语音/音频处理学术速递[11.14]

【1】Proceedings of The third international workshop on eXplainable AI for the Arts (XAIxArts)
标题：第三届eXplainable AI for the Arts（XAIxArts）国际研讨会会议录
链接：https://arxiv.org/abs/2511.10482

【2】VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction
标题：VocalNet-M2：通过集成的多码本令牌化和多令牌预测推进低延迟口语建模
链接：https://arxiv.org/abs/2511.10232

【3】Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard
标题：对多模式LLM的语音音频合成攻击及其使用SALMONN-Guard的缓解
链接：https://arxiv.org/abs/2511.10222

【4】FabasedVC: Enhancing Voice Conversion with Text Modality Fusion and Phoneme-Level SSL Features
标题：FabasedVC：通过文本模式融合和音素级SSL功能增强语音转换
链接：https://arxiv.org/abs/2511.10112

【5】Audio-VLA: Adding Contact Audio Perception to Vision-Language-Action Model for Robotic Manipulation
标题：Audio-VLA：将接触式音频感知添加到机器人操纵的视觉-语言-动作模型中
链接：https://arxiv.org/abs/2511.09958

【6】HI-TransPA: Hearing Impairments Translation Personal Assistant
标题：HI-TransPA：听力障碍翻译私人助理
链接：https://arxiv.org/abs/2511.09915

【7】Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Models
标题：叛逆：音频推理模型的噪音稳健推理训练
链接：https://arxiv.org/abs/2511.09682

【8】Video Echoed in Music: Semantic, Temporal, and Rhythmic Alignment for Video-to-Music Generation
标题：音乐中的视频回响：视频到音乐生成的语义、时间和节奏对齐
链接：https://arxiv.org/abs/2511.09585

【9】WaveRoll: JavaScript Library for Comparative MIDI Piano-Roll Visualization
标题：WaveRoll：用于比较铅笔钢琴滚动可视化的JavaScript库
链接：https://arxiv.org/abs/2511.09562

【10】Investigation of Feature Selection and Pooling Methods for Environmental Sound Classification
标题：环境声分类的特征选择和合并方法研究
链接：https://arxiv.org/abs/2511.09802

【1】Direction-of-Arrival and Noise Covariance Matrix joint estimation for beamforming
标题：到达方向和噪音协方差矩阵联合估计用于射束
链接：https://arxiv.org/abs/2511.10639

【2】Music Flamingo: Scaling Music Understanding in Audio Language Models
标题：音乐火烈鸟：在音频语言模型中扩展音乐理解
链接：https://arxiv.org/abs/2511.10289

【3】A Study of Binaural Deep Beamforming With Interpretable Beampatterns Guided by Time-Varying RTF
标题：时变RTI引导的可解释束模式的双耳深射束形成研究
链接：https://arxiv.org/abs/2511.10168

【4】Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS
标题：基于流匹配的Zero-ShotTTC中说话人相似性的时间层自适应对齐
链接：https://arxiv.org/abs/2511.09995

【5】MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
标题：MTR-DuplexBench：全面评估高保真语音语言模型的多轮对话
链接：https://arxiv.org/abs/2511.10262