Publications AITRICS' innovative research takes the lead in advancements in medical artificial intelligence. All AAAI ACL ACS Acute and Critical Care AISTATS arXiv BMJ Health & Care Informatics CHIL Computer Vision&Image Understanding Critical Care CVPR ECCV EMNLP ICASSP ICCV ICLR ICML IEEE IJCAI INTERSPEECH JCDD JMIR Journal Clinical Medicine MLHC NAACL NeurIPS SaTML Scientific Reports Sensors COLM EACL Title Content Search 6 ICASSP Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting ICASSP 2025 Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting Wooseok Han, Minki Kang, Changhun Kim, Eunho Yang Speaker-adaptive Text-to-Speech (TTS) synthesis has attracted considerable attention due to its broad range of applications, such as p... 5 ICASSP Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping ICASSP 2025 Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping Minki Kang, Wooseok Han, Eunho Yang Generating speech from a face image is crucial for developing virtual humans capable of interacting using their uniq... 4 ICASSP COMPACT AND DE-BIASED NEGATIVE INSTANCE EMBEDDING FOR MULTI-INSTANCE LEARNING ON WHOLE-SLIDE IMAGE CLASSIFICATION ICASSP 2024 COMPACT AND DE-BIASED NEGATIVE INSTANCE EMBEDDING FOR MULTI-INSTANCELEARNING ON WHOLE-SLIDE IMAGE CLASSIFICATION Joohyung Lee, Heejeong Nam, Kwanhyung Lee, Sangchul Hahn Whole-slide image (WSI) classification is a challenging task because 1) patches ... 3 ICASSP WeavSpeech: Data Augmentation Strategy For Automatic Speech Recognition Via Semantic-Aware Weaving ICASSP 2023 WeavSpeech: Data Augmentation Strategy For Automatic Speech Recognition Via Semantic-Aware Weaving Kyusung Seo, Joonhyung Park, Jaeyun Song and Eunho Yang A cut-and-paste type of data augmentation strategy has attracted considerable attention in the vision... 2 ICASSP Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models ICASSP 2023 Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models Minki Kang, Dongchan Min, Sung Ju Hwang There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in ne... 1 ICASSP Mutually-Constrained Monotonic Multihead Attention for Online ASR ICASSP 2021 Mutually-Constrained Monotonic Multihead Attention for Online ASR Jaeyun Song, Hajin Shim, Eunho Yang Despite the feature of real-time decoding, Monotonic Multihead Attention (MMA) shows comparable performance to the state-of-the-art offline methods ... 1
