Singing voice synthesizing method, singing voice synthesizing device, program, recording medium, and robot apparatus

• US 7,183,482 B2
• Filed: 03/19/2004
• Issued: 02/27/2007
• Est. Priority Date: 03/20/2003
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Kobayashi, Kenichiro
• Primary Examiner(s): Donels, Jeffrey W
• Application Number:
  US10/548,280
• Publication Number:
  US 20060156909A1
• Time in Patent Office: 1,075 Days
• Field of Search: 846/45, 704/268
• US Class Current: 84/645
• CPC Class Codes: G10H 1/0066 using a MIDI interface
• CPC Class Codes: G10H 2230/055 Spint toy, i.e. specifically designed for children, e.g. adapted for smaller fingers or simplified in some way; Musical instrument-shaped game input interfaces with simplified control features
• CPC Class Codes: G10H 2250/455 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 formant synthesis G10H2250/481; parcor synthesis G10H2250/505; modulation effects G10H2210/195; ensemble effects G10H2210/245; speech synthesis in general G10L13/00
• CPC Class Codes: G10H 7/002 using a common processing for different operations or calculations, and a set of microinstructions (programme) to control the sequence thereof

Abstract

A singing voice synthesizing method synthesizes the singing voice by exploiting performance data, such as MIDI data. The input performance data are analyzed as the musical information including the pitch and the length of the sounds and the lyric (S2 and S3). If the musical information analyzed lacks in the lyric information, an arbitrary lyric is donated to an arbitrary string of notes (S9, S11, S12 and S15). The singing voice is generated based on the so donated lyric (S17).

Claims

1. A method for synthesizing the singing voice comprising

an analyzing step of analyzing performance data as a musical information of a pitch and a length of a sound and a lyric;

and

a lyric imparting step of imparting the lyric to a string of notes, based on the lyric information of the musical information analyzed, and imparting an optional lyric to an optional string of notes in the absence of the lyric information; and

a singing voice generating step of generating the singing voice based on the lyric imparted.

2. The method for synthesizing the singing voice according to claim 1 wherein

said performance data is performance data of a MIDI file.

3. The method for synthesizing the singing voice according to claim 1 wherein

said lyric imparting step imparts a predetermined lyric to an optional string of notes in the absence of designation of a particular lyric from outside.

4. The method for synthesizing the singing voice according to claim 2 wherein

said lyric imparting step imparts the lyric to a string of notes included in a track or a channel of said MIDI file.

5. The method for synthesizing the singing voice according to claim 4 wherein

said lyric imparting step arbitrarily selects said track or the channel.

6. The method for synthesizing the singing voice according to claim 4 wherein

said lyric imparting step imparts the lyric to a string of notes of a track or a channel appearing first in the performance data.

7. The method for synthesizing the singing voice according to claim 4 wherein

said lyric imparting step imparts an independent lyric to each of a plurality of the tracks or the channels.

8. The method for synthesizing the singing voice according to claim 2 wherein

said lyric imparting step stores the results of donation of the lyric.

9. The method for synthesizing the singing voice according to claim 2 further comprising

a speech inserting step of reading aloud a speech, by synthesized voice, in place of a lyric in question, at the timing of enunciation of said lyric in question, for introducing the speech into a song, in case the information indicating the speech is included in said lyric information.

10. An apparatus for synthesizing the singing voice comprising:

analyzing means for analyzing performance data as a musical information of a pitch and a length of a sound and a lyric;

lyric imparting means for imparting the lyric to a string of notes, based on the lyric information of the musical information analyzed, and imparting an optional lyric to an optional string of notes in the absence of the lyric information; and

singing voice generating means for generating the singing voice based on the lyric imparted.

11. The apparatus for synthesizing the singing voice according to claim 10 wherein

said performance data is performance data of a MIDI file.

12. The apparatus for synthesizing the singing voice according to claim 10 wherein

said lyric imparting means imparts a predetermined lyric to an optional string of notes in the absence of designation of a particular lyric from outside.

13. The apparatus for synthesizing the singing voice according to claim 11 wherein

said lyric imparting means imparts the lyric to a string of notes included in a track or a channel of said MIDI file.

14. The apparatus for synthesizing the singing voice according to claim 11 further comprising

speech inserting means for reading aloud a speech, by synthesized speech, in place of a lyric in question, at the timing of enunciation of the lyric in question, for introducing the speech into a song in case the information indicating the speech is included in said lyric information.

15. A computer-readable recording medium, having recorded thereon a program that when executed by a processor portion perform steps comprising:

an analyzing step of analyzing input performance data as a musical information of a pitch and a length of a sound and a lyric;

a lyric imparting step of imparting the lyric to a string of notes, based on the lyric information of the musical information analyzed, and imparting an optional lyric to an optional string of notes in the absence of the lyric information; and

a singing voice generating step of generating the singing voice based on the lyric imparted.

16. The recording medium according to claim 15 wherein said performance data is performance data of a MIDI file.

17. An autonomous robot apparatus comprising

analyzing means for analyzing performance data as a musical information of a pitch and a length of a sound and a lyric;

lyric imparting means for imparting the lyric to a string of notes, based on the lyric information of the musical information analyzed, and imparting an optional lyric to an optional string of notes in the absence of the lyric information; and

singing voice generating means for generating the singing voice based on the lyric imparted.

18. The robot apparatus according to claim 17 wherein said performance data is performance data of a MIDI file.