公开(公告)号：US11437016B2

公开(公告)日：2022-09-06

申请号：US17119371

申请日：2020-12-11

申请人： Yamaha Corporation

发明人： Makoto Tachibana ,  Motoki Ogasawara

IPC分类号： G06F3/16 ,  G10L13/033 ,  G10L13/027

摘要： An information processing method is realized by a computer, and includes setting a pronunciation style with regard to a specific range on a time axis, arranging one or more notes in accordance with an instruction from a user within the specific range for which the pronunciation style has been set, and generating a characteristic transition, which is a transition of acoustic characteristics of voice that pronounces the one or more notes within the specific range in the pronunciation style set for the specific range.

公开(公告)号：US09355628B2

公开(公告)日：2016-05-31

申请号：US14455652

申请日：2014-08-08

申请人： Yamaha Corporation

发明人： Makoto Tachibana

IPC分类号： G10H1/06 ,  G10H7/00 ,  G10H1/36 ,  G10H7/02 ,  G10L13/033 ,  G10L13/00 ,  G10L13/06 ,  G10L13/10

CPC分类号： G10H1/361 ,  G10H7/00 ,  G10H7/008 ,  G10H7/02 ,  G10H2210/00 ,  G10H2210/051 ,  G10H2210/066 ,  G10H2210/091 ,  G10H2210/095 ,  G10H2210/325 ,  G10H2210/331 ,  G10H2220/155 ,  G10H2240/121 ,  G10H2250/455 ,  G10L13/00 ,  G10L13/0335 ,  G10L13/06 ,  G10L13/10

摘要： A voice analysis method includes a variable extraction step of generating a time series of a relative pitch. The relative pitch is a difference between a pitch generated from music track data, which continuously fluctuates on a time axis, and a pitch of a reference voice. The music track data designate respective notes of a music track in time series. The reference voice is a voice obtained by singing the music track. The pitch of the reference voice is processed by an interpolation processing for a voiceless section from which no pitch is detected. The voice analysis method also includes a characteristics analysis step of generating singing characteristics data that define a model for expressing the time series of the relative pitch generated in the variable extraction step.

摘要翻译： 语音分析方法包括产生相对间距的时间序列的可变提取步骤。 相对间距是由时间轴上连续波动的音轨数据产生的音高与参考声音的音高之间的差。 音乐轨道数据以时间序列指定音乐轨道的各个音符。 参考声音是通过唱歌音乐获得的声音。 参考语音的音调通过对其没有检测到音调的清音部分的内插处理进行处理。 语音分析方法还包括：特征分析步骤，生成规定用于表示在可变提取步骤中生成的相对间距的时间序列的模型的歌唱特征数据。

公开(公告)号：US09818396B2

公开(公告)日：2017-11-14

申请号：US15215882

申请日：2016-07-21

申请人： Yamaha Corporation

发明人： Makoto Tachibana ,  Masafumi Yoshida

IPC分类号： G10L13/00 ,  G10L13/033 ,  G10L13/08

CPC分类号： G10L13/0335 ,  G10H2210/066 ,  G10H2220/116 ,  G10H2220/126 ,  G10H2240/145 ,  G10H2250/455 ,  G10L2013/083

摘要： A singing voice synthesis data editing method includes adding, to singing voice synthesis data, a piece of virtual note data placed immediately before a piece of note data having no contiguous preceding piece of note data, the singing voice synthesis data including: multiple pieces of note data for specifying a duration and a pitch at which each note that is in a time series, representative of a melody to be sung, is voiced; multiple pieces of lyric data associated with at least one of the multiple pieces of note data; and a sequence of sound control data that directs sound control over a singing voice synthesized from the multiple pieces of lyric data, and obtaining the sound control data that directs sound control over the singing voice synthesized from the multiple pieces of lyric data, and that is associated with the piece of virtual note data.