SLP-P35: Speech/Text Translation & Speech LLMs
Poster
Thu, 7 May, 09:00 - 11:00
Location: Poster Area 31
Session Type: Poster
Track: Speech and Language Processing [SL]
Click the to view the manuscript on IEEE Xplore Open Preview

SLP-P35.1: ATTENTION2PROBABILITY: ATTENTION-DRIVEN TERMINOLOGY PROBABILITY ESTIMATION FOR ROBUST SPEECH-TO-TEXT SYSTEM
Yangfan Du, Northeastern University, China; Jun Zhang, Bin Wang, Jin Qiu, Lu Huang, Bytedance, China; Yuan Ge, Xiaoqian Liu, Tong Xiao, Jingbo Zhu, Northeastern University, China

SLP-P35.2: Direct Simultaneous Translation Activation for Large Audio-Language Models
Pei Zhang, Tongyi Lab, Alibaba Group, China; Yiming Wang, Shanghai Jiao Tong University, China; Jialong Tang, Baosong Yang, Tongyi Lab, Alibaba Group, China; Rui Wang, Shanghai Jiao Tong University, China; Derek F. Wong, NLP2CT Lab, University of Macau, China; Fei Huang, Tongyi Lab, Alibaba Group, China

SLP-P35.3: DIRECT TRANSFER OF PROSODY IN SPEECH-TO-SPEECH TRANSLATION USING DISENTANGLED SPEECH TOKENS
Ismail Rasim Ulgen, Johns Hopkins University, United States of America; Nancy Liu, Najmeh Sadoughi, Abhishek Yanamandra, Abhinav Jain, Zhu Liu, Vimal Bhat, Amazon Prime Video, United States of America

SLP-P35.4: EDPOTRANS: ENHANCED DIRECT PREFERENCE OPTIMIZATION FOR MACHINE TRANSLATION BETWEEN LOW-RESOURCE LANGUAGE AND CHINESE WITH LIMITED MONOLINGUAL DATA
Lianxi Wang, Xuming Li, Yuting Su, Songxi Xu, Jiahuan Yang, Nankai Lin, Shengyi Jiang, Guangdong University of Foreign Studies, China

SLP-P35.5: JOINT AUTOREGRESSIVE MODELING OF MULTI-TALKER OVERLAPPED SPEECH RECOGNITION AND TRANSLATION
Tomohiro Tanaka, Ryo Masumura, Naoki Makishima, Mana Ihori, Naotaka Kawata, Shota Orihashi, Satoshi Suzuki, Taiga Yamane, NTT, Inc., Japan

SLP-P35.6: LIFT: A QUALITY-AWARE DATA SELECTION FRAMEWORK FOR LOW-RESOURCE MACHINE TRANSLATION
Lianxi Wang, Guandong University of Foreign Studies, China; Jiahuan Yang, Xuanqi Chen, Xuming Li, Guangdong University of Foreign Studies, China; Xiaotian Lin, The Hong Kong University of Science and Technology (Guangzhou), China

SLP-P35.7: MTP-S2UT: ENHANCING SPEECH-TO-SPEECH TRANSLATION QUALITY WITH MULTI-TOKEN PREDICTION
Jianjin Wang, Runsong Zhao, Xiaoqian Liu, Yuan Ge, Ziqiang Xu, Tong Xiao, Northeastern University, China, China; Shengxiang Gao, Zhengtao Yu, Kunming University of Science and Technology, China; Jingbo Zhu, Northeastern University, China, China

SLP-P35.8: NMGE: Nested Multi-Granularity Expert Groups for Complexity-Aware Routing in Multilingual Translation
Liangying Shao, Yangyang Liu, Heng Liu, Xiaohu Zhao, Hao Wang, Bo Zeng, Linlong Xu, Longyue Wang, Weihua Luo, Kaifu Zhang, Alibaba International Digital Commerce Group, China

SLP-P35.9: PROST-LLM: PROGRESSIVELY ENHANCING THE SPEECH-TO-SPEECH TRANSLATION CAPABILITY IN LLMS
Jing Xu, Jiaqi Wang, The Chinese University of Hong Kong, Hong Kong; Daxin Tan, Xiao Chen, Huawei, Hong Kong

SLP-P35.10: REVISITING DIRECT SPEECH-TO-TEXT TRANSLATION WITH SPEECH LLMS: BETTER SCALING THAN COT PROMPTING?
Oriol Pareras, Barcelona Supercomputing Center, Spain; Gerard I. Gállego, Federico Costa, Barcelona Supercomputing Center & Universitat Politècnica de Catalunya, Spain; Cristina España-Bonet, Barcelona Supercomputing Center & DFKI GmbH, Spain; Javier Hernando, Barcelona Supercomputing Center & Universitat Politècnica de Catalunya, Spain