同步公众号(arXiv每日学术速递)
【1】 Wavelet-based spatial audio framework
标题：基于小波的空间音频框架
作者： Davide Scaini
链接：https://arxiv.org/abs/2003.03287
【2】 A Neural Network Based Framework for Archetypical Sound SYnthesis
标题：基于神经网络的原型声音合成框架
作者： Eric Guizzo, Alberto Novello
链接：https://arxiv.org/abs/2003.03160
【3】 Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
标题：资源不足语言中用于多语言代码交换语音的ASR系统的半监督开发
作者： Astik Biswas, Thomas Niesler
链接：https://arxiv.org/abs/2003.03135
【4】 Defense against adversarial attacks on spoofing countermeasures of ASV
标题：ASV欺骗对抗攻击防御对策
作者： Haibin Wu, Hung-yi Lee
备注：Accepted by ICASSP 2020
链接：https://arxiv.org/abs/2003.03065
【5】 End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification
标题：端到端神经离散化：将说话人离散化重构为简单的多标签分类
作者： Yusuke Fujita, Kenji Nagamatsu
备注：Submission to IEEE TASLP. This article draws from our previous conference papers: arxiv:1909.06247 and arxiv:1909.05952
链接：https://arxiv.org/abs/2003.02966
【6】 Tatistical Context-Dependent Units Boundary Correction for Corpus-based Unit-Selection Text-to-Speech
标题：基于语料库的单元选择文本到语音的统计上下文相关单元边界校正
作者： Claudio Zito, Piero Cosi
备注：isbn:978-88-7870-619-4
链接：https://arxiv.org/abs/2003.02837
【7】 Guided Generative Adversarial Neural Network for Representation Learning and High Fidelity Audio Generation using Fewer Labelled Audio Data
标题：用于表示学习和使用较少标记音频数据的高保真音频生成的引导生成对抗神经网络
作者： Kazi Nazmul Haque, Björn Schuller
链接：https://arxiv.org/abs/2003.0283
