[4N3-GS-7] Vision, speech media processing:

Fri. May 30, 2025 2:00 PM - 3:40 PM Room N (Room 1009)

座長：品川政太朗（SB Intuitions）

2:00 PM - 2:20 PM

[4N3-GS-7-01] Error Correction for Japanese Speech Recognition by Combining N-best Hypotheses and Large Language Models

〇Kengo Fujii¹, Sonoyama Masashi¹, Takahashi Ichiro¹ (1. KONICA MINOLTA, INC.)

2:20 PM - 2:40 PM

〇Hikaru Suzuki¹, Tomoya Fujino¹, Yusuke Itani¹ (1. Mitsubishi Electric Corporation)

2:40 PM - 3:00 PM

〇Minami Hotta¹, Noriko Ogasawara¹, Kengo Miyajima¹, Ryotaro Shimizu¹, Masayuki Goto¹ (1. Waseda University)

3:00 PM - 3:20 PM

〇Koki Horikoshi¹, Gen Sato¹, Izumi Tsunokuni¹, Yusuke Ikeda¹ (1. Tokyo Denki University)

3:20 PM - 3:40 PM

〇Junichiro Fujii¹, Yukino Tsuzuki¹, Tomoyasu Nanaumi¹, Junichi Okubo¹ (1. Yachiyo Engineering Co., Ltd.)