Singing voice synthesis method and singing voice synthesis system

Patent metadata

Field	Value
Publication number	US-2020105244-A1
Application number	US-201816622387-A
Country	US
Kind code	A1
Filing date	Jun 14, 2018
Priority date	Jun 14, 2017
Publication date	Apr 2, 2020
Grant date	—

Abstract

Disclosed are a singing voice synthesis method and a singing voice synthesis system. The singing voice synthesis method includes: detecting a trigger for singing voice synthesis; reading out parameters according to a user who has input the trigger from a table in which parameters used for singing voice synthesis are recorded in association with the user; and synthesizing a singing voice by using the read-out parameters. The singing voice synthesis system includes: a detecting unit that detects a trigger for singing voice synthesis; a reading unit that reads out parameters according to a user who has input the trigger from a table in which parameters used for singing voice synthesis are recorded in association with the user; and a synthesizing unit that synthesizes a singing voice by using the read-out parameters.

First claim

What is claimed is:

1 . A singing voice synthesis method comprising:
detecting a trigger for singing voice synthesis; reading out parameters according to a user who has input the trigger from a table in which parameters used for singing voice synthesis are recorded in association with the user; and synthesizing a singing voice by using the read-out parameters.

2 . The singing voice synthesis method according to claim 1 , wherein,
in the table, the parameters used for singing voice synthesis are recorded in association with the user and emotions, the singing voice synthesis method has estimating an emotion of the user who has input the trigger, and, in the reading out the parameters from the table, parameters according to the user who has input the trigger and the emotion of the user are read out.

3 . The singing voice synthesis method according to claim 2 , wherein,
in the estimating the emotion of the user, a voice of the user is analyzed and the emotion of the user is estimated based on a result of the analysis.

4 . The singing voice synthesis method according to claim 3 , wherein
the estimating the emotion of the user includes at least processing of estimating an emotion based on contents of the voice of the user or processing of estimating an emotion based on a pitch, a volume, or a change in speed regarding the voice of the user.

5 . The singing voice synthesis method according to claim 1 , further comprising:
acquiring lyrics used for the singing voice synthesis; acquiring a melody used for the singing voice synthesis; and correcting one of the lyrics and the melody based on another.

6 . The singing voice synthesis method according to claim 1 , further comprising:
selecting one database according to the trigger from a plurality of databases in which voice fragments acquired from a plurality of singers are recorded, wherein, in the synthesizing the singing voice, the singing voice is synthesized by using voice fragments recorded in the one database.

7 . The singing voice synthesis method according to claim 1 , further comprising:
selecting a plurality of databases according to the trigger from a plurality of databases in which voice fragments acquired from a plurality of singers are recorded, wherein, in the synthesizing the singing voice, the singing voice is synthesized by using voice fragments obtained by combining a plurality of voice fragments recorded in the plurality of databases.

8 . The singing voice synthesis method according to claim 1 , wherein,
in the table, lyrics used for the singing voice synthesis are recorded in association with the user, and, in the synthesizing the singing voice, the singing voice is synthesized by using the lyrics recorded in the table.

9 . The singing voice synthesis method according to claim 1 , further comprising:
acquiring lyrics from one source selected from a plurality of sources according to the trigger, wherein, in the synthesizing the singing voice, the singing voice is synthesized by using the lyrics acquired from the selected one source.

10 . The singing voice synthesis method according to claim 1 , further comprising:
generating an accompaniment corresponding to the synthesized singing voice; and synchronizing and outputting the synthesized singing voice and the generated accompaniment.

11 . A singing voice synthesis system comprising:
a detecting unit that detects a trigger for singing voice synthesis; a reading unit that reads out parameters according to a user who has input the trigger from a table in which parameters used for singing voice synthesis are recorded in association with the user; and a synthesizing unit that synthesizes a singing voice by using the read-out parameters.

12 . The singing voice synthesis system according to claim 11 , wherein,
in the table, the parameters used for singing voice synthesis are recorded in association with the user and emotions, the singing voice synthesis system has an estimating unit that estimates emotion of the user who has input the trigger, and the reading unit reads out parameters according to the user who has input the trigger and the emotion of the user.

13 . The singing voice synthesis system according to claim 12 , wherein
the estimating unit analyzes a voice of the user and estimates the emotion of the user based on a result of the analysis.

14 . The singing voice synthesis system according to claim 13 , wherein
the estimating unit executes at least processing of estimating an emotion based on contents of the voice of the user or processing of estimating an emotion based on a pitch, a volume, or a change in speed regarding the voice of the user.

15 . The singing voice synthesis system according to claim 11 , further comprising:
a first acquiring unit that acquires lyrics used for the singing voice synthesis; a second acquiring unit that acquires a melody used for the singing voice synthesis; and a correcting unit that corrects one of the lyrics and the melody based on another.

16 . The singing voice synthesis system according to claim 11 , further comprising:
a selecting unit that selects one database according to the trigger from a plurality of databases in which voice fragments acquired from a plurality of singers are recorded, wherein the synthesizing unit synthesizes the singing voice by using voice fragments recorded in the one database.

17 . The singing voice synthesis system according to claim 11 , further comprising:
a selecting unit that selects a plurality of databases according to the trigger from a plurality of databases in which voice fragments acquired from a plurality of singers are recorded, wherein the synthesizing unit synthesizes the singing voice by using voice fragments obtained by combining a plurality of voice fragments recorded in the plurality of databases.

18 . The singing voice synthesis system according to claim 11 , wherein,
in the table, lyrics used for the singing voice synthesis are recorded in association with the user, and the synthesizing unit synthesizes the singing voice by using the lyrics recorded in the table.

19 . The singing voice synthesis system according to claim 15 , wherein
the first acquiring unit acquires lyrics from one source selected from a plurality of sources according to the trigger, wherein the synthesizing unit synthesizes the singing voice by using the lyrics acquired from the selected one source.

20 . The singing voice synthesis system according to claim 11 , further comprising:
a generating unit that generates an accompaniment corresponding to the synthesized singing voice; a synchronizing unit that synchronizes the synthesized singing voice and the generated accompaniment; and an outputting unit that outputs the accompaniment.

Assignees

• Yamaha Corp

Inventors

• Kuramitsu Daiki
• NARA Shoko
• Miyaki Tsuyoshi
• Shiihara Hiromasa
• Yamauchi Kenichi
• Yamanaka Susumu

Classifications

• G10H2210/576

  Chord progression · CPC title

• G10H1/361

  Recording/reproducing of accompaniment for use with an external source, e.g. karaoke systems · CPC title

• G10H2220/011

  Lyrics displays, e.g. for karaoke applications · CPC title

• G10H2250/455

  Gensound singing voices, i.e. generation of human voices for musical applications, vocal singing sounds or intelligible words at a desired pitch or with desired vocal effects, e.g. by phoneme synthesis · CPC title

• G10H2240/131

  Library retrieval, i.e. searching a database or selecting a specific musical piece, segment, pattern, rule or parameter set · CPC title