arXiv每日推荐-3.4:语音/音频每日论文速递

同步公众号(arXiv每日学术速递)
【1】 SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks
标题:SELD-TCN:基于时间卷积网络的声音事件定位与检测
作者: Karim Guirguis, Bin Yang
备注:5 pages, 3 tables, 2 figures. Submitted to EUSIPCO 2020
链接:https://arxiv.org/abs/2003.01609

【2】 Unsupervised Interpretable Representation Learning for Singing Voice Separation
标题:歌唱声音分离的无监督可解释表示学习
作者: Stylianos I. Mimilakis, Gerald Schuller
链接:https://arxiv.org/abs/2003.01567

【3】 Voice Separation with an Unknown Number of Multiple Speakers
标题:具有未知数量的多个说话者的语音分离
作者: Eliya Nachmani, Lior Wolf
链接:https://arxiv.org/abs/2003.01531

【4】 Amateur Drones Detection: A machine learning approach utilizing the acoustic signals in the presence of strong interference
标题:业余无人机检测:一种在强干扰存在下利用声信号的机器学习方法
作者: Zahoor Uddin, Ali Kashif Bashir
备注:25 pages, 10 figures, accepted for the publication in future issue of “Computer Communications (2020)”
链接:https://arxiv.org/abs/2003.01519

【5】 Improving Uyghur ASR systems with decoders using morpheme-based language models
标题:使用基于语素的语言模型用解码器改进维吾尔语ASR系统
作者: Zicheng Qiu, Turghunjan Mamut
链接:https://arxiv.org/abs/2003.01509

【6】 The Effect of Silence Feature in Dimensional Speech Emotion Recognition
标题:无声特征在空间语音情感识别中的作用
作者: Bagus Tris Atmaja, Masato Akagi
链接:https://arxiv.org/abs/2003.01277

【7】 Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework
标题:神经分析-合成框架中声门脉冲位置的半监督学习
作者: Frederik Bous, Axel Roebel
链接:https://arxiv.org/abs/2003.01220

【8】 Multichannel Singing Voice Separation by Deep Neural Network Informed DOA Constrained CNMF
标题:基于深度神经网络信息DOA约束的CNMF多声道歌唱语音分离
作者: Antonio J. Muñoz-Montoro, Konstantinos Drossos
链接:https://arxiv.org/abs/2003.01162

【9】 Inferring the location of reflecting surfaces exploiting loudspeaker directivity
标题:利用扬声器指向性推断反射面的位置
作者: Vincenzo Zaccà, Richard Heusdens
备注:Submitted to EUSIPCO 2020
链接:https://arxiv.org/abs/2003.0111

原文链接:https://zhuanlan.zhihu.com/p/110764899

你可能感兴趣的:(语音识别,语音识别)