今日论文合集：cs.SD语音8篇，eess.AS音频处理3篇。


本文经arXiv每日学术速递授权转载

微信公众号：arXiv_Daily


cs.SD语音


【1】Spatial Audio Rendering for Real-Time Speech Translation in Virtual Meetings

标题：虚拟会议中实时语音翻译的空间音频渲染

作者：Margarita Geleta, Hong Sodoma, Hannes Gamper

备注：17 pages, 5 figures

链接：https://arxiv.org/pdf/2511.09525


【2】End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering

标题：长形式口语问答的端到端对比语音预训练模型

作者：Jiliang Hu, Zuchao Li, Baoyuan Qi, Liu Guoming, Ping Wang

备注：12 pages, 7 figures, accepted by AAAI 2026

链接：https://arxiv.org/pdf/2511.09282


【3】POTSA: A Cross-Lingual Speech Alignment Framework for Low Resource Speech-to-Text Translation

标题：POTSA：用于低资源语音到文本翻译的跨语言语音对齐框架

作者：Xuanchen Li, Chenrui Cui, Tianrui Wang, Meng Ge, Zikang Huang, Jin Li, Yizhou Peng, Longbiao Wang, Jianwu Dang, Nyima Tashi

备注：5 pages, 3 figures, submitted to ICASSP 2026

链接：https://arxiv.org/pdf/2511.09232


【4】Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music Generation

标题：迪夫-V2 M：一个具有显式节奏建模的分层条件扩散模型，用于视频到音乐生成

作者：Shulei Ji, Zihao Wang, Jiaxing Yu, Xiangyuan Yang, Shuyu Li, Songruoyao Wu, Kejun Zhang

备注：AAAI 2026

链接：https://arxiv.org/pdf/2511.09090


【5】Sound impact of simple viscoelastic damping changes due to aging and the role of the double bentside on soundboard tension in a 1755 Dulcken harpsichord

标题：由于老化而导致的简单粘弹衰减变化的声音影响以及1755年杜尔肯羽管键琴中双波纹边对音板张力的作用

作者：Rolf Bader, Niko Plath, Patrick Kontopidis

链接：https://arxiv.org/pdf/2511.09037


【6】Non-verbal Perception of Room Acoustics using Multi Dimensional Scaling Metho

标题：使用多维缩放方法对房间声学的非言语感知

作者：Leonie Böhlke, Tim Ziemer, Rolf Bader

链接：https://arxiv.org/pdf/2511.09029


【7】Chord-conditioned Melody and Bass Generation

标题：和弦条件旋律与低音生成

作者：Alexandra C Salem, Mohammad Shokri, Johanna Devaney

备注：To appear at NeurIPS 2025 Workshop on AI for Music (AI4Music)

链接：https://arxiv.org/pdf/2511.08755


【8】Robust Multi-modal Task-oriented Communications with Redundancy-aware Representations

标题：具有冗余感知表示的鲁棒多模态面向任务通信

作者：Jingwen Fu, Ming Xiao, Zhonghao Lyu, Mikael Skoglund, Celimuge Wu

链接：https://arxiv.org/pdf/2511.08642


eess.AS音频处理


【1】Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask

标题：使用基于块的注意力屏蔽为Conformer和基于LLM的ASB开发有效且高效的非自回归解码器

作者：Tianzi Wang, Xurong Xie, Zengrui Jin, Mengzhe Geng, Jiajun Deng, Zhaoqing Li, Shoukang Hu, Shujie Hu, Guinan Li, Mingyu Cui, Helen Meng, Xunying Liu

备注：Accepted by regular paper in the IEEE Transactions on Audio, Speech and Language Processing (TASLP)

链接：https://arxiv.org/pdf/2511.09084


【2】ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction

标题：ParaS 2S：为副语言感知的语音交互进行基准测试和调整口语模型

作者：Shu-wen Yang, Ming Tu, Andy T. Liu, Xinghua Qu, Hung-yi Lee, Lu Lu, Yuxuan Wang, Yonghui Wu

链接：https://arxiv.org/pdf/2511.08723


【3】Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music Generation

标题：迪夫-V2 M：一个具有显式节奏建模的分层条件扩散模型，用于视频到音乐生成

作者：Shulei Ji, Zihao Wang, Jiaxing Yu, Xiangyuan Yang, Shuyu Li, Songruoyao Wu, Kejun Zhang

备注：AAAI 2026

链接：https://arxiv.org/pdf/2511.09090


机器翻译由腾讯交互翻译提供，仅供参考