Singing voice synthesizing apparatus, singing voice synthesizing method and program for synthesizing singing voice

• US 7,379,873 B2
• Filed: 07/03/2003
• Issued: 05/27/2008
• Est. Priority Date: 07/08/2002
• Status: Expired due to Fees

• Current Assignee: Yamaha Corporation
• Original Assignee: Yamaha Corporation
• Inventors: Kemmochi, Hideki
• Primary Examiner(s): Azad; Abul K.
• Application Number:
  US10/613,301
• Publication Number:
  US 20040006472A1
• Time in Patent Office: 1,790 Days
• Field of Search: None
• US Class Current: 704/269
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing

Abstract

Voice synthesis unit data stored in a phoneme database 10 is selected by a voice synthesis unit selector 12 in accordance with MIDI information stored in a performance data storage unit 11. Characteristic parameters are derived from the selected voice synthesis unit data. A characteristic parameter correction unit 21 corrects the characteristic parameters based on pitch information, etc. A spectrum envelope generating unit 23 generates a spectrum envelope in accordance with the corrected characteristic parameter. A timbre transformation unit 25 changes timbre by correcting the characteristic parameters in accordance with timbre transformation parameters in a time axis. Timbres in the same song position can be transformed into different arbitrary timbres respectively; therefore, the synthesized singing voice will be rich in variety and reality.

Claims

1. A singing voice synthesizing apparatus, comprising:

a singing voice information input device that inputs singing voice information for synthesizing a singing voice;

a phoneme database that stores voice synthesis unit data;

a selector that selects the voice synthesis unit data stored in the phoneme database in accordance with the singing voice information;

a timbre transformation parameter input device that inputs a timbre transformation parameter for transforming timbre, the timbre transformation parameter including a coefficient α

indicating whether a singing voice is made to be feminine or masculine;

a mapping function generator that generates, in accordance with the coefficient included in the timbre transformation parameter, a mapping function defined by a following equation (1)

fout =(fs/2) ×

(2×

fin /fs)^α

 

 

(1),

where fout is an output frequency, fs is a sampling frequency, fin is an input frequency and α

is the coefficient indicating whether the singing voice is made to be feminine or masculine; and

a singing voice synthesizer that generates a spectrum envelope based on the selected voice synthesis unit data, transforms the generated spectrum envelope in accordance with the mapping function generated by using a local peak frequency of the spectrum envelope as the input frequency, and generates a synthetic singing voice of which character is changed by using the transformed spectrum envelope.

2. A singing voice synthesizing apparatus according to claim 1, further including a characteristic parameter output device that derives a characteristic parameter from the voice synthesis unit data selected by the selector and outputs the derived characteristic parameter, and wherein the singing voice synthesizer corrects the characteristic parameter in accordance with the timbre transformation parameter.

3. A singing voice synthesizing apparatus according to claim 1, wherein the timbre transformation parameter input device includes a timbre transformation parameter adjuster that changes the timbre transformation parameter in a time axis.

4. A singing voice synthesizing method, comprising:

inputting singing voice information for synthesizing a singing voice;

storing voice synthesis unit data into a phoneme database in advance and selecting the voice synthesis unit data stored in the phoneme database in accordance with the singing voice information;

inputting a timbre transformation parameter for transforming a timbre, the timbre transformation parameter including a coefficient α

indicating whether a singing voice is made to be feminine or masculine;

generating, in accordance with the coefficient included in the timbre transformation parameter, a mapping function defined by a following equation (1)

fout =(fs/2)×

(2×

fin/fs)<sup>α

(</sup>1)

where fout is an output frequency, fs is a sampling frequency, fin is an input frequency, and α

is the coefficient indicating whether the singing voice is made to be feminine or masculine;

generating a spectrum envelope based on the selected voice synthesis unit data;

transforming the generated spectrum envelope in accordance with the mapping function generated by using a local peak frequency of the spectrum envelope as the input frequency; and

generating a synthetic singing voice of which character is changed by using the transformed spectrum envelope.

5. A computer-readable storage medium having encoded thereon a singing voice synthesizing program including instructions which when executed by a computer causes:

inputting singing voice information for synthesizing a singing voice;

storing voice synthesis unit data into a phoneme database in advance and selecting the voice synthesis unit data stored in the phoneme database in accordance with the singing voice information;

inputting a timbre transformation parameter for transforming timbre, the timbre transformation parameter including a coefficient α

indicating whether a singing voice is made to be feminine or masculine;

generating, in accordance with the coefficient included in the timbre transformation parameter, a mapping function defined by a following equation (1)

fout =(fs/2)×

(2×

fin/fs)<sup>α

(</sup>1)

where fout is an output frequency, fs is a sampling frequency, fin is an input frequency, and α

is the coefficient indicating whether the singing voice is made to be feminine or masculine;

generating a spectrum envelope based on the selected voice synthesis unit data;

transforming the generated spectrum envelope in accordance with the mapping function generated by using a local peak frequency of the spectrum envelope as the input frequency; and

generating a synthetic singing voice of which character is changed by using the transformed spectrum envelope.