ᬯពᐇ⌧䝰䝕䝹䛾ᣑᙇ䛻ᇶ䛵䛟ᴦ᭤㛫㢮ఝᗘ䛾ホ౯

(1)

- 1 -

ᬯពᐇ⌧䝰䝕䝹䛾ᣑᙇ䛻ᇶ䛵䛟ᴦ᭤㛫㢮ఝᗘ䛾ホ౯

Evaluating Melodic Similarity

based on an Extended Implication-Realization Model 㻌㻌㻌㻌㻌㻌㻌㻌㻌㻌㻌㻌㻌 ▮⃝ḈᏊ

^*1

㻌㻌㻌㻌㻌㻌 ὾୰㞞ᩄ

^*2^㻌

㻌㻌㻌㻌㻌 Ᏹὠ࿅Ṋோ

^*3

Sakurako YAZAWA^*1 Masatoshi HAMANAKA² Takehito UTSURO^*1

㻌㻌㻌㻌㻌㻌㻌㻌㻌

^*1^㻌

⟃Ἴ኱Ꮫ኱Ꮫ㝔䝅䝇䝔䝮᝟ሗᕤᏛ◊✲⛉▱⬟ᶵ⬟䝅䝇䝔䝮ᑓᨷ

Graduate School of Systems and Information Engineering University of Tsukuba #1

㻌㻌㻌㻌㻌㻌㻌㻌㻌㻌*2㻌

ி㒔኱Ꮫ኱Ꮫ㝔་Ꮫ◊✲⛉㻌㻌

^*3^㻌

⟃Ἴ኱Ꮫ䝅䝇䝔䝮᝟ሗ⣔▱⬟ᶵ⬟ᕤᏛᇦ

Department of Clinical System Onco-Informatics Kyoto University #2 Faculty of Engineering, Information and Systems University of Tsukuba #3

This paper proposes to measure similarity of melodies based on Implication-Realization Model (IRM), a music theory that abstracts music and then expresses music through symbol sequences based on information constituting the music such as pitch, rhythm, and rests and so on. This paper especially extends IRM so that the theory becomes much more appropriate to measuring similarity of melodies. More specifically, compared with the symbols of the original IRM, we introduce finer grained symbols by simply distinguishing up and down of interval directions and by dividing each most symbols of the original IRM into two extended symbols. Furthermore, we implement a parser which transforms tone sequence of an input melody into a sequence of the extended IRM symbols. The results of experimental evaluation through subjective human judgments show that the proposed extended IRM symbols outperform the original IRM symbols with respect to measuring similarity of melodies.

1. 䛿䛨䜑䛻

㻌 ᮏ ✏ 䛷䛿㡢 ᴦ ⌮ ㄽ ᬯ ព ᐇ ⌧ 䝰䝕䝹[

Narmour 1990

] [

Narmour 1992

]䛻ᇶ䛵䛔䛯ᴦ᭤㛫㢮ఝᗘィ⟬䛻䛴䛔䛶㏙䜉䜛䠊ᬯពᐇ⌧䝰䝕䝹䛷䛿ᴦ᭤䜢䝅䞁䝪䝹䛸࿧䜀䜜䜛グྕิ䛻ᢳ

㇟໬䛧⾲⌧䛩䜛䛣䛸䛜䛷䛝䜛䠊௒ᅇ䛿≉䛻䠈ᴦ᭤㛫㢮ఝᗘィ⟬

䛻㐺䛧䛯ᬯពᐇ⌧䝰䝕䝹䛾ᣑᙇ䛻䛴䛔䛶㏙䜉䜛䠊

㻌 ᮏ✏䛷䛿䠈㡢ᴦ⌮ㄽ䛻ᇶ䛵䛔䛯ศᯒ⤖ᯝ䜢ᴦ᭤㛫㢮ఝᗘ ィ⟬䛻⏝䛔䜛᪉ἲ䜢᳨ウ䛧䛯䠊ᴦ᭤㛫㢮ఝᗘィ⟬䛾◊✲䛿䛥䛛䜣䛻⾜䜟䜜䛶䛚䜚, 䝴䞊䝄䞊䛻ዲ䜏䛾ᴦ᭤䜢㑅䜀䛫, 䛭䛾ᴦ

᭤᝟ሗ䛛䜙䝴䞊䝄䞊䛾Ⴔዲ䜢⾲䛩䝧䜽䝖䝹䜢⏕ᡂ䛧ዲ䜏䛾ᴦ

᭤䜢㢮ఝᴦ᭤䛸䛧䛶㑅䜆ᡭἲ[Hoashi 2003]䜔ධຊ䛻㡢㡪≉ᚩ 㔞䜢⏝䛔䛯䝙䝳䞊䝷䝹䝛䝑䝖䜢ᵓ⠏䛩䜛䛣䛸䛷㢮ఝᴦ᭤䜢ᢳฟ 䛩䜛䝅䝇䝔䝮[Lampropoulos 2004], 㞳ᩓ䝣䞊䝸䜶ኚ᥮䜢䛛䛡䛶䝣䝺䞊䝈䛾䝟䝍䞊䞁䜢ぢ䛔䛰䛩ᡭἲ[Velardea 2013], ᴦ᭤䛻ྵ

䜎䜜䜛㡢➢ิ䜢ᩥᏐิ䛻ኚ᥮䛧, 䛭䛾ᩥᏐิ䛻ᑐ䛧䛶 N-gram 䜢㐺⏝䛩䜛䛣䛸䛷㢮ఝᴦ᭤䛾ᢳฟ䜢⾜䛖ヨ䜏[Doraisamy 2004]

䛺䛹ᵝ䚻䛺ᡭἲ䛜ᥦ᱌䛥䜜䛶䛔䜛.

㡢 ᴦ ⌮ ㄽ 䜢 ⏝ 䛔䛯 ᚑ ᮶ ◊ ✲ 䛸䛧䛶䛿䠈㡢 ᴦ ⌮ ㄽ GTTM

[Lerdahl 1983]

䛻ᇶ䛵䛔䛯ᴦ᭤㛫㢮ఝᗘィ⟬᪉ἲ䛜䛒䛢䜙䜜䜛䠊GTTM 䛿䝯䝻䝕䜱䛻ྵ䜎䜜䜛㡢䛾㔜せᗘ䜢ィ⟬䛧䠈䝍䜲䝮䝇䝟䞁䝒䝸䞊䛸࿧䜀䜜䜛ᮌᵓ㐀䜢ᵓ⠏䛩䜛䛣䛸䛷䝯䝻䝕䜱䜢㝵 ᒙⓗ䛻ᤊ䛘ศᯒ,⌮ゎ䛩䜛㡢ᴦ⌮ㄽ䛷䛒䜛

[Hamanaka 2007]

^䠊㻌 GTTM 䛻ᇶ䛵䛔䛯ᴦ᭤㛫㢮ఝᗘィ⟬

[Hirata 2013]

^䛿 GTTM 䛻䛚䛡䜛䝍䜲䝮䝇䝟䞁䝒䝸䞊䛜ᴦ᭤㛫䛷ྜ⮴䛧䛶䛔䜛㒊 ศ䛻ᑐ䛧䛶䠈䛭䛾䝍䜲䝮䝇䝟䞁䝒䝸䞊䛻௜䛔䛶䛔䜛㡢䛾㛗䛥䞉ᩘ

䛾఩⨨䛻䛒䜛㡢䛾⥲ᩘ䜢⏝䛔䛶㢮ఝᗘ䜢ィ⟬䛧䛶䛔䛯䠊䛣䛾ᡭ ἲ䛿䜋䜌ྠ䛨᭤䛾ሙྜ䛻䛾䜏㢮ఝィ⟬䛜䛷䛝䜛䜒䛾䛷䛒䜚䠈ྠ

䛨᭤䜢᳨⣴䛩䜛ሙྜ䛻䛿䛸䛶䜒㐺䛧䛶䛔䜛䠊䛧䛛䛧ไ⣙䛜䛸䛶䜒 ཝ䛧䛔䛯䜑䠈ே㛫䛜⫈䛔䛯ሙྜ䛻䛂䛒䜛⛬ᗘఝ䛶䛔䜛䛃䛸ឤ䛨䜛

᭤䛾⤌䛾㢮ఝᗘ䛜༑ศ㧗䛟䛺䜙䛺䛔䛸䛔䛖ၥ㢟䛜䛒䛳䛯䠊㻌 ᮏ◊✲䛷䛿㡢ᴦ⌮ㄽᬯពᐇ⌧䝰䝕䝹䜢⏝䛔䛯ᴦ᭤㛫㢮ఝ ᗘィ⟬ἲ䜢ᥦ᱌䛩䜛䠊ᬯពᐇ⌧䝰䝕䝹䜢⏝䛔䛯ඛ⾜◊✲䛸䛧䛶

[

Grachten

2005]

䛿ᬯពᐇ⌧䝰䝕䝹䛷ᐃ⩏䛥䜜䛶䛔䜛ᵓ㐀䜢

⏝䛔䜛ᡭἲ䜢ᥦ᱌䛧䠈㢮ఝᗘ䜢ィ⟬䛷䛝䜛䛣䛸䜢♧䛧䛯䠊䛧䛛䛧䠈 ᬯពᐇ⌧䝰䝕䝹䛿ᮏ᮶䠈ᴦ᭤㛫㢮ఝᗘ䜢ィ⟬䛩䜛䛯䜑䛾㡢ᴦ

⌮ㄽ䛷䛿䛺䛔䛯䜑䠈䜸䝸䝆䝘䝹䛾ᵓ㐀䜢⏝䛔䛯䛰䛡䛷䛿䠈㢮ఝ ᗘィ⟬䛸䛔䛖ほⅬ䛷䛿⢭ᗘ䛜ୗ䛜䛳䛶䛧䜎䛖ၥ㢟䛜䛒䛳䛯䠊䛭䛣䛷ᡃ䚻䛿䜸䝸䝆䝘䝹䛾ᬯពᐇ⌧䝰䝕䝹䛻ᑐ䛧䛶ᣑᙇ䜢⾜䛖䛣䛸䛷ᴦ᭤㛫㢮ఝᗘィ⟬⢭ᗘ䛾ྥୖ䜢ᅗ䛳䛯䠊

㻌 ᡃ䚻䛿䜸䝸䝆䝘䝹ᬯពᐇ⌧䝰䝕䝹䠈䛚䜘䜃䠈ᣑᙇ䜢⾜䛳䛯 ᬯពᐇ⌧䝰䝕䝹䛾୧᪉䛷ᴦ᭤㛫㢮ఝᗘィ⟬䜢⾜䛳䛯䠊ィ⟬⤖

ᯝ䛻ᇶ䛵䛝㢮ఝᴦ᭤䜢䝕䞊䝍䝧䞊䝇䛛䜙㑅䜃ฟ䛧䠈⿕㦂⪅୺

ほᐇ㦂䜢⾜䛳䛯䠊䛭䛾⤖ᯝ䠈ᣑᙇ䜢⾜䛳䛯ᬯពᐇ⌧䝰䝕䝹䛷䛾㢮ఝᗘィ⟬䛜䜸䝸䝆䝘䝹䛾ᬯពᐇ⌧䝰䝕䝹䜢ୖᅇ䛳䛯䠊

2. 䝯䝻䝕䜱䜈䛾ᬯពᐇ⌧䝰䝕䝹䛾䝅䞁䝪䝹௜୚

2.1 ᬯពᐇ⌧䝰䝕䝹

㻌 ᴦ᭤㛫㢮ఝᗘุᐃ䝅䝇䝔䝮䜢ᵓ⠏䛩䜛䛻䛒䛯䜚䠈ᬯពᐇ⌧

䝰䝕䝹䛸䛔䛖㡢ᴦ⌮ㄽ䛻╔┠䛧䛯䠊ᬯពᐇ⌧䝰䝕䝹䛸䛿㡢ᴦᏛ

⪅䛷䛒䜛Eugene Narmour䛻䜘䛳䛶ᥦၐ䛥䜜䛯⌮ㄽ䛷䛒䜛䠊䛣䛾

⌮ㄽ㡢ྠኈ䛾㛵ಀ䜢䝛䝑䝖䝽䞊䜽䛾䜘䛖䛻ᤊ䛘䛶䝯䝻䝕䜱䜢グ㏙

䛧䛶䛚䜚, 䛣䛾䝛䝑䝖䝽䞊䜽䜢ゎᯒ䞉ᢳฟ䛩䜛䛣䛸䛻䜘䜚䠈䝯䝻䝕䜱䛜䛹䛾䜘䛖䛺ᵓ㐀䛻䛺䛳䛶䛔䜛䛛䜢ศᯒ䛩䜛䛣䛸䛜䛷䛝䜛䠊䜎䛯ᐇ 㝿䛾ゎᯒ䛿ᴦ᭤䜢ᵓᡂ䛩䜛㡢㧗䠈㡢⛬䠈䝸䝈䝮䜔ఇ➢➼䛾᝟ሗ 䜢⏝䛔䛶ᴦ᭤䜢䝅䞁䝪䝹䛸࿧䜀䜜䜛グྕ䜢⏝䛔䛶グྕิ䜈䛸ᢳ

㇟໬䛧䛶⾲⌧䛩䜛䛣䛸䛜䛷䛝䜛㐃⤡ඛ䠖▮⃝ḈᏊ䠈⟃Ἴ኱Ꮫ኱Ꮫ㝔䝅䝇䝔䝮᝟ሗᕤᏛ◊✲⛉

༤ኈᚋᮇㄢ⛬䠈㻌㼟㼍㼗㼡㼞㼍㼗㼛㻬㼙㼡㼟㼕㼏㻚㼕㼕㼠㻚㼠㼟㼡㼗㼡㼎㼍㻚㼍㼏㻚㼖㼜㻌㻌

The 29th Annual Conference of the Japanese Society for Artificial Intelligence, 2015

2C5-OS-21b-6in

(2)

- 2 -

2.2 ᬯពᐇ⌧䝰䝕䝹䛾ᣑᙇ

㻌 ᬯពᐇ⌧䝰䝕䝹䜢⏝䛔䛯ᴦ᭤㛫㢮ఝᗘุᐃ䛿ඛ⾜◊✲䜘䜚䠈䝅䞁䝪䝹䜢⏝䛔䛯グྕิẚ㍑䛻䜘䛳䛶㢮ఝᗘィ⟬䛜䛒䜛⛬

ᗘྍ⬟䛷䛒䜛䛣䛸䜢♧䛧䛯䠊䛧䛛䛧䠈䜸䝸䝆䝘䝹䛾ᬯពᐇ⌧䝰䝕䝹䛷ᐃ⩏䛥䜜䛶䛔䜛䝅䞁䝪䝹䛷䛿㡢⛬䛾ୖୗ᪉ྥ䛾௙᪉䛻㛵䛧䛶䛾ᐃ⩏䛜↓䛔䛯䜑䛻㢮ఝᗘィ⟬䛸䛔䛖ほⅬ䛷䛿⢭ᗘ䛜ୗ

䛜䛳䛶䛧䜎䛳䛶䛔䛯䠊౛䛘䜀㡢⛬䛜䛂ୗ䛜䛳䛶ୖ䛜䜛䛃䛸䛂䛒䛜䛳䛶ୗ䛜䜛䛃䛸䛔䛖᣺䜛⯙䛔䜢䛧䛶䛔䜛㡢ิ䛜ᴦ᭤䛻ฟ䛶᮶䛯ሙྜ

䛻䠈඲䛟㐪䛖᪕ᚊ䜢ᡃ䚻䛿⫈䛔䛶䛔䜛䛾䛻ྠ䛨䝅䞁䝪䝹䛜๭䜚ᙜ 䛶䜙䜜䛶䛧䜎䛳䛶䛔䛯䠊

㻌㢮ఝᗘィ⟬䛻୺║䜢䛚䛔䛯ሙྜ䠈ඛ䛾䜘䛖䛺⫈䛔䛯༳㇟䛜

඲䛟㐪䛖᪕ᚊ㡢ิ䛜ྠ䛨䝅䞁䝪䝹䛸ุᐃ䛥䜜䜛䛸䠈ᴦ᭤䛾ᒎ㛤䛿

ྠ䛨䛷䜒ᐇ㝿䛻⫈䛔䛯ሙྜ䛻ఝ䛶䛔䛺䛔䛸ุᐃ䛥䜜䛶䛧䜎䛖䛸䛔䛖ၥ㢟䛜Ⓨ⏕䛩䜛䠊䛣䛾ၥ㢟䜢ゎỴ䛩䜛䛯䜑ᡃ䚻䛿㡢⛬䛾ୖୗ

᪉ྥ䜈䛾ᐃ⩏䛾ᣑᙇ䜢⾜䛳䛯䠊ᣑᙇ䛾ලయⓗ౛䜢ᅗ 1䛻♧䛩䠊

2.3 ᣑᙇᬯពᐇ⌧䝰䝕䝹䛾䝅䞁䝪䝹䝟䞊䝃䞊

㻌 ᮏ⠇䛷䛿ᵓ⠏䛧䛯ᬯពᐇ⌧䝰䝕䝹䝟䞊䝃䞊䛻䛴䛔䛶㏙䜉䜛䠊ᮏ䝟䞊䝃䞊䛷䛿ධຊ䛧䛯 midi ᙧᘧ䛾ᴦ᭤䜢ศᯒ䛧䠈ᬯព ᐇ⌧䝰䝕䝹䛾䝅䞁䝪䝹ิ䜢ฟຊ䛩䜛䠊

㻌䝟䞊䝃䞊䛿䜎䛪䠈㡢౯䛜ኚ໬䛩䜛㒊ศ䛸ఇ➢䜢ษ䜜┠䛸䛧䛶㡢ิ䛾䜾䝹䞊䝥䜢స䜛䠊䛭䛾䜾䝹䞊䝥䛾ඛ㢌䛛䜙㐃⥆䛩䜛䠏㡢䛪䛴䜢䛥䜙䛻⣽䛛䛔䜾䝹䞊䝥䛸䛧䠈㐃⥆䛩䜛䠎䛴䛾⣽䛛䛔䜾䝹䞊䝥䛿䠍䛴䛾㡢䜢ඹ᭷䛩䜛䠊䛴䜎䜚䠈㐃⥆䛩䜛䠎䛴䛾䜾䝹䞊䝥䛻ྵ䜎䜜䜛㐃⥆䛩䜛䠑㡢䛾䛖䛱๓༙䠏㡢䛸ᚋ༙䠏㡢䛻ᑐ䛧䛶䝅䞁䝪䝹䜢䜂䛸䛴䛪䛴๭䜚᣺䜛䠊䛣䛾㡢ิ䜢䝅䞁䝪䝹໬䛩䜛㝿䛾㡢

ิ䛾㡢ᩘ䛾ሙྜศ䛡䜢⾜䛖䛸௨ୗ䛾䠐㏻䜚䛸䛺䜛䠊1)k=1, 2)k=2, 3)k=2n+1 (1䍺n), 4)k=2n+2 (1䍺n), 䛣䛣䛷k䛿๭䜚᣺䜛䝅䞁䝪䝹䜢♧䛧䛶䛔䜛䠊1)䛸 2)䛾ሙྜ䠈ྵ䜎䜜䜛1㡢䜒䛧䛟䛿 2㡢䛻ᑐ䛧䛶౛እᆺ䛸࿧䜀䜜䜛䝅䞁䝪䝹䜢๭䜚᣺䜛䠊3)䛾ሙྜ䛿඲䛶䛾⤌

䜏ྜ䜟䛫䛻䝅䞁䝪䝹䜢๭䜚᣺䜚䠈4)䛾ሙྜ䛿᭱ᚋ䛾 2 㡢䛻ᑐ䛧䛶䛾䜏౛እᆺ䜢๭䜚᣺䜛䠊

ᅗ

1, ᣑᙇᬯពᐇ⌧ࣔࢹࣝࡢ18

✀㢮ࡢࢩࣥ࣎ࣝ

(3)

- 3 -

ᅗ

2,ᣑᙇIRM

ࡢࢩࣥ࣎ࣝิ㛫ࡢ㢮ఝᗘィ⟬ᡭ㡰

3. ᴦ᭤㛫㢮ఝᗘ

ᮏ❶䛷䛿ᴦ᭤㛫㢮ఝᗘィ⟬᪉ἲ䛻䛴䛔䛶㏙䜉䜛䠊ᴦ᭤㛫䛸䛿ᣑᙇᬯពᐇ⌧䝰䝕䝹䛷䛾ᴦ᭤䝅䞁䝪䝹ิ䛸䜸䝸䝆䝘䝹ᬯព ᐇ⌧䝰䝕䝹䛷䛾ᴦ᭤䝅䞁䝪䝹ิ䜢ᣦ䛩䠊ྛ䝅䞁䝪䝹ิ䜢 Seq1䠈 Seq2䛸䛧䛶䠈㢮ఝᗘ⟬ฟ⤖ᯝ䜢ᅗ2䛻♧䛩䠊ᮏ✏䛷䛿䠈ᮏィ⟬

䜢䛩䜛䛻䛒䛯䜚python䛾n-gram䝷䜲䝤䝷䝸䜢౑⏝䛧䛯

4. ホ౯ᐇ㦂

4.1 ホ౯ᡭ㡰

㻌 ᡃ䚻䛿 Essen 䛾䝣䜷䞊䜽䝋䞁䜾䝕䞊䝍䝧䞊䝇䝁䝺䜽䝅䝵䞁 (http://www.esac-data.org/)䛛䜙 5000 ᭤䜢⏝䛔䛶ホ౯ᐇ㦂䜢⾜

䛳䛯䠊

5000᭤䜢⥲ᙜ䛯䜚䛷䛾ẚ㍑䜢⾜䛔䠈㢮ఝᗘ䜢඲䛶䛾⤌䜏䛻 ᑐ䛧䛶⟬ฟ䛧䛯䠊㢮ఝᗘ䛿 0ࠥ1.00 䛷⟬ฟ䛥䜜䠈㢮ఝᗘ= 0, 0.05i<㢮ఝᗘ 0.05(i+1) (i=0,…,18), 0.95+0.01i<㢮ఝᗘ 0.95+0.01(i+1) (i=0,…,4) 䛾䜘䛖䛻♧䛥䜜䜛25䝺䞁䝆䛻᣺䜚ศ 䛡䛯䠊䝺䞁䝆䛤䛸䛻 2᭤䛷䠍⤌䛸䛧䛯䠑⤌䛪䛴䠈ྜィ 125⤌䛾ᴦ

᭤䛾⤌䜏ྜ䜟䛫䛻ᑐ䛧䛶୺ほホ౯ᐇ㦂䜢⾜䛳䛯䠊

㻌⿕㦂⪅䛿⏨ዪ 15 ே䛷䠈ྛ⤌䜏ྜ䜟䛫䜢⫈䛝ẚ䜉䛶䜒䜙䛔䛂䛹䛾⛬ᗘఝ䛶䛔䜛䛛䛃䜢䠑ẁ㝵䛷ホ౯䛧䛶䜒䜙䛳䛯䠊䛂䛸䛶䜒ఝ䛶䛔䜛䛃䜢5Ⅼ䠈䛂ఝ䛶䛔䜛䛃䜢4Ⅼ䠈䛂䛹䛱䜙䛷䜒䛺䛔䛃䜢3Ⅼ䠈䛂ఝ 䛶䛔䛺䛔䛃䜢2Ⅼ䠈䛂඲䛟ఝ䛶䛔䛺䛔䛃䜢1Ⅼ䛸䛧䛯䠊

㻌 ᡃ䚻䛿ᣑᙇᬯពᐇ⌧䝰䝕䝹䛸䜸䝸䝆䝘䝹䛾ᬯពᐇ⌧䝰䝕䝹䛾୧᪉䛷㢮ఝᗘィ⟬䜢⾜䛔䠈⿕㦂⪅ᐇ㦂䛾⤖ᯝ䜢ẚ㍑䛧䛯䠊 4.2 ホ౯⤖ᯝ

㻌 ᅗ 3,4,5䛻ᣑᙇᬯពᐇ⌧䝰䝕䝹䜢⏝䛔䛯ሙྜ䛸䜸䝸䝆䝘䝹

ᬯពᐇ⌧䝰䝕䝹䜢⏝䛔䛯ሙྜ䛾୺ほホ౯ᐇ㦂⤖ᯝ䜢♧䛩䠊⾲

1䛿㢮ఝᗘẚ㍑౛䛷䠈㉥ᩥᏐ䛻䛺䛳䛶䛔䜛㒊ศ䛜Seq1䛸Seq2 䛷ᕪศ䛜⌧䜜䛯㒊ศ䛷䛒䜛䠊

㻌䛣䛾⤖ᯝ䜘䜚䠈ᣑᙇᬯពᐇ⌧䝰䝕䝹䛻ᇶ䛵䛝㢮ఝᗘィ⟬䜢

⾜䛳䛯ሙྜ䛾᪉䛜䠈䜸䝸䝆䝘䝹ᬯពᐇ⌧䝰䝕䝹䛻ᇶ䛵䛝㢮ఝ ᗘィ⟬䜢⾜䛳䛯ሙྜ䜘䜚䜒᫂䜙䛛䛻Ⰻ䛔ᛶ⬟䜢♧䛧䛯䠊

⾲

1,ࢩࣥ࣎ࣝิ㛫ࡢ㢮ఝᗘィ⟬౛

(4)

- 4 -

(a)

ᣑᙇᬯពᐇ⌧ࣔࢹࣝ

(b) ࢜ࣜࢪࢼࣝᬯពᐇ⌧ࣔࢹࣝ

ᅗ

3,ホ౯⤖ᯝ㸦0.95<㢮ఝᗘӌ1㸧

(a) ᣑᙇᬯពᐇ⌧ࣔࢹࣝ

(b) ࢜ࣜࢪࢼࣝᬯពᐇ⌧ࣔࢹࣝ

ᅗ

4. ホ౯⤖ᯝ(0.65 <㢮ఝᗘӌ 0.95)

5. 䜎䛸䜑

㻌 ᮏ✏䛷䛿ᬯពᐇ⌧䝰䝕䝹䛻ᇶ䛵䛔䛯ᴦ᭤㛫㢮ఝᗘィ⟬ᡭ ἲ䛻䛴䛔䛶ᥦ᱌䛧䛯䠊ᥦ᱌䛿ᬯពᐇ⌧䝰䝕䝹䛻ᣑᙇ䜢⾜䛖䛸䛔䛖䜒䛾䛷䠈䜸䝸䝆䝘䝹ᬯពᐇ⌧䝰䝕䝹䛷ᐃ⩏䛥䜜䛶䛔䜛䝅䞁䝪䝹䛻ᑐ䛧䛶㻘㻌㡢⛬ኚ໬䜢ୗ䛢䜛㻛ୖ䛢䜛᪉ྥ䛷༊ู䛩䜛⾜ື䛾ᑟ ධ䛷䛒䜛䠊䜎䛯䠈ᣑᙇᬯពᐇ⌧䝰䝕䝹䛸䜸䝸䝆䝘䝹ᬯពᐇ⌧䝰䝕䝹䛷䛾ศᯒ䜢⾜䛘䜛ศᯒჾ䠄䝅䞁䝪䝹䝟䞊䝃䞊䠅䜢ᐇ⿦䛧䛯䠊㻌㻌 ᮏ✏䛷ᥦ᱌䛧䛯ᣑᙇᬯពᐇ⌧䝰䝕䝹䛻䜘䛳䛶䠈䜸䝸䝆䝘䝹䛾 ᬯពᐇ⌧䝰䝕䝹䜘䜚䜒㐺ษ䛺ᴦ᭤㛫㢮ఝᗘ⟬ฟ䛜ᐇ⌧䛷䛝䛯䠊 ᐇ㝿䛻⫈䛝ẚ䜉䜢⾜䛖୺ほⓗ㢮ఝᗘホ౯ᐇ㦂䛾⤖ᯝ䜘䜚䠈ᣑᙇ ᬯពᐇ⌧䝰䝕䝹䛻䜘䛳䛶䠈䜸䝸䝆䝘䝹ᬯពᐇ⌧䝰䝕䝹䛸ẚ㍑䛧䛶⢭ᗘ䜘䛟㢮ఝᗘィ⟬䛜䛷䛝䜛䛣䛸䜢♧䛧䛯䠊㻌

㻌 ௒ᚋ䛿䠈௒ᅇ౑⏝䛧䛯㡢ᴦ䝆䝱䞁䝹௨እ䛾ᴦ᭤䝕䞊䝍䝧䞊䝇䜢⏝䛔䛶䠈ᥦ᱌䛧䛯㢮ఝᗘᑻᗘ䛜༑ศ䛻ᶵ⬟䛩䜛䛛䛹䛖䛛䜢᳨

ウ䛩䜛䠊䜎䛯䠈ᗈ䛔⠊ᅖ䛾ᵓ㐀䜢㢮ఝᗘィ⟬䛻⤌䜏㎸䜐䛣䛸䛷䛥䜙䛺䜛ᬯពᐇ⌧䝰䝕䝹䛾ᣑᙇ䜢᳨ウ䛩䜛䠊䜎䛯䠈⌧ᅾ䛾䝹䞊䝹䝧䞊䝇䝟䞊䝃䞊䛷䛿ศᯒ䛷䛝䛺䛔ᴦ᭤䜢䜹䝞䞊䛩䜛䛯䜑䛻 ᶵᲔᏛ⩦䛻ᇶ䛵䛔䛯䝟䞊䝃䞊䛾ᐇ⿦䜢⾜䛖䠊㻌

ཧ⪃ᩥ⊩

[Narmour 1990] Eugene Narmour, “The Analysis and Cognition of Basic Melodic Structures”, The university of Chicago press

[Narmour 1992] Eugene Narmour, “The Analysis and Cognition of Melodic Complexity”, The university of Chicago press [Hoashi 2003] Hoashi K, Matsumoto K, Inoue N.,

“Personalization of User Content-based Music Retrieval on Relevance Feed Back” Proceedings of ACM Multimedia , pp110-119.

[Lampropoulos 2004] Lampropoulos A S, Sotiropoulos D N, Tsihrintzis G A, “Individualization of Music Similarity Perception via Feature Subset Selection”, IEEE, International Conference on System, Man and Cybernetics 2004

[Velardea 2013] Gissel Velardea, Tillman Weydeb, David Mereditha, "An approach to melodic segmentation and classification based on filtering with the Haar-wavelet "

Journal of New Music Research Volume 42, Issue 4.

[Doraisamy 2004] Shyamala Doraisamy, Stefan Ruger “A Polyphonic Music Retrieval System Using N-Grams”, Proc.

of ISMIR 2004

[Lerdahl 1983]

Fred

Lerdahl, "A Generative Theory of Tonal Music", The MIT Press

[Hamanaka 2007] Msatoshi Hamanaka, Keiji Hirata, Satoshi Tojo : ”FATTA: FULL AUTOMATIC TIME-SPAN TREE ANALYZER”, Proceedings of the 2007 International Computer Music conference

[Hirata 2013] Keiji Hirata, Satoshi Tojo, Masatoshi Hamanaka, ”Cognitive Similarity grounded by tree distance from the analysis of K. 265/300e “, Proceedings of CMMR 2013

[Grachten 2005] Maarten Grachten, Josep Lluis Arcos and Ramon Lopez de Mantaras, “Melody Retrieval using the Implication/Realization Model”, MIREX 2012 Symbolic Melodic Similarity Results

ᬯពᐇ⌧䝰䝕䝹䛾ᣑᙇ䛻ᇶ䛵䛟ᴦ᭤㛫㢮ఝᗘ䛾ホ౯

- 1 -