ܥྻม׵ͰͰ͖ΔԻ੠ೝࣝɾԻ੠߹੒ʴ㱣 Š࣮૷JTBMMXFOFFEŠ Ԭຊ୓ຏ ࠃཱݚڀ։ൃ๏ਓɹ৘ใ௨৴ݚڀػߏ /*$5 ˞֤ςʔϚͷεϥΠυΧϥʔ ɹŠԻ੠ೝࣝܥ ɹŠԻ੠߹੒ܥ ɹŠԻ৔ऩ࿥ܥ ɹŠԻ৔੍ޚܥ UI"VH OE4VNNFS4FNJOBSPG"4+!Y

ࣗݾ঺հ Ի੠ೝࣝɾԻ੠߹੒ɾػց຋༁ͱ͸ Կ͕೉͍͠ͷ͔ ஫ҙػߏ෇͖ܥྻม׵ϞσϧʹΑΔ࣮ݱ ܥྻม׵ϞσϧͷԠ༻ྫͱՄೳੑ㱣 ܥྻม׵Ϟσϧͷ՝୊ "UUFOUJPOJTBMMZPVOFFE࣮૷JTBMMXFOFFE ·ͱΊ એ఻ɿདྷ݄ͷݚڀൃදձͰͷൃද ෇࿥ ຊ೔ͷൃද

ࣗݾ঺հ Ԭຊ୓ຏ ݚڀςʔϚ Իڹ৴߸ॲཧɿಛʹԻ৔ऩ࿥ɾ੍ޚ ϚΠΫϩϗϯɾεϐʔΧΞϨΠ৴߸ॲཧ 
 ೥݄ʙ೥݄ɿ౦๺େֶઌ୺Ի৘ใγεςϜ म࢜ɾത࢜ɾϙευΫ 
 ೥݄ʙ೥݄ɿ/*$5௒ྟ৔ײϓϩδΣΫτˏ/*$5 
 ೥ʙݱࡏɿࣗ਎ͷՊݚඅ!/*$5 Ի੠ॲཧ 
 ೥݄ʙ೥݄ɿԻ੠ର࿩ɾݴޠࣝผ!/*$5 
 ೥݄ʙݱࡏɿχϡʔϥϧωοτϫʔΫΛ༻͍ͨԻ੠߹੒ɾԻ੠೾ܗੜ੒ झຯ ҿΈձ ίϩφͷͨΊօແˠࣗ୐൩ऌঢ়ଶ ɼδϣΪϯά ݄ؒΩϩ ঺հϖʔδ /*$5ݚڀ৬ɾݚڀٕज़৬࠾༻αΠτɿIUUQTXXXOJDUHPKQFNQMPZNFOUSFTFBSDIFSPLBNPUPUBLVNBIUNM ೔ຊԻڹֶձࢽΩϟϦΞύεখಛूʮೋీΛ௥͏΋ͷԿీΛಘΔ ʯɿIUUQTEPJPSHKBTK@ ͦͷଞɿ೥݄ʙ೥݄ɿ೔ຊԻڹֶձֶੜɾएखϑΥʔϥϜװࣄձୈظ୅ද ଍ͷΘΒ͡ݚڀੜ׆೥໨ˠඇৗʹָ͍͠ ͚Ͳ๩͍͠

/*$5͕ఏڙ͢ΔԻ੠຋༁ΞϓϦ7PJDF5SBΛྫʹ Ի੠ೝࣝ ສਓͷԻ੠ΛςΩετ΁ม׵ ػց຋༁ ೖྗ͞ΕͨςΩετΛผͷݴޠ΁ม׵ ςΩετԻ੠߹੒ ೖྗ͞ΕͨςΩετΛԻ੠৴߸΁ม׵ Ի੠ೝࣝɾԻ੠߹੒ɾػց຋༁ͱ͸

χϡʔϥϧԻ੠߹੒σϞ Šࢲͷ୅ΘΓʹࠃࡍձٞϏσΦͰ࿩͍͍ͯͨͩͨ͠Š

Noise level limited sub-modeling for diffusion probabilistic vocoders Takuma Okamoto1, Tomoki Toda2,1, Yoshinori Shiga1* and Hisashi Kawai1 1National Institute of Information and Communications Technology (NICT), Japan 2Nagoya University, Japan *Y. Shiga is currently with the Tokyo Denki University, Japan WaveGrad + DiffWave

೉͠͞ͷͭɿೖྗͱग़ྗͷ௕͕͞શવҧ͏ ࣮ࡍʹԻ੠߹੒ͯ͠Έͨྫ ςΩετɿจࣈ ʴ۟఺ ɼԻૉྻɿ Իڹಛ௃ྔ ϝϧεϖΫτϩάϥϜ ɿϑϨʔϜ γϑτྔNT Ի੠೾ܗ αϯϓϦϯάप೾਺L)[ ɿ αϯϓϧ Կ͕೉͍͠ͷ͔ ͋ΒΏΔݱ࣮Λɼ͢΂ͯࣗ෼ͷ΄͏΁Ͷ͡ۂ͛ͨͷͩ BSBZVSVHF/KJUTVPQBVTVCFUFKJCV/OPIPPFOFKJNBHFUBOPEB

ػց຋༁͔Βੜ·Εͨ஫ҙػߏ෇͖ܥྻม׵χϡʔϥϧωοτϫʔΫϞσϧ ೖྗ.ͱग़ྗ/ͷ௕͕͞ҧ͏ˠߦྻԋࢉʹΑͬͯม׵Մೳɿ<"Y.>Y<.Y/><"Y/> .ߦ/ྻͷม׵ߦྻ ೖྗͱग़ྗͱͷҐஔؔ܎ΞϥΠϝϯτ ΋ֶशʹΑΓࣗಈ֫ಘ͢ΔҰ؏ֶश ɹ஫ҙػߏ෇͖ܥྻม׵ϞσϧʹΑΔ࣮ݱ σίʔμ ςΩετ Իૉྻ . Τϯίʔμ / ɾ஫ҙػߏ "UUFOUJPO ߦྻ ɹೖྗͷͲ͜ʹ஫ҙΛ޲͚Δ͔ ɾΤϯίʔμͱσίʔμʹ΋ ɹ஫ҙػߏΛ࣋ͨͤΔ ɹࣗݾ஫ҙػߏ 4FMGBUUFOUJPO ˣ ຋༁ɾೝࣝɾ߹੒͚ͩͰͳ͘ ༷ʑͳ෼໺ʹͯ׆༻

ܥྻม׵Ϟσϧͷಛ௃ ೖྗͱग़ྗͷϖΞσʔλ͕͋Ε͹͍Ζ͍Ζͱ΋࢖͑Δ ྫɿςΩετˡˠԻ੠ ຋༁ɾೝࣝɾ߹੒Ͱಉ͡ωοτϫʔΫ͕࢖͑ΔͷͰॳֶऀͷෑډ͸௿͍ ෇࿥ࢀর Ի੠෼໺͚ͩͰ΋Ԡ༻͸༷ʑ ը૾ೝࣝ౳Ͱ΋ଟ਺࠾༻ ࿩ऀμΠΞϦθʔγϣϯɿऩ࿥Ի੠ˠ୭͕͍ͭ࿩͔ͨ͠ ෳ਺࿩ऀԻ੠ೝࣝɿऩ࿥Ի੠ˠ୭͕ԿΛ࿩͔ͨ͠ &OEUPFOEԻ੠຋༁ɿ೔ຊޠԻ੠ˠɹɹɹɹɹˠӳޠ຋༁Ի੠ Ի੠ڧௐɿϊΠδʔԻ੠ˠΫϦʔϯԻ੠ Իݯ෼཭ɿࠞ߹Ի੠ˠ෼཭Ի੠ ԻڹΠϕϯτݕग़ɿऩ࿥೾ܗˠΠϕϯτϥϕϧ แஸͰ໺ࡊΛ੾ΔԻɼͳͲ ੠࣭ม׵ɿ࿩ऀ"ͷԻ੠ˠɹɹɹɹɹɹˠ࿩ऀ#ͷԻ੠ ܥྻม׵ϞσϧͷԠ༻ྫ ෼໺໊ ྫɿTQFFDIFOIBODFNFOU BUUFOUJPO Ͱݕࡧ͢Δͱ͍Ζ͍Ζݟ͔ͭΔ

௚ઢεϐʔΧΞϨΠΛ༻͍ͨϚϧνεϙοτ࠶ੜγεςϜ *$"441 +"DPVTU4PD"N ͜Μʹͪ͸ )FMMP 㟬޷ Japanese area (null) (null) (null) (null) English area (null) (null) (null) (null) Chinese area (null) (null) (null) (null) Bright zone (Listening area) (null) (null) (null) (null) Dark zone (Quiet area) (null) (null) (null) (null) Իͷฉ͑͜Δ ΤϦΞ Իͷฉ͑͜ͳ͍ ΤϦΞ ॏͶ߹Θͤ

χϡʔϥϧԻ੠຋༁ٕज़ͱϚϧνεϙοτ࠶ੜٕज़ͷ༥߹ ଟݴޠϚϧνεϙοτ࠶ੜܕಉ࣌௨༁γεςϜ ೥݄/*$5খۚҪΦʔϓϯϋ΢ε αΠΤϯετʔΫ͓Αͼ"453&$σϞలࣔʹͯެ։ ͷ͸͕ͣίϩφʹΑΓதࢭ ೔ຊޠ͚͕ͩ ฉ͑͜ΔΤϦΞ ͜Μʹͪ͸ )FMMP 㟬޷ ӳޠ͚͕ͩ ฉ͑͜ΔΤϦΞ தࠃޠ͚͕ͩ ฉ͑͜ΔΤϦΞ ͜Μʹͪ͸ ଟݴޠ χϡʔϥϧ Ի੠ೝࣝ ͜Μʹͪ͸ ςΩετ ଟݴޠ χϡʔϥϧ ػց຋༁ ͜Μʹͪ͸ ςΩετ 㟬޷ ςΩετ )FMMP ςΩετ ଟݴޠ χϡʔϥϧ Ի੠߹੒ ͜Μʹͪ͸ Ի੠ 㟬޷ Ի੠ )FMMP Ի੠ Ϛϧνεϙοτ ࠶ੜ

͜ΜͳԠ༻ྫ΋ΞϦ &OEUPFOEଟݴޠϚϧνεϙοτ࠶ੜܕಉ࣌௨༁γεςϜ Ԡ༻ઌ͸㱣 ೔ຊޠ͚͕ͩ ฉ͑͜ΔΤϦΞ ͜Μʹͪ͸ )FMMP 㟬޷ ӳޠ͚͕ͩ ฉ͑͜ΔΤϦΞ தࠃޠ͚͕ͩ ฉ͑͜ΔΤϦΞ ͜Μʹͪ͸ ଟݴޠ χϡʔϥϧ Ի੠ೝࣝ ͜Μʹͪ͸ ςΩετ ଟݴޠ χϡʔϥϧ ػց຋༁ ͜Μʹͪ͸ ςΩετ 㟬޷ ςΩετ )FMMP ςΩετ ଟݴޠ χϡʔϥϧ Ի੠߹੒ ͜Μʹͪ͸ Ի੠ 㟬޷ Ի੠ )FMMP Ի੠ Ϛϧνεϙοτ ࠶ੜ ܥྻม׵χϡʔϥϧωοτ

Ի੠ೝࣝ΍Ի੠߹੒͸஫ҙػߏߦྻͷॏΈ͕ର֯ʹͳΔඞཁ͋Γ ɹ஫ҙػߏਪఆ͕ࣦഊͨ͠৔߹ͷ࢒೦ͳྫ ஫ҙػߏͷਪఆ͕ࣦഊ͢Δͱʜ ࣮αʔϏεͰ͸࢖͑ͳ͍ˠݚڀ՝୊

ݚڀΛՃ଎ͤ͞Δެ։࣮૷Ϟσϧ ओʹ1ZUIPO ɾίʔύε (JUIVCʹΑΔιʔείʔυͷެ։ ެ։ίʔύε Ի੠߹੒ ɿ-+4QFFDI ӳޠ ɼ7$5, ӳޠෳ਺࿩ऀ ɼ-JCSJ554 ӳޠෳ਺࿩ऀ ɼ+465 ೔ຊޠ ɼ +74 ೔ຊޠෳ਺࿩ऀ ɼʜ &41OFUFOEUPFOETQFFDIQSPDFTTJOHUPPMLJU ܥྻม׵ &OEUPFOE ༻Ի੠ॲཧπʔϧΩοτɿӳޠ͚ͩͲ ओ࠵ऀؚΊ ೔ຊਓ΋ଟ਺ࢀը Ի੠ೝࣝɼԻ੠߹੒ɼԻ੠຋༁ɼԻ੠ڧௐɼ੠࣭ม׵ɼԻ੠ݴޠཧղɼͰಉؔ͡਺͕࢖ΘΕ͍ͯΔˠԠ༻ઌ㱣 Α͘Θ͔Βͳ͍ ࣮૷ͯ͠ΈΑ͏ (PPHMFͷܥྻม׵ 5SBOTGPSNFS ͷ࿦จλΠτϧ l"UUFOUJPOJTBMMZPVOFFEz ˣ ࣮૷JTBMMXFOFFE ཧղ͢Δʹ͸࣮૷͋ΔͷΈମͰཧղ͢Δ ࣗ਎ͷ࣮૷͕ಈ͘ˠೝࣝͰ͖ΔPS߹੒Ͱ͖Δˠײແྔ

छͷਆث ܥྻม׵Ϟσϧ͸ষ ܥྻม׵Ϟσϧ͸ɾষ

χϡʔϥϧωοτͷجૅ͸ͪ͜Β %FFQ͔ͩΒਂւڕ

ܥྻม׵Ϟσϧͱ͸ ೖྗͱܥྻ௕͕ҧ͏ग़ྗ΁ͷม׵͕ՄೳɿԻ੠ςΩετɼςΩετԻ੠ɼʜ ܥྻ௕Λม͑ΔͨΊͷߦྻΛֶश ॴ๬ͷग़ྗΛಘΔʹ͸ೖྗͷͲ͜ʹ஫໨͢Δͷ͔Λֶश Ԡ༻ઌ͸㱣 ࣮૷JTBMMXFOFFE ཧղ͢ΔͨΊʹ͸ମͰ֮͑Δ࣮૷͋ΔͷΈ ࣮૷Ͱ͖Δ؀ڥ͸े෼ʹ͋ΔɿHJUIVCɼίʔύε ࠓޙ͸΋ͬͱ૿͑Δϋζ Ի੠߹੒ɿ࣮ࡍʹ࡞ͬͨϞσϧͰ͠Ό΂ͬͨ࣌͸ײಈ ·ͱΊ

ߴ଎࠶ੜɾෳ਺࿩ऀԻ੠೾ܗੜ੒χϡʔϥϧωοτϫʔΫϞσϧ ̍ɿদݪ ਆށେ.ɿ/*$5ݚमੜ ɼԬຊɼߴౡ ਆށେ ɼୌޱ ਆށେ ɼށా ໊େ ɼՏҪɼ )J'J("/Ϙίʔμʹ͓͚Δ-1$/FUಛ௃ྔͷݕ౼ ݴޠ֫ಘΤʔδΣϯτԻ੠೾ܗੜ੒χϡʔϥϧωοτϫʔΫϞσϧ εϖγϟϧηογϣϯ ɿాத ౦޻େमྃੜ ɼԬຊɼࣰ࡚ ౦޻େ ɼ Ի੠ݴޠ֫ಘγεςϜͷͨΊͷ8BWF(SBEΛ༻͍ͨԻ੠ൃ੠ػߏͱൃԻదԠ $16ͷΈͰߴ଎ੜ੒ɾߴ඼࣭೔ຊޠχϡʔϥϧԻ੠߹੒Ϟσϧ 1ɿԬຊɼށా ໊େ ɼՏҪ ڧ੍ΞϥΠϝϯτ൛1BSBMMFM5BDPUSPOͱ)J'J("/Λ༻͍ͨ$16ܕϦΞϧλΠϜ೔ຊޠχϡʔϥϧςΩετԻ ੠߹੒γεςϜͷ࣮૷ ෳ਺ྖҬԻ৔੍ޚ ࣗ਎ͷՊݚඅςʔϚ ɿԬຊɼ Ի৔෼཭ͱ಺෦֎෦ಉ੍࣌ޚʹجͮ͘ϚϧνԻ৔੍ޚ એ఻ɿདྷ݄ͷݚڀൃදձͰͷൃද

Thank you for your !! Ԭຊ୓ຏ (Takuma OKAMOTO)ˏNICT e-mail: HP: https://www.okamotocamera.com Twitter: @okamotocamerea

Ի੠ೝࣝͱԻ੠߹੒ɼԿ͕೉͍͠ͷ͔ ڞ௨ɿೖྗͱग़ྗͷ௕͕͞શવҧ͏ˠԻڹಛ௃ྔɿ਺ඦϑϨʔϜɼςΩετɿ਺ेจࣈ ೝࣝɿશਓྨͷൃ࿩͕λʔήοτ ലେͳଟ༷ੑ ɼ࿩଎΋όϥόϥ ߹੒ɿೖྗͱग़ྗͷ௕͞͸͞Βʹશવҧ͏ˠԻ੠೾ܗ L)[ ɿͨͬͨඵͰສαϯϓϧ ͜Ε·ͰͷԻ੠ೝࣝͱԻ੠߹੒ɿϋʔυϧߴ͍ ઐ໳஌ࣝଟ਺ඞཁ ม׵·Ͱʹ͸༷ʑͳϞδϡʔϧΛͦΕͧΕֶशɾ࿈݁ ڞ௨ɿԻڹಛ௃ྔͱςΩετͱͷҐஔؔ܎Λֶश ΞϥΠϝϯτ ೝࣝɿԻڹϞσϧɼൃԻࣙॻɼݴޠϞσϧɼσίʔμʔ ߹੒ɿԻૉܧଓ௕ϞσϧɼԻڹϞσϧɼ೾ܗੜ੒Ϟσϧ Ϙίʔμ ܥྻม׵Ϟσϧͷొ৔ɿϋʔυϧ௿͍ ઐ໳஌ࣝ͸χϡʔϥϧωοτ͕Χόʔ ͭͷχϡʔϥϧωοτʹΑΔҰׅม׵͕Մೳ ೝࣝɿԻڹಛ௃ྔˠ<ܥྻม׵Ϟσϧ>ˠ୯ޠྻ ςΩετ ߹੒ɿςΩετ Իૉܥྻ ˠ<ܥྻม׵Ϟσϧ>ˠԻڹಛ௃ྔˠ<೾ܗੜ੒Ϟσϧ>ˠԻ੠೾ܗ 
 ɹɹɹςΩετ Իૉܥྻ ˠ<ܥྻม׵Ϟσϧʴ೾ܗੜ੒Ϟσϧ>ˠԻ੠೾ܗ ෇࿥ɿԻ੠ೝࣝɾԻ੠߹੒ͷ͜Ε·Ͱͱݱࡏ