同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文。
cs.SD 方向,今日共计5篇
【1】 A hybrid parametric-deep learning approach for sound event localization and detection
标题:一种用于声音事件定位和检测的混合参数深度学习方法
作者: Andres Perez-Lopez, Xavier Serra
备注:5 pages, 5 figures, submitted to DCASE2019 Workshop
链接:https://arxiv.org/abs/1908.10133
【2】 Overview of Tasks and Investigation of Subjective Evaluation Methods in Environmental Sound Synthesis and Conversion
标题:环境声合成与转换中的任务概述及主观评价方法研究
作者: Yuki Okamoto, Yoichi Yamashita
链接:https://arxiv.org/abs/1908.10055
【3】 The Wiki Music dataset: A tool for computational analysis of popular music
标题:Wiki Music数据集:流行音乐的计算分析工具
作者: Fabio Celli
备注:Copyright 2019, Fabio Celli. 5 pages. Keywords: Popular Music, Computational Music analysis, Wikipedia, Natural Language Processing
链接:https://arxiv.org/abs/1908.10275
【4】 Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis
标题:文本到语音合成的可训练最大语音频率的神经谐波加噪声波形模型
作者: Xin Wang, Junichi Yamagishi
备注:Accepted by Speech Synthesis Workshop 2019
链接:https://arxiv.org/abs/1908.10256
【5】 VAE-based Domain Adaptation for Speaker Verification
标题:基于VAE的说话人验证领域适配
作者: Xueyi Wang, Dong Wang
链接:https://arxiv.org/abs/1908.10092
机器翻译,仅供参考
网友评论