Yera Choi, Seong-Eun Moon^†, Ho-Young Jung^†. BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification. Conference of the International Speech Communication Association (INTERSPEECH) 2024. [pdf] [code]
	[C5] June-Woo Kim, Miika Toikkanen, Sangmin Bae, Minseok Kim^†, Ho-Young Jung^†. RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2024. [pdf]
	[C4] June-Woo Kim, Sangmin Bae, Won-Yang Cho, Byungjo Lee, Ho-Young Jung^†. Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024. [pdf] [code]

2023

	[W1] June-Woo Kim, C. Yoon, M. Toikkanen, S. Bae, Ho-Young Jung^†. Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance. Neural Information Processing Systems Workshop on Deep Generative Models for Health (NeurIPSW) 2023. [webpage] [demo]
	[J6] June-Woo Kim, Hoon Chung, Ho-Young Jung^†. Spectral Salt-and-Pepper Patch Masking for Self-Supervised Speech Representation Learning. Mathematics 2023. [webpage]
	[C3] Sangmin Bae, June-Woo Kim, Won-Yang Cho, Hyerim Baek, Soyoun Son, Byungjo Lee, Changwan Ha, Kyongpil Tae, Sungnyun Kim^†, Se-Young Yun^†. Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification. Conference of the International Speech Communication Association (INTERSPEECH) 2023. [pdf] [code]
	[J5] June-Woo Kim, Hoon Chung, Ho-Young Jung^†. Unsupervised Representation Learning with Task-Agnostic Feature Masking for Robust End-to-End Speech Recognition . Mathematics 2023. [webpage]

2022

[J4] June-Woo Kim, Hyekyung Yoon, Ho-Young Jung^†. Improved Spoken Language Representation for Intent Understanding in a Task-Oriented Dialogue System. Sensors 2022. [webpage]

2021

[J3] June-Woo Kim, Hyekyung Yoon, Ho-Young Jung^†. Linguistic-Coupled Age-to-Age Voice Translation to Improve Speech Recognition Performance in Real Environments. IEEE ACCESS 2021. [webpage]

2020

	[J2] June-Woo Kim, Ho-Young Jung^†. End-to-End Speech Recognition Models using Limited Training Data. Phonetics and Speech Sciences 2020. [webpage]
	[J1] June-Woo Kim, Ho-Young Jung^†. Voice-to-voice Conversion using Transformer Network. Phonetics and Speech Sciences 2020. [webpage]
	[C2] June-Woo Kim, Ho-Young Jung, Minho Lee^†. Vocoder-free End-to-End Voice Conversion with Transformer Network. International Joint Conference on Neural Networks (IJCNN) 2020. [pdf] [webpage] [demo]

2018

[C1] Myungsu Chae, Tae-Ho Kim, Younghoon Shin, June-Woo Kim, Soo-Young Lee^†. End-to-End Multimodal Emotion and Gender Recognition with Dynamic Weights of Joint Loss. International Conference on Intelligent Robots and Systmes Workshop (IROSW) 2018. [pdf] [code]

Projects

[ETRI] AI-based Broadcasting Media Editing for Content Analysis Simulator. Project Manager. 2023

[ETRI] Unsupervised Speech Representation Learning for Robust Speech Recognition Performance. Project Manager. 2021-Present

[IITP] Innovative Prediction Intelligence Technology using Multimodal Information. 2021-Present

[ADD] Context Awareness-based Automatic Report Generation. 2021-2023

Services

Research Collaboration with School of Medicine, Wonkwang University. 2024-Present

Research Collaboration with Department of Pediatrics, Seoul National University College of Medicine. 2023-Present

Research Collaboration with MODULABS. 2022-Present

AI Researcher at KAIST AI (KI4AI), advised by Prof.Soo-Young LEE 2017-2018

Awards and Honors

4th place from Human Understanding AI Paper Contest in ETRI. 2023

Grand Prize from KNU Graduate Student Paper Contest in KNU. 2022

7th place from Korean Speech Recognition AI Contest in Korea Ministry of Science and Technology Information and Communication. 2022

5th place from Human Understanding AI Paper Contest in ETRI. 2022

Grand Prize from English Children Speech Recognition Hackathon Competition in National Information Society Agency (NIA). 2021

Grand Prize from Korean Children Speech Recognition Hackathon Competition in National Information Society Agency (NIA). 2021

First Prize (2th place) from ETRI AI Practice Tech Day 2021 in ETRI. 2021

Bronze Prize (7th place) from the National Institute of Korean AI-Language Proficiency Assessment Contest. 2021

Grand Prize from ETRI AI Practice Tech Day 2020 in ETRI. 2020

Excellent Researcher Award at KAIST Institute Awards in KAIST. 2018