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
0
230
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
Tweet
Share
More Decks by LINEヤフーTech (LY Corporation Tech)
See All by LINEヤフーTech (LY Corporation Tech)
日本語テキストと音楽の対照学習の技術とその応用
lycorptech_jp
PRO
1
450
Java Virtual Threads, Kotlin Coroutines, Go Goroutinesの比較
lycorptech_jp
PRO
1
110
マイクロサービスアーキテクチャのトレードオフとコンポーネント増加について〜Yahoo!ニュース〜
lycorptech_jp
PRO
0
43
AIプラットフォームにおけるMLflowの利用について
lycorptech_jp
PRO
2
270
MLflowダイエット大作戦
lycorptech_jp
PRO
1
250
4%ルールとN1思考──不確実性に対抗するディスカバリー検証
lycorptech_jp
PRO
1
220
初めてのOSS貢献の雑ガイド
lycorptech_jp
PRO
1
59
LINEスタンプ開発の日常
lycorptech_jp
PRO
1
750
LINEスタンプサーバーサイド
lycorptech_jp
PRO
0
750
Other Decks in Technology
See All in Technology
AWS DevOps Agent x ECS on Fargate検証 / AWS DevOps Agent x ECS on Fargate
kinunori
2
250
マーケットプレイス版Oracle WebCenter Content For OCI
oracle4engineer
PRO
5
1.6k
OpenShiftでllm-dを動かそう!
jpishikawa
0
140
Bedrock PolicyでAmazon Bedrock Guardrails利用を強制してみた
yuu551
0
270
マネージャー視点で考えるプロダクトエンジニアの評価 / Evaluating Product Engineers from a Manager's Perspective
hiro_torii
0
190
Bill One急成長の舞台裏 開発組織が直面した失敗と教訓
sansantech
PRO
2
410
データの整合性を保ちたいだけなんだ
shoheimitani
8
3.2k
Codex 5.3 と Opus 4.6 にコーポレートサイトを作らせてみた / Codex 5.3 vs Opus 4.6
ama_ch
0
220
20260208_第66回 コンピュータビジョン勉強会
keiichiito1978
0
200
Agile Leadership Summit Keynote 2026
m_seki
1
680
今日から始めるAmazon Bedrock AgentCore
har1101
4
420
GitHub Issue Templates + Coding Agentで簡単みんなでIaC/Easy IaC for Everyone with GitHub Issue Templates + Coding Agent
aeonpeople
1
260
Featured
See All Featured
How to build a perfect <img>
jonoalderson
1
4.9k
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
140
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
220
RailsConf 2023
tenderlove
30
1.3k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
1.7k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
180
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
2
430
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
aleyda
1
1.9k
Joys of Absence: A Defence of Solitary Play
codingconduct
1
290
Reality Check: Gamification 10 Years Later
codingconduct
0
2k
A Modern Web Designer's Workflow
chriscoyier
698
190k
Designing for humans not robots
tammielis
254
26k
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