Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
LINEヤフーの音声AIがもたらす未来:ASR/TTSと対話技術の新たな可能性 / LY Co...
Search
LINEヤフーTech (LY Corporation Tech)
PRO
July 01, 2025
Technology
290
0
Share
LINEヤフーの音声AIがもたらす未来:ASR/TTSと対話技術の新たな可能性 / LY Corporation's Speech AI Vision: Towards Realtime Spoken Dialogue through Advanced ASR and TTS
LINEヤフーの音声認識と音声合成技術を活用した応用事例と、近年注目されているLLM基盤のリアルタイム音声対話技術の自社の取り組みについて紹介します。
LINEヤフーTech (LY Corporation Tech)
PRO
July 01, 2025
More Decks by LINEヤフーTech (LY Corporation Tech)
See All by LINEヤフーTech (LY Corporation Tech)
類似画像検索モデルの開発ノウハウ
lycorptech_jp
PRO
4
1.1k
NFLコンペ2026 解法
lycorptech_jp
PRO
0
130
Kaggle未経験社員をメダリストに育てる「AIドラゴン桜」
lycorptech_jp
PRO
0
690
コーポレートサイトのアクセシビリティ改善とJIS準拠への実践
lycorptech_jp
PRO
2
150
Yahoo!ファイナンス - 投資の「難しい・手間がかかる」を「分かる・簡単にする」-
lycorptech_jp
PRO
0
43
Slack MCPでインシデント対応とFAQ生成を加速する:社内ワークショップの実践
lycorptech_jp
PRO
0
740
SDDで⾒える、AIコーディングの"内訳"
lycorptech_jp
PRO
0
790
コーディングAIが導くリスクベースド探索的テストの実践
lycorptech_jp
PRO
1
770
Orchestration Development Workshopを半期実施して
lycorptech_jp
PRO
0
740
Other Decks in Technology
See All in Technology
海外カンファレンス「JavaOne」参加レポート ユーザー系IT企業における目的・成果/JavaOne Report Purpose and Results in the User IT Company
muit
0
120
Cloud Run のアップデート 触ってみる&紹介
gre212
0
270
AIガバナンス実践 - 生成AIコネクタのデータ漏洩リスクと実務対策
knishioka
0
150
AI Adaptable なテストを整える工夫 / Ways to Make Your Tests AI-Adaptable
bitkey
PRO
2
190
string地獄を脱出する
sansantech
PRO
1
110
関西に縁あるMicrosoft MVPsが語るCopilotの未来
kasada
0
820
oracle-to-databricks-migration-with-llm-and-dbt
casek
1
390
Claude Codeですべての日常業務を爆速化しよう!
minorun365
PRO
17
16k
OpenID Connectによるサービス間連携
takesection
0
150
先取りMaven4 ~16年ぶりのメジャーアップデート、その進化とは?~
ogiwarat
0
110
Unlocking the Apps
pimterry
0
140
美味しいスイスチーズを作ろう🧀🐭
taigamikami
1
190
Featured
See All Featured
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
3
150
Building Flexible Design Systems
yeseniaperezcruz
330
40k
技術選定の審美眼(2025年版) / Understanding the Spiral of Technologies 2025 edition
twada
PRO
118
120k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
The Curious Case for Waylosing
cassininazir
1
370
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.1k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
2
320
What Being in a Rock Band Can Teach Us About Real World SEO
427marketing
0
240
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
23k
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
830
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
300
Transcript
-:$PSQPSBUJPOT4QFFDI"*7JTJPO 5PXBSET3FBMUJNF4QFFDIUP4QFFDI UISPVHI"EWBODFE"43BOE554 4QFFDIBOE"DPVTUJD"*%FQU %BUB4DJFODF(SPVQ +VNQFJ .JZBLF 5BJLJ,JOPTIJUB -*/&ϠϑʔͷԻ"*͕ͨΒ͢ະདྷɿ"43554ͱରٕज़ͷ৽ͨͳՄೳੑ
"HFOEB -:$PSQPSBUJPO`T4QFFDI"* -*/&ϠϑʔͷԻ"*ʹ͍ͭͯ -:$PSQPSBUJPO`T"43554 -*/&ϠϑʔͷԻೝࣝɾԻ߹ͷհ 3FBMUJNF4QFFDIUP4QFFDI ϦΞϧλΠϜ4QFFDIUP4QFFDIٕज़։ൃͷऔΓΈʹ͍ͭͯ
'VUVSF8PSLT ࠓޙͷల
-:$PSQPSBUJPO`T4QFFDI"* -*/&ϠϑʔͷԻ"*ʹ͍ͭͯ 7JEFPBOE"VEJP $POUFOU"OBMZTJT 4QFFDI 3FDPHOJUJPO 4QFFDI (FOFSBUJPO 7JEFP"VEJP$POUFOUT $BMM$FOUFS
.FFUJOH 7PJDF6TFS*OUFSGBDF 7JEFP"VEJP$POUFOUBOE$BMM"OBMZTJT ࣸਅૉࡐఏڙΞϑϩ
-*/&ϠϑʔͷԻೝࣝͱԻ߹ͷհ *OUSPEVDUJPOPG -:$PSQPSBUJPO`T"43554 "43"VUPNBUJD4QFFDI3FDPHOJUJPO 5545FYU5P4QFFDI
:+70*$&4USFBNJOH"43 :+70*$&ετϦʔϛϯάԻೝࣝ &GGJDJFOUMZBEBQUTUPUBSHFUEPNBJOT • "TUSBUFHZCBTFEPODPNQBDUNPEFMTXJUIPVU FYUFSOBMMBOHVBHFNPEFMT • %PNBJOBEBQUBUJPOXJUIPVUUBSHFUBVEJPEBUB 1BJSFETQFFDIUFYUEBUB 6OQBJSFEUFYUEBUB
#BTF.PEFM "EBQUBUJPO .PEFM 4QFFDI 5FYU 5FYU #PPTUTQISBTFXJUIVTFSEJDUJPOBSJFT 4QFFDI 3FDPHOJUJPO 8PVMEZPV MJLFUPTUBSU UIFOBWJHBUJPO WJBUIJTSPVUF 4FSWJDF4QFDJGJD %JDUJPOBSZ :FT /P 1SJPSJUJ[FFYQSFTTXBZT 1SJPSJUJ[FHFOFSBMSPBET ʷ :FBTU ˠ ˓ :FT ʷ ,OPX ˠ ˓ /P ʷ 1SJPSJUJ[FHFOFSBMMPBET ˣ ˓ 1SJPSJUJ[FHFOFSBM SPBET 3FTPMWFTIPNPOZNT ຊ ڮ χ ϗ ϯ ό γ · Ͱ Ϛ σ ͷ ϊʜ 4VSGBDF 3FBE 4VSGBDF 3FBE &OEUP&OE "43 4QFFDI • JF ɾຊڮ χϗϯόγ JTBMPDBUJPOJO5PLZP ɾຊڮ χοϙϯόγ JTBMPDBUJPOJO0TBLB • +PJOUQSFEJDUJPOPGCPUITVSGBDFBOESFBEJOH ಉදهҟԻޠ ޮతͳυϝΠϯదԠ ಈతϢʔβࣙॻʹΑΔϑϨʔζೝࣝڧԽ ˞"CPVU'FBUVSF 'FBUVSF)JHIBDDVSBDZGPSXFCTFBSDIBOE-:$PSQPSBUJPOEPNBJO 'FBUVSF 3FTPMWFTIPNPOZNTBOEDVTUPNJ[FTFBTJMZ 'FBUVSF1SPWJEFT8FC"1*BOEPOEFWJDFNPEVMFT
"DIPSJT&YQSFTTJWF554 "DIPSJT දݱྗ͕๛͔ͳԻ߹ 'FBUVSF$POUSPMFNPUJPOJOUFOTJUZXJUIFYQSFTTJPOTUZMFT 'FBUVSF QSFTFUTQFBLFSPQUJPOTXJUIIVNBOMJLFRVBMJUZ 'FBUVSF1SPWJEFT8FC"1* POEFWJDFNPEVMFTBOEFEJUJOHXFCUPPMT "DIPSJT &EJUPS5FYUUPTQFFDIFEJUJOHUPPM
"DIPSJT &YQSFTTJWFUFYUUPTQFFDI $POUSPM0WFS4QFBLFS &NPUJPO BOE*OUFOTJUZ
ԻೝࣝͷαʔϏε׆༻ࣄྫ • :BIPP +"1"/"QQ`T7PJDF4FBSDI • 7PJDF4FBSDIJTJNQMFNFOUFEJONPTU:BIPP+"1"/4FSWJDFT JFTFSWJDFTJODMVEJOH.BQT 5SBOTJU BOETIPQQJOH :BIPP+"1"/"QQ
J04"OESPJE &YBNQMFTPG"QQMJDBUJPO
Ի߹ͷαʔϏε׆༻ࣄྫ • /BWJHBUJPOWPJDFJO:BIPP+"1"/$BS/BWJHBUJPO"QQ • 0O%FWJDF/FVSBM5FYU5P4QFFDI&OHJOF DBMMFEl"DIPSJT -JUFz • (FOFSBUFBTFDPOEBVEJPXBWFGPSNJO
TFDPOET ˎ 3FBM5JNF'BDUPS 35' JTJOJ1IPOF • 5PNJOJNJ[FBQQTJ[F XFWFJNQMFNFOUFE WBSJPVTPQUJNJ[BUJPOTJOCPUIJOGFSFODFMJCSBSJFTBOENPEFMTJ[F :BIPP+"1"/$BS/BWJHBUJPO"QQ &YBNQMFTPG"QQMJDBUJPO
"MBCBQQGPSSFBMUJNFTQPLFOEJBMPHVF CBTFEPOB--. VOEFSEFWFMPQJOH IUUQTXXXMZDPSQDPKQKBUFDIOPMPHZEFTJHOMBCT &YBNQMFTPG"QQMJDBUJPO ϦΞϧλΠϜԻରͷ࣮ݧΞϓϦ ։ൃத
ϦΞϧλΠϜ4QFFDIUP4QFFDIٕज़։ൃͷऔΓΈ 3FBMUJNF4QFFDIUP4QFFDI
3FBMUJNF4QFFDIUP4QFFDI5SFOE ϦΞϧλΠϜ4QFFDIUP4QFFDIͷٕज़ಈ IUUQTPQFOBJDPNKB+1DIBUHQUPWFSWJFX IUUQTHFNJOJHPPHMFPWFSWJFXHFNJOJMJWF IUUQTNPTIJDIBU IUUQTOVEJBMPHVFHJUIVCJPKNPTIJ
0QFO"* $IBU(15 "EWBODFE7PJDF.PEF ,ZVUBJ .PTIJ /BHPZBVOJW +.PTIJ (PPHMF (FNJOJ-JWF
4QFFDIUP4QFFDI"SDIJUFDUVSF 4QFFDIUP4QFFDIͷϞσϧߏ -BSHF-BOHVBHF.PEFM 5FYU(VJEFE4QFFDI (FOFSBUJPO Low-latency speech generation using audio
tokens or a streaming TTS module "VEJP"EBQUFS 4QFFDI &ODPEFS .PEBMJUZBMJHONFOU CFUXFFOUFYUBOEBVEJP 1SPNQU 4QFFDI 4JOHMF4USFBN 6TFSTTQFFDIPOMZ .VMUJ4USFBN 6TFSTTQFFDI --.HFOFSBUFETQFFDI
1SPTPG*OUFHSBUJOH4QFFDI&ODPEFS XJUI--.T Իͱ--.Tͷ౷߹ʹΑΔར -FWFSBHF--. $BQBCJMJUJFT 1SPNQU%SJWFO 'MFYJCJMJUZ #ZQBTT "43&SSPST --.ͷߴͳج൫ೳྗͷ׆༻
ϓϩϯϓτʹΑΔߴ͍ΧελϚΠζੑ ԻೝࣝޡΓͷӨڹΛճආ
&WBMVBUJPOPG5BTL1FSGPSNBODF 4QFFDI--.ͷλεΫੑೳͷධՁ JOQVU +42V"% 2VFTUJPO"OTXFS DIBS@G "-5 5SBOTMBUJPOGSPNKQ UPFO
#FSU4DPSF (SPVOEUSVUIUFYU UFYUUPUFYU 5SBOTDSJCFEUFYU UFYUUPUFYU 4QFFDI TQFFDIUPUFYU --.HFNNBCJU "43NPEFMXIJTQFSTNBMM 4QFFDI&ODPEFSXIJTQFSTNBMM 5SBJOJOH5PPMLJU4-".--. &WBMVBUJPO5PPMLJUMMNKQFWBM 4-".--.IUUQTHJUIVCDPN9-"/$&4-".--. MMNKQFWBMIUUQTHJUIVCDPNMMNKQMMNKQFWBM $PNQBSBCMF QFSGPSNBODFPO USBOTMBUJPO UBTL #FUUFS QFSGPSNBODFPO 2"UBTL
&WBMVBUJPOPG*OGFSFODF4QFFE ਪͷධՁ 0 10 20 30 40 50
60 vllm slam-llm (transformers) Generated Characters per Second W--.,XPO 8PPTVL FUBM&GGJDJFOUNFNPSZNBOBHFNFOUGPSMBSHFMBOHVBHFNPEFMTFSWJOHXJUIQBHFEBUUFOUJPO1SPDFFEJOHTPGUIFUI4ZNQPTJVNPO0QFSBUJOH4ZTUFNT1SJODJQMFT 'BTUFS YGBTUFS (FOFSBUFT)PXDBO*IFMQZPVUPEBZ JOTFDPOET /VNCFSPG5PLFOT
'VUVSF8PSLT ࠓޙͷల 8FBSFEFWFMPQJOH • 3FBMUJNF4QFFDIUP4QFFDI JOUFHSBUJPOXJUI--. • .VMUJMJOHVBM4QFFDI5P5FYU5FYU5P4QFFDI 7PJDF$POUSPMJOB$BS )VNBOMJLFBOE/BUVSBM
$POWFSTBUJPOBM4FBSDI 4QPLFO%JBMPHVFWJB$BMM "*"HFOU 03 4FBSDI 8FBUIFS 1PEDBTU "*"HFOU "*"HFOU "*"HFOU
EOP