June-Woo Kim

Ph.D. Candidate, MLC Lab

Department of Artificial Intelligence, Kyungpook National University
80, Daehak-ro, Buk-gu, Daegu, 41566, Korea

Email: kaen2891xkxkxk@knu.ac.kr / kaen2891xkxkxk@gmail.com
CV, Linkedin, Github

Welcome to my page! I am currently pursuing a Ph.D. at Kyungpook National University. While my main area of concentration has been in Speech Recognition, I have also delved into various other fields within AI such as NLP, Audio, Audio in Medical AI, and Video, with the aim of expanding my understanding and skills. Specifically, I am interested in creating an ASR system that ensures fair speech recognition performance regardless of the speaker's personal characteristics, as well as medical AI including respiratory sound classification, speech-based psychiatry analysis and depression detection. News

May. 2024: Starting a new position as Applied Scientist Intern at Amazon. I am now in UK!

Apr. 2024: I will attend ICASSP 2024 for my presentation. Let's get in touch in Seoul, Korea!.

Apr. 2024: A paper on 'Input-Agnostic Augmentation for Respiratory Sound Classification' accepted at EMBC 2024.

Jan. 2024: Starting a new position as Research Ph.D Internship at NAVER AI.

Dec. 2023: A paper on 'Cross-domain adaptation with Supervised Contrastive Learning on Respiratory Sound' accepted at ICASSP 2024.

Education

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

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 - Present

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

2024

	[P1] J.-W. Kim, M. Toikkanen, Y. Choi, S.-E. Moon^†, H.-Y. Jung^†. BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification. Preprint .
	[C5] J.-W. Kim, M. Toikkanen, S. Bae, M. Kim^†, H.-Y. Jung^†. RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2024.
	[C4] J.-W. Kim, S. Bae, W.-Y. Cho, B. Lee, H.-Y. 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] J.-W. Kim, C. Yoon, M. Toikkanen, S. Bae, H.-Y. 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] J.-W. Kim, H. Chung, H.-Y. Jung^†. Spectral Salt-and-Pepper Patch Masking for Self-Supervised Speech Representation Learning. Mathematics 2023. [webpage]
	[C3] S. Bae, J.-W. Kim, W. Cho, H. Baek, S. Son, B. Lee, C. Ha, K. Tae, S. Kim^†, S.-Y. 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] J.-W. Kim, H. Chung, H.-Y. Jung^†. Unsupervised Representation Learning with Task-Agnostic Feature Masking for Robust End-to-End Speech Recognition . Mathematics 2023. [webpage]

2022

[J4] J.-W. Kim, H. Yoon, H.-Y. Jung^†. Improved Spoken Language Representation for Intent Understanding in a Task-Oriented Dialogue System. Sensors 2022. [webpage]

2021

[J3] J.-W. Kim, H. Yoon, H.-Y. Jung^†. Linguistic-Coupled Age-to-Age Voice Translation to Improve Speech Recognition Performance in Real Environments. IEEE ACCESS 2021. [webpage]

2020

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

2018

[C1] M. Chae, T-H. Kim, Y.H. Shin, J.-W. Kim, S.-Y. 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 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