首页> 外国专利> Method and Apparatus for Synthesizing/Modulating Singing Voice of Multiple Singers

Method and Apparatus for Synthesizing/Modulating Singing Voice of Multiple Singers

机译:用于合成/调制多个歌手歌声的方法和装置

摘要

Disclosed are an apparatus and method for synthesizing/modulating sung voices for a plurality of singers. This embodiment obtains a user request to designate a singer and a song, generates a tone and a singing style for the singer using an inference model based on a deep neural network, a formant with a tone adjusted, and a singing style with an adjusted tone Creates a high-pitched skeleton. Also, to provide a singing voice synthesis/modulation apparatus and method for generating a singing voice for a song from a pitch skeleton masked with a formant using a deep neural network-based SR transformation model.
机译:公开了一种用于合成/调制多个歌手的唱歌的装置和方法。 本实施例获得用户请求指定歌手和歌曲,使用基于深神经网络的推理模型来生成歌手的音调和歌曲风格,这是一种具有调整音调的素质,以及具有调整音调的歌曲风格 创造一个高倾斜的骨架。 此外,为了提供一种唱歌语音合成/调制装置和用于从使用深度神经网络的SR变换模型与塑造掩模的音调骨架的歌曲产生歌声的方法。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号