VOICE QUALITY EDIT DEVICE AND VOICE QUALITY EDIT METHOD

• US 20100250257A1
• Filed: 06/04/2008
• Published: 09/30/2010
• Est. Priority Date: 06/06/2007
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Hirose, Yoshifumi, Kamai, Takahiro
• Granted Patent: US 8,155,964 B2
• Time in Patent Office: Days
• US Class Current: 704/278
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management

Abstract

This invention includes: a voice quality feature database (101) holding voice quality features; a speaker attribute database (106) holding, for each voice quality feature, an identifier enabling a user to expect a voice quality of the voice quality feature; a weight setting unit (103) setting a weight for each acoustic feature of a voice quality; a scaling unit (105) calculating display coordinates of each voice quality feature based on the acoustic features in the voice quality feature and the weights set by the weight setting unit (103); a display unit (107) displaying the identifier of each voice quality feature on the calculated display coordinates; a position input unit (108) receiving designated coordinates; and a voice quality mix unit (110) (i) calculating a distance between (1) the received designated coordinates and (2) the display coordinates of each of a part or all of the voice quality features, and (ii) mixing the acoustic features of the part or all of the voice quality features together based on a ratio between the calculated distances in order to generate a new voice quality feature.

Claims

1. A voice quality edit device that generates a new voice quality feature by editing a part or all of voice quality features each consisting of acoustic features regarding a corresponding voice quality, said voice quality edit device comprising:

a voice quality feature database holding the voice quality features;

a speaker attribute database holding, for each of the voice quality features held in said voice quality feature database, an identifier enabling a user to expect a voice quality of a corresponding voice quality feature;

a weight setting unit configured to set a weight for each of the acoustic features of a corresponding voice quality;

a display coordinate calculation unit configured to calculate display coordinates of each of the voice quality features held in said voice quality feature database, based on (i) the acoustic features of a corresponding voice quality feature and (ii) the weights set for the acoustic features by said weight setting unit;

a display unit configured to display, for each of the voice quality features held in said voice quality feature database, the identifier held in said speaker attribute database on the display coordinates calculated by said display coordinate calculation unit;

a position input unit configured to receive designated coordinates; and

a voice quality mix unit configured to (i) calculate a distance between (1) the designated coordinates received by said position input unit and (2) the display coordinates of each of a part or all of the voice quality features held in said voice quality feature database, and (ii) mix the acoustic features of the part or all of the voice quality features together based on a ratio between the calculated distances in order to generate a new voice quality feature.

2. The voice quality edit device according to claim 1,

wherein said speaker attribute database holds, for each of the voice quality features held in said voice quality feature database, (i) at least one of a face image, a portrait, and a name of a speaker of a voice having the voice quality of the corresponding voice quality feature, or (ii) at least one of an image and a name of a character uttering a voice having the voice quality of the corresponding voice quality feature, and

said display unit is configured to display on the display coordinates calculated by said display coordinate calculation unit, for each of the voice quality features held in said voice quality feature database, (i) the at least one of the face image, the portrait, and the name of the speaker or (ii) the at least one of the image and the name of the character, which are held in said speaker attribute database.

3. The voice quality edit device according to claim 1,

wherein said display coordinate calculation unit includes:

an inter-voice-quality distance calculation unit configured to (i) extract an arbitrary pair of voice quality features from the voice quality features held in said voice quality feature database, (ii) weight the acoustic features of each of the voice quality features in the extracted arbitrary pair, using the respective weights set by said weight setting unit, and (iii) calculate a distance between the voice quality features in the extracted arbitrary pair after the weighting; and

a scaling unit configured to calculate plural sets of the display coordinates of the voice quality features held in said voice quality feature database based on the distances calculated by said inter-voice-quality distance calculation unit using a plurality of the arbitrary pairs, and

said display unit is configured to display, for each of the voice quality features held in said voice quality feature database, the identifier held in said speaker attribute database on a corresponding set of the display coordinates in the plural sets calculated by said scaling unit.

4. The voice quality edit device according to claim 1,

wherein said weight setting unit includes:

a weight storage unit configured to hold pieces of weight information each consisting of a plurality of the weights each set for a corresponding acoustic feature in the acoustic features regarding a corresponding voice quality;

a weight designation unit configured to designate a piece of weight information; and

a weight selection unit configured to select from said weight storage unit the piece of weight information designated by said weight designation unit, in order to set the weights each set for the corresponding acoustic feature.

5. The voice quality edit device according to claim 1,

wherein said weight setting unit includes:

a representative voice quality storage unit configured to hold at least two voice quality features which are previously selected from the voice quality features held in said voice quality feature database;

a voice quality presentation unit configured to present the user with the at least two voice quality features held in said representative voice quality storage unit;

a voice quality feature pair input unit configured to receive a designated pair of voice quality features chosen from the at least two voice quality features presented by said voice quality presentation unit; and

a weight calculation unit configured to calculate the weights for the acoustic features so that a distance regarding the display coordinates between the designated pair received by said voice quality feature pair input unit is minimized.

6. The voice quality edit device according to claim 1,

wherein said weight setting unit includes:

a subjective expression presentation unit configured to present a subjective expression for each of the acoustic features of a corresponding voice quality;

an importance degree input unit configured to receive an important degree designated for each of the subjective expressions presented by said subjective expression presentation unit; and

a weight calculation unit configured to calculate the weight for each of the acoustic features by deciding the weight based on the designated important degree received by said importance degree input unit so that the weight is decided heavier when the importance degree is higher.

7. The voice quality edit device according to claim 1, further comprising

a user information management database holding identification information of a voice quality feature of a voice quality which the user knows,

wherein said display unit is configured to display, for each of the voice quality features which are held in said voice quality feature database and have respective pieces of the identification information held in said user information management database, the identifier held in said speaker attribute database on the display coordinates calculated by said display coordinate calculation unit.

8. The voice quality edit device according to claim 1, further comprising:

an individual characteristic input unit configured to receive a designated sex or age of the user; and

a user information management database holding, for each sex or age of users, identification information of a voice quality feature of a voice quality which is supposed to be known by the users,

wherein said display unit is configured to display, for each of the voice quality features which are held in said voice quality feature database and have respective pieces of identification information held in said user information management database and associated with the designated sex or age received by said individual characteristic input unit, the identifier held in said speaker attribute database on the display coordinates calculated by said display coordinate calculation unit.

12. The voice quality edit device according to claim 1,

wherein said display coordinate calculation unit is configured to calculate the display coordinates of each of the voice quality features held in said voice quality feature database, so that a plurality of the voice quality features which are more similar having the acoustic features set with the weights heavier by said weight setting unit are displayed to be arranged closer to each other.

9. A voice quality edit method of generating a new voice quality feature by editing a part or all of voice quality features each consisting of acoustic features regarding a corresponding voice quality using a voice quality edit device,

the voice quality edit device including:

a voice quality feature database holding the voice quality features; and

a speaker attribute database holding, for each of the voice quality features held in the voice quality feature database, an identifier enabling a user to expect a voice quality of a corresponding voice quality feature,

said voice quality edit method comprising;

setting a weight for each of the acoustic features of a corresponding voice quality;

calculating display coordinates of each of the voice quality features held in the voice quality feature database, based on (i) the acoustic features of a corresponding voice quality feature and (ii) the weights set for the acoustic features in said setting;

displaying, for each of the voice quality features held in the voice quality feature database, the identifier held in the speaker attribute database on a corresponding set of the display coordinates in the plural sets generated in said calculating in a display device;

receiving designated coordinates; and

(i) calculating a distance between (1) the designated coordinates received in said receiving and (2) the display coordinates of each of a part or all of the voice quality features held in the voice quality feature database, and (ii) mixing the acoustic features of the part or all of the voice quality features together based on a ratio between the calculated distances in order to generate a new voice quality feature.

13. The voice quality conversion method according to claim 9,

wherein in said calculating of the display coordinates, the display coordinates of each of the voice quality features held in the voice quality feature database are calculated so that a plurality of the voice quality features which are more similar having the acoustic features set with the weights heavier in said setting are displayed to be arranged closer to each other.

10. A program for generating a new voice quality feature by editing a part or all of voice quality features each consisting of acoustic features regarding a corresponding voice quality, said program causing

a computer including:

a voice quality feature database holding the voice quality features; and

a speaker attribute database holding, for each of the voice quality features held in the voice quality feature database, an identifier enabling a user to expect a voice quality of a corresponding voice quality feature,

to execute;

setting a weight for each of the acoustic features of a corresponding voice quality;

calculating display coordinates of each of the voice quality features held in the voice quality feature database, based on (i) the acoustic features of a corresponding voice quality feature and (ii) the weights set for the acoustic features in said setting;

displaying, for each of the voice quality features held in the voice quality feature database, the identifier held in the speaker attribute database on a corresponding set of the display coordinates in the plural sets generated in said calculating in a display device;

receiving designated coordinates; and

(i) calculating a distance between (1) the designated coordinates received in said receiving and (2) the display coordinates of each of a part or all of the voice quality features held in the voice quality feature database, and (ii) mixing the acoustic features of the part or all of the voice quality features together based on a ratio between the calculated distances in order to generate a new voice quality feature.

14. The program according to claim 10,

wherein in said calculating of the display coordinates, the display coordinates of each of the voice quality features held in the voice quality feature database are calculated so that a plurality of the voice quality features which are more similar having the acoustic features set with the weights heavier in said setting are displayed to be arranged closer to each other.

11. A voice quality edit system that generates a new voice quality feature by editing a part or all of voice quality features each consisting of acoustic features regarding a corresponding voice quality, said voice quality edit system comprising

a first terminal, a second terminal, and a server, which are connected to one another via a network,

each of said first terminal and said second terminal includes:

a voice quality feature database holding the voice quality features;

a speaker attribute database holding, for each of the voice quality features held in said voice quality feature database, an identifier enabling a user to expect a voice quality of a corresponding voice quality feature;

a weight setting unit configured to set a weight for each of the acoustic features of a corresponding voice quality and send the weight to said server;

an inter-voice-quality distance calculation unit configured to (i) extract an arbitrary pair of voice quality features from the voice quality features held in said voice quality feature database, (ii) weight the acoustic features of each of the voice quality features in the extracted arbitrary pair, using the respective weights held in said server, and (iii) calculate a distance between the voice quality features in the extracted arbitrary pair after the weighting;

a scaling unit configured to calculate plural sets of the display coordinates of the voice quality features held in said voice quality feature database based on the distances calculated by said inter-voice-quality distance calculation unit using a plurality of the arbitrary pairs;

a display unit configured to display, for each of the voice quality features held in said voice quality feature database, the identifier held in said speaker attribute database on a corresponding set of the display coordinates in the plural sets calculated by said scaling unit;

a position input unit configured to receive designated coordinates; and

a voice quality mix unit configured to (i) calculate a distance between (1) the designated coordinates received by said position input unit and (2) the display coordinates of each of a part or all of the voice quality features held in said voice quality feature database, and (ii) mix the acoustic features of the part or all of the voice quality features together based on a ratio between the calculated distances in order to generate a new voice quality feature, and

said server includes a weight storage unit configured to hold the weight sent from any of said first terminal and said second terminal.