咨询与建议

限定检索结果

文献类型

  • 2 篇 会议

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 2 篇 电气工程
    • 2 篇 计算机科学与技术...
  • 1 篇 理学
    • 1 篇 物理学
  • 1 篇 医学
    • 1 篇 临床医学

主题

  • 2 篇 parallel text-to...
  • 1 篇 emphasis control
  • 1 篇 lexical focus
  • 1 篇 prominence
  • 1 篇 prosody
  • 1 篇 multi-layer perc...
  • 1 篇 singing voice sy...

机构

  • 1 篇 yale univ new ha...
  • 1 篇 neosapience inc
  • 1 篇 apple cupertino ...

作者

  • 1 篇 raitio tuomo
  • 1 篇 seshadri shreyas
  • 1 篇 li jiangchuan
  • 1 篇 tae jaesung
  • 1 篇 castellani dan
  • 1 篇 lee younggun
  • 1 篇 kim hyeongju

语言

  • 2 篇 英文
检索条件"主题词=parallel text-to-speech"
2 条 记 录,以下是1-10 订阅
排序:
Emphasis control for parallel neural TTS  23
Emphasis control for parallel neural TTS
收藏 引用
Interspeech Conference
作者: Seshadri, Shreyas Raitio, Tuomo Castellani, Dan Li, Jiangchuan Apple Cupertino CA 95014 USA
Recent parallel neural text-to-speech (TTS) synthesis methods are able to generate speech with high fidelity while maintaining high performance. However, these systems often lack control over the output prosody, thus ... 详细信息
来源: 评论
MLP SINGER: TOWARDS RAPID parallel KOREAN SINGING VOICE SYNTHESIS  31
MLP SINGER: TOWARDS RAPID PARALLEL KOREAN SINGING VOICE SYNT...
收藏 引用
IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
作者: Tae, Jaesung Kim, Hyeongju Lee, Younggun Yale Univ New Haven CT 06520 USA Neosapience Inc Seoul South Korea
Recent developments in deep learning have significantly improved the quality of synthesized singing voice audio. However, prominent neural singing voice synthesis systems suffer from slow inference speed due to their ... 详细信息
来源: 评论