Publications and granted patents.

^* Equal contribution. Links open the publisher, paper, or project page.

• Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qingming Tang, Ankur Gandhe, Hung-yi Lee, Chieh-Chi Kao, Chao Wang INTERSPEECH 2026 (Oral) · mentored internship
  arXiv
• Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation Kuan-Po Huang, Bo-Ru Lu, Byeonggeun Kim, Mihee Lee, Zalan Fabian, Renard Korzeniowski, Qingming Tang, Greg Ver Steeg, Hung-yi Lee, Chieh-Chi Kao, Chao Wang arXiv preprint, 2026 · mentored internship
  arXiv

• Amazon Nova 2: Multimodal reasoning and generation models Amazon Artificial General Intelligence Amazon Technical Report, 2025
  tech report
• Unlocking Transfer Learning for Open-World Few-Shot Recognition Byeonggeun Kim^*, Jun-Tae Lee^*, Kyuhong Shim, Simyung Chang NeurIPS 2025 — Reliable ML Workshop
  arXiv
• Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction Shu-wen Yang, Byeonggeun Kim^*, Kuan-Po Huang^*, Qingming Tang, Huy Phan, Bo-Ru Lu, Harshavardhan Sundar, Shalini Ghosh, Hung-yi Lee, Chieh-Chi Kao, Chao Wang ICML 2025 · primary research mentor
  amazon science
• IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling Kuan-Po Huang, Shu-wen Yang, Huy Phan, Bo-Ru Lu, Byeonggeun Kim, Sashank Macha, Qingming Tang, Shalini Ghosh, Hung-yi Lee, Chieh-Chi Kao, Chao Wang ICML 2025 · mentored internship
  amazon science
• Effective Techniques for Scaling Audio Encoder Pretraining Byeonggeun Kim^*, Andrew Bydlon^*, Qingming Tang, Huy Phan, Chieh-Chi Kao, Tao Zhang, Chao Wang ICASSP 2025 (Oral)
  amazon science

• Cross-Triggering Issue in Audio Event Detection and Mitigation Huy Phan, Byeonggeun Kim, Vu Nguyen, Andrew Bydlon, Qingming Tang, Chieh-Chi Kao, Chao Wang ICASSP 2024
  amazon science

• Task-Agnostic Open-Set Prototype for Few-Shot Open-Set Recognition Byeonggeun Kim^*, Jun-Tae Lee^*, Kyuhong Shim, Simyung Chang ICIP 2023
  paper
• Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data Seunghan Yang, Byeonggeun Kim, Kyuhong Shim, Simyung Chang INTERSPEECH 2023 (Oral)
  arXiv
• Scalable Weight Reparametrization for Efficient Transfer Learning Byeonggeun Kim^*, Jun-Tae Lee^*, Seunghan Yang, Simyung Chang ICASSP 2023 (Oral)
  arXiv
• TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation Hyesu Lim, Byeonggeun Kim, Jaegul Choo, Sungha Choi ICLR 2023 · mentored internship
  OpenReview

• Dummy Prototypical Networks for Few-shot Open-set Keyword Spotting Byeonggeun Kim, Seunghan Yang, Inseop Chung, Simyung Chang INTERSPEECH 2022
  arXiv
• Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification Byeonggeun Kim, Seunghan Yang, Jangho Kim, Hyunsin Park, Juntae Lee, Simyung Chang INTERSPEECH 2022
  arXiv DCASE results
• Personalized Keyword Spotting through Multi-task Learning Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang INTERSPEECH 2022 (Oral)
  arXiv

• Broadcasted Residual Learning for Efficient Keyword Spotting (BCResNets) Byeonggeun Kim^*, Simyung Chang^*, Jinkyu Lee, Dooyong Sung INTERSPEECH 2021
  arXiv code
• Domain Generalization on Efficient Acoustic Scene Classification Using Residual Normalization Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang DCASE 2021 Workshop
  workshop paper official results
• QTI submission to DCASE 2021: Residual normalization for device imbalanced acoustic scene classification with efficient design Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang DCASE Challenge 2021 — 1st place winner
  official results technical report workshop paper INTERSPEECH extension

• Orthogonality Constrained Multi-Head Attention For Keyword Spotting Mingu Lee, Jinkyu Lee, Hye Jin Jang, Byeonggeun Kim, Wonil Chang, Kyuwoong Hwang IEEE ASRU 2019
  arXiv
• Query-by-Example On-Device Keyword Spotting Byeonggeun Kim, Mingu Lee, Jinkyu Lee, Yeonseok Kim, Kyuwoong Hwang IEEE ASRU 2019
  arXiv dataset

• Acoustic event detection Quoc Huy Phan, Byeonggeun Kim, Andrew Thomas Bydlon, Qingming Tang, Chieh-Chi Kao, Chao Wang, Tien Vu Nguyen US 12,646,502 · 2 Jun 2026
  patent certificate inventor award
• Multi-task learning for personalized keyword spotting Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang US 12,347,439 · 1 Jul 2025
  patent
• Relaxed instance frequency normalization for neural-network-based audio processing Byeonggeun Kim, Seunghan Yang, Hyunsin Park, Juntae Lee, Simyung Chang US 12,266,379 · 1 Apr 2025
  patent
• Target Keyword Selection Wonil Chang, Jinseok Lee, Mingu Lee, Jinkyu Lee, Byeonggeun Kim, Dooyong Sung, Jaewon Choi, Kyu Woong Hwang US 12,039,968 · 16 Jul 2024
  patent
• Task Agnostic Open-set Prototypes for Few-shot Open-set Recognition Byeonggeun Kim, Juntae Lee, Simyung Chang US 12,019,641 · 25 Jun 2024
  patent
• Systems and methods of image processing based on gaze detection Hyunsin Park, Juntae Lee, Simyung Chang, Byeonggeun Kim, Jaewon Choi, Kyu Woong Hwang US 11,798,204 · 24 Oct 2023
  patent
• On-device self training in two-stage wakeup system Young Mo Kang, Sungrack Yun, Kyu Woong Hwang, Hye Jin Jang, Byeonggeun Kim US 11,664,012 · 30 May 2023
  patent
• Activating speech recognition based on hand patterns detected using plurality of filters Sungrack Yun, Young Mo Kang, Hye Jin Jang, Byeonggeun Kim, Kyu Woong Hwang US 11,437,031 · 6 Sep 2022
  patent
• Method and apparatus for activating speech recognition Byeonggeun Kim, Young Mo Kang, Sungrack Yun, Kyu Woong Hwang, Hye Jin Jang US 11,205,433 · 21 Dec 2021
  patent