arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

多模态大模型

跨文本、图像、视频、音频等模态的大模型与学习方法。

2025-08-18 至 2025-08-18 共收录 4 信号源:cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 音频语音多模态 4 篇

2508.11362 2025-08-18 cs.SD eess.AS 79%

Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge

Honghong Wang, Yankai Wang, Dejun Zhang, Jing Deng, Rong Zheng

机构 * Beijing Fosafer Information Technology Co., Ltd.(北京福萨弗信息科技有限公司)

专题命中 音频语音多模态 :multimodal(title,abstract);分类 eess.AS

Comments 2 pages. pubilshed by ICASSP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11187 2025-08-18 eess.AS cs.CL cs.SD 62%

Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style

Wonjune Kang, Deb Roy

机构 * Massachusetts Institute of Technology(麻省理工学院)

专题命中 音频语音多模态 :cross-modal(abstract);分类 cs.CL、eess.AS

Comments Accepted to ASRU 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11255 2025-08-18 cs.CV 57%

FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

MengChao Wang, Qiang Wang, Fan Jiang, Mu Xu

机构 * Project Leader(项目负责人)

专题命中 音频语音多模态 :multimodal(abstract);分类 cs.CV

Comments https://fantasy-amap.github.io/fantasy-talking2/

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11074 2025-08-18 cs.SD cs.AI cs.CV eess.AS 56%

LD-LAudio-V1: Video-to-Long-Form-Audio Generation Extension with Dual Lightweight Adapters

Haomin Zhang, Kristin Qi, Shuxin Yang, Zihao Chen, Chaofan Ding, Xinhan Di

机构 * Giant Network, China(中国巨网) Computer Science, University of Massachusetts Boston(马萨诸塞大学波士顿分校计算机科学系)

专题命中 音频语音多模态 :分类 cs.CV、cs.AI、eess.AS;audio-visual(comments)

Comments Gen4AVC@ICCV: 1st Workshop on Generative AI for Audio-Visual Content Creation

详情

展开后加载摘要…

URL PDF HTML 收藏