Publications & Patents
PUBLICATIONS
2024
[C13] Cross-Triggering Issue in Audio Event Detection and Mitigation [PDF]
Huy Phan, Byeonggeun Kim, Vu Nguyen, Andrew Bydlon, Qingiming Tang, Chieh-Chi Kao, and Chao Wang
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024
2023
[C12] Task-Agnostic Open-Set Prototype for Few-Shot Open-Set Recognition [PDF]
Byeonggeun Kim*, Jun-Tae Lee*, Kyuhong Shim, and Simyung Chang (* equal contribution)
IEEE International Conference on Image Processing (ICIP) 2023
[C11] Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data [PDF]
Seunghan Yang, Byeonggeun Kim, Kyuhong Shim and Simyung Chang
INTERSPEECH 2023 (Oral presentation)
[C10] Scalable Weight Reparametrization for Efficient Transfer Learning [PDF]
Byeonggeun Kim*, Jun-Tae Lee*, Seunghan Yang, and Simyung Chang (* equal contribution)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023 (Oral presentation)
[C9] TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation [PDF]
Hyesu Lim, Byeonggeun Kim, Jaegul Choo, Sungha Choi
International Conference on Learning Representations (ICLR) 2023
2022
[C8] Dummy Prototypical Networks for Few-shot Open-set Keyword Spotting [PDF]
Byeonggeun Kim, Seunghan Yang, Inseop Chung, Simyung Chang
INTERSPEECH 2022
[C7] Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification [PDF]
Byeonggeun Kim, Seunghan Yang, Jangho Kim, Hyunsin Park, Juntae Lee, Simyung Chang
INTERSPEECH 2022
[C6] Personalized Keyword Spotting through Multi-task Learning [PDF]
Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang
INTERSPEECH 2022 (Oral presentation)
2021
[C5] Broadcasted Residual Learning for Efficient Keyword Spotting [PDF] [code]
Byeonggeun Kim*, Simyung Chang*, Jinkyu Lee, Dooyong Sung (* equal contribution)
INTERSPEECH 2021
BCResNets
[C4] Domain Generalization on Efficient Acoustic Scene Classification Using Residual Normalization [PDF] [poster] [video]
Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang
Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE), 2021
[C3] QTI submission to DCASE 2021: Residual normalization for device imbalanced acoustic scene classification with efficient design [PDF] [results]
Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang
IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE challenge), 2021
1st place in DCASE-2021 challenge
2019
[C2] Orthogonality Constrained Multi-Head Attention For Keyword Spotting [PDF]
Mingu Lee, Jinkyu Lee, Hye Jin Jang, Byeonggeun Kim, Wonil Chang, Kyuwoong Hwang
IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019
[C1] Query-by-Example On-Device Keyword Spotting [PDF] [Qualcomm keyword speech dataset]
Byeonggeun Kim, Mingu Lee, Jinkyu Lee, Yeonseok Kim, Kyuwoong Hwang
IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019
GRANTED PATENTS
[P4] Systems and methods of image processing based on gaze detection [PDF]
Hyunsin Park, Juntae Lee, Simyung Chang, Byeonggeun Kim, Jaewon Choi, and Kyu Woong Hwang
U.S. Patent No. 11,798,204. 24 Oct. 2023.
[P3] On-device self training in two-stage wakeup system comprising a system on chip which operates in a reduced-activity mode [PDF]
Young Mo Kang, Sungrak Yun, Kyu Woong Hwang, Hye Jin Jang, Byeonggeun Kim
U.S. Patent No. 11,664,012. 30 May. 2023.
[P2] Activating speech recognition based on hand patterns detected using plurality of filters [PDF]
Sungrack Yun, Young Mo Kang, Hye Jin Jang, Byeonggeun Kim, Kyu Woong Hwang
U.S. Patent No. 11,437,031. 6 Sep. 2022.
[P1] Method and apparatus for activating speech recognition [PDF]
Byeonggeun Kim, Young Mo Kang, Sungrack Yun, Kyu Woong Hwang, Hye Jin Jang
U.S. Patent No. 11,205,433. 21 Dec. 2021.