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
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
LINEヤフーTech (LY Corporation Tech)
PRO
July 01, 2025
Technology
0
220
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
370
Java Virtual Threads, Kotlin Coroutines, Go Goroutinesの比較
lycorptech_jp
PRO
1
87
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
30
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
260
MLflowダイエット大作戦
lycorptech_jp
PRO
1
220
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
170
初めてのOSS貢献の雑ガイド
lycorptech_jp
PRO
1
51
LINEスタンプ開発の日常
lycorptech_jp
PRO
1
700
LINEスタンプサーバーサイド
lycorptech_jp
PRO
0
690
Other Decks in Technology
See All in Technology
新規事業 toitta におけるAI 機能評価の話 / AI Feature Evaluation in toitta
pokutuna
0
280
JuliaTokaiとしてはこれが最後かもしれない(仮) for NGK2026S
antimon2
0
130
Contract One Engineering Unit 紹介資料
sansan33
PRO
0
13k
それぞれのペースでやっていく Bet AI / Bet AI at Your Own Pace
yuyatakeyama
1
680
Azure SQL Databaseでベクター検索を活用しよう
nakasho
0
120
2026年はチャンキングを極める!
shibuiwilliam
8
1.6k
Amazon Bedrock AgentCore EvaluationsでAIエージェントを評価してみよう!
yuu551
0
190
AI開発をスケールさせるデータ中心の仕組みづくり
kzykmyzw
0
180
BPaaSオペレーション・kubell社内 n8n活用による効率化検証事例紹介
kentarofujii
0
320
ゼロから始めたFindy初のモバイルアプリ開発
grandbig
2
490
エンジニアとして長く走るために気づいた2つのこと_大賀愛一郎
nanaism
1
260
セキュリティ はじめの一歩
nikinusu
0
1.2k
Featured
See All Featured
How STYLIGHT went responsive
nonsquared
100
6k
[SF Ruby Conf 2025] Rails X
palkan
0
730
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1.1k
The Spectacular Lies of Maps
axbom
PRO
1
480
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.9k
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
0
260
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
440
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
130
The Organizational Zoo: Understanding Human Behavior Agility Through Metaphoric Constructive Conversations (based on the works of Arthur Shelley, Ph.D)
kimpetersen
PRO
0
230
Building a Scalable Design System with Sketch
lauravandoore
463
34k
Optimizing for Happiness
mojombo
379
71k
BBQ
matthewcrist
89
10k
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