首页> 外国专利> SOUND SIGNAL SYNTHESIS METHOD, GENERATIVE MODEL TRAINING METHOD, SOUND SIGNAL SYNTHESIS SYSTEM, AND PROGRAM

SOUND SIGNAL SYNTHESIS METHOD, GENERATIVE MODEL TRAINING METHOD, SOUND SIGNAL SYNTHESIS SYSTEM, AND PROGRAM

机译:声音信号合成方法,生成模型训练方法,声信号合成系统和程序

摘要

A computer-implemented sound signal synthesis method generates control data including pitch notation data indicative of a pitch name corresponding to a pitch of a sound signal to be synthesized and octave data indicative of an octave of the pitch of the sound signal; and estimates output data indicative of the sound signal by inputting the generated control data into a generative model that has learned a relationship between control data including pitch notation data indicative of a pitch name corresponding to a pitch of a reference signal to be synthesized and octave data indicative of an octave of the pitch of the reference signal and output data indicative of the reference signal.
机译:计算机实现的声音信号合成方法生成控制数据,该控制数据包括指示与要合成的声音信号的间距对应的音调名称,该节距名称被合成和倍频程数据指示声音信号的音调的八度音程; 并通过将生成的控制数据输入到生成模型中,估计指示声音信号的输出数据,该生成模型已经学习了控制数据之间的关系,包括指示与要合成的参考信号的音高的音高名称的音调符号的节奏数据 表示参考信号的音高的速度和指示参考信号的输出数据。

著录项

  • 公开/公告号EP3929913A1

    专利类型

  • 公开/公告日2021-12-29

    原文格式PDF

  • 申请/专利权人 YAMAHA CORPORATION;

    申请/专利号EP20200758584

  • 发明设计人 NISHIMURA MASANARI;

    申请日2020-02-18

  • 分类号G10L13;G10H7/08;

  • 国家 EP

  • 入库时间 2022-08-24 23:05:34

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