AUTOMATED GENERATION OF A SONG FOR PROCESS LEARNING

• US 20100162879A1
• Filed: 12/29/2008
• Published: 07/01/2010
• Est. Priority Date: 12/29/2008
• Status: Active Grant

• Current Assignee: Rakuten Group, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Marcus, Jane B.
• Granted Patent: US 7,977,560 B2
• Time in Patent Office: Days
• US Class Current: 84/609
• CPC Class Codes: G09B 19/00 Teaching not covered by other main groups of this subclass teaching or practice apparatus for gun-aiming or gun-laying F41G3/26
• CPC Class Codes: G09B 5/04 with audible presentation of the material to be studied sound recording or reproducing G11B
• CPC Class Codes: G10H 1/0025 Automatic or semi-automatic music composition, e.g. producing random music, applying rules from music theory or modifying a musical piece automatically producing a series of tones G10H1/26
• CPC Class Codes: G10H 2210/061 for extraction of musical phrases, isolation of musically relevant segments, e.g. musical thumbnail generation, or for temporal structure analysis of a musical piece, e.g. determination of the movement sequence of a musical work

Abstract

Embodiments of the present invention address deficiencies of the art in respect to ad hoc music creation to facilitate learning and provide a method, system and computer program product for the automated generation of a song for process learning. In an embodiment of the invention, a method for automated generation of a song for process learning can include loading from fixed storage a process description for transformation into a song intended to facilitate learning of the process by a target listener. The method also can include defining lyrical segments for the process description, selecting a particular melody from a set of melodies stored in fixed storage, and mapping the defined lyrical segments to musical phrases in the particular melody. Finally, the method can include merging pre-recorded audio segments corresponding to the defined lyrical segments with the musical phrases in the particular melody according to the mapping to generate the song.

Claims

1. A method for automated generation of a song for process learning, the method comprising:

loading from fixed storage a process description for transformation into a song intended to facilitate learning of the process by a target listener;

defining lyrical segments for the process description;

selecting a particular one of a plurality of melodies stored in fixed storage;

mapping the defined lyrical segments to musical phrases in the particular one of the melodies; and

,

merging pre-recorded audio segments corresponding to the defined lyrical segments with the musical phrases in the particular one of the melodies according to the mapping to generate the song.

2. The method of claim 1, wherein selecting a particular one of a plurality of melodies stored in fixed storage, comprises:

specifying a characterization of the target listener;

defining a subset of the melodies consonant with the characterization; and

,

selecting a particular one of a plurality of melodies in the subset of the melodies.

3. The method of claim 1, wherein selecting a particular one of a plurality of melodies stored in fixed storage, comprises:

determining a syllabic profile for at least one of the lyrical segments; and

,

selecting a particular one of a plurality of melodies stored in fixed storage matching the syllabic profile.

4. The method of claim 2, wherein the characterization comprises a characterization of the target listener selected from the group consisting of age group, gender, music style preference, ethnicity and language.

5. The method of claim 3, wherein the syllabic profile is a number of syllables in at least one of the lyrical segments.

6. The method of claim 3, wherein the syllabic profile is a number of letters in a particular word in at least one of the lyrical segments.

7. A music editor data processing system configured for automated generation of a song for process learning, the system comprising:

a host computing platform with an operating system;

a music editor executing in the host computing platform through the operating system; and

,

a personalized song generation module coupled to the music editor, the module comprising program code enabled to load from fixed storage coupled to the host computing platform a process description for transformation into a song intended to facilitate learning of the process by a target listener, to define lyrical segments for the process description, to select a particular one of a plurality of melodies stored in the fixed storage, to map the defined lyrical segments to musical phrases in the particular one of the melodies, and to merge pre-recorded audio segments corresponding to the defined lyrical segments with the musical phrases in the particular one of the melodies according to the mapping to generate the song.

8. A computer program product comprising a computer usable medium embodying computer usable program code for automated generation of a song for process learning, the computer program product comprising:

computer usable program code for loading from fixed storage a process description for transformation into a song intended to facilitate learning of the process by a target listener;

computer usable program code for defining lyrical segments for the process description;

computer usable program code for selecting a particular one of a plurality of melodies stored in fixed storage;

computer usable program code for mapping the defined lyrical segments to musical phrases in the particular one of the melodies; and

,

computer usable program code for merging pre-recorded audio segments corresponding to the defined lyrical segments with the musical phrases in the particular one of the melodies according to the mapping to generate the song.

9. The computer program product of claim 8, wherein the computer usable program code for selecting a particular one of a plurality of melodies stored in fixed storage, comprises:

computer usable program code for specifying a characterization of the target listener;

computer usable program code for defining a subset of the melodies consonant with the characterization; and

,

computer usable program code for selecting a particular one of a plurality of melodies in the subset of the melodies.

10. The computer program product of claim 8, wherein the computer usable program code for selecting a particular one of a plurality of melodies stored in fixed storage, comprises:

computer usable program code for determining a syllabic profile for at least one of the lyrical segments; and

,

computer usable program code for selecting a particular one of a plurality of melodies stored in fixed storage matching the syllabic profile.

11. The computer program product of claim 9, wherein the characterization comprises a characterization of the target listener selected from the group consisting of age group, gender, music style preference, ethnicity and language.

12. The computer program product of claim 10, wherein the syllabic profile is a number of syllables in at least one of the lyrical segments.

13. The computer program product of claim 10, wherein the syllabic profile is a number of letters in a particular word in at least one of the lyrical segments.