Research on audio clue-based target speaker extraction (TSE) has focused on modeling mixtures and reference speech, achieving strong results in English due to abundant datasets. However, cross-lingual properties remain underexplored, as low-resource languages face challenges from limited annotated data and linguistic resources. To bridge this gap, we propose WHYV (Wanna Hear Your Voice), a cross-lingual TSE framework enabling zero-shot adaptation without fine-tuning. WHYV employs a frequency-modulated gating mechanism that dynamically adjusts the acoustic features of the target speaker, minimizing reliance on language-specific cues. Evaluations demonstrate state-of-the-art zero-shot performance: 13.8 dB (Libri2Mix mix-both), 18.1 dB (mix-clean), and 14.8 dB on Vietnamese data.
Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset
Manipal Institute of Technology(曼尼帕尔理工学院)
机器监听中的声音事件检测(SED)需要识别音频文件中的不同声音并识别音频中特定声音事件的开始和结束时间。SED可用于各种应用,例如音频监视、语音识别以及多媒体数据库中的数据的基于上下文的索引和检索。然而,在现实生活中,来自各种来源的音频很少没有任何干扰噪声或干扰。在本文中,我们测试的性能,你只听到一次(YOHO)算法对嘈杂的音频数据。受计算机视觉中You Only Look Once(YOLO)算法的启发,YOHO算法可以在音乐语音检测数据集、TUT声音事件和Urban-SED数据集等数据集上与各种最先进算法的性能相匹配,但推理时间更短。在本文中,我们探讨了YOHO算法的VOICe数据集上的性能,包含在不同的声音噪声比(SNR)的噪声的音频文件。YOHO可以超越或至少匹配VOICe数据集论文中报告的最佳性能SED算法,并在更短的时间内进行推断。
Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems
National Taiwan University(台湾大学);University of Southern California(南加州大学);University of Michigan(密歇根大学);NTU Artificial Intelligence Center of Research Excellence (NTU AI-CoRE)(台湾大学人工智能卓越研究中心)
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Columbia University(哥伦比亚大学);Washington University in St. Louis(圣路易斯华盛顿大学);New York University(纽约大学);Pennsylvania State University(宾夕法尼亚州立大学);Rutgers University(罗格斯大学)
A Chinese Heart Failure Status Speech Database with Universal and Personalised Classification
School of Information Science and Technology(信息科学与技术学院);Advanced Computing and Storage Laboratory, 2012 Laboratories(先进计算与存储实验室);Institute of High Performance Computing(高性能计算研究所)
EEG-Derived Voice Signature for Attended Speaker Detection
National University of Singapore(新加坡国立大学);University of New South Wales(新南威尔士大学);Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Kriston AI Lab(科斯顿人工智能实验室);University of Bremen(不来梅大学)