Changhan Oh, Kiyoung Park, Jeom Ja Kang, Woo-Yong Choi, Hwa Jeon Song. Improving Cross-Attention based on Positional Alignment during Inference for Robust Long-form Speech Recognition. In Odette Scharenborg, Catharine Oertel, Khiet Truong, editors, 26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025. ISCA, 2025. [doi]
Abstract is missing.