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
SpeechAnalyzerによるSpeech to Textの進化を探る
Search
Masashi
October 02, 2025
Programming
13
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
SpeechAnalyzerによるSpeech to Textの進化を探る
extension DC 2025 Day2 @Sansan
https://sansan.connpass.com/event/362403/
Masashi
October 02, 2025
More Decks by Masashi
See All by Masashi
Speech Frameworkを使った音声認識の基本
kawabe
0
83
Eight iOSを支えるアーキテクチャ
kawabe
1
630
これだけは伝えたい設計の技術
kawabe
0
1.3k
EightのUI Component化の取り組み
kawabe
0
140
Other Decks in Programming
See All in Programming
「なぜそう決めたのか」を残し続ける仕組み ― Notion AI カスタムエージェント × Slack連携による設計判断の自動記録 - NIKKEI Tech Talk #47
niftycorp
PRO
0
250
エンジニア向け会社紹介/Findy Company Profile
findyinc
6
360k
Generative UI & AI-Assistants for Your Angular Solutions
manfredsteyer
PRO
0
110
エンジニアにデザインハーネスを 〜デザインプロセスを規定するためのハーネス〜 / Design harness from an engineer's perspective
rkaga
2
600
フロントエンドとバックエンドで「1文字」を揃えよう
youkidearitai
PRO
0
780
ECSアプリログをFireLensでコスト削減しようとしたけど諦めた話 in Fargate×Node.js
akihisaikeda
2
4.2k
Hatena Engineer Seminar #37「言語モデルの活用に関する研究」
slashnephy
0
460
Signal Forms: Details & Live Coding @enterJS 2026 in Mannheim
manfredsteyer
PRO
0
210
これからAgentCoreを触る方へトレンドはGatewayです
har1101
6
460
The NotImplementedError Problem in Ruby
koic
1
1.1k
ローカルLLMでどこまでコードが書けるか -縮小版 / How much code can be written on a local LLM Shortened
kishida
2
170
Snowflake Summitでの新機能 CoCo / CoWork / snowflake-summit-2026-overall-what-new-coco
tatsuhiro
1
210
Featured
See All Featured
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
[RailsConf 2023] Rails as a piece of cake
palkan
59
6.7k
Believing is Seeing
oripsolob
1
160
Java REST API Framework Comparison - PWX 2021
mraible
34
9.4k
GitHub's CSS Performance
jonrohan
1033
470k
My Coaching Mixtape
mlcsv
0
170
YesSQL, Process and Tooling at Scale
rocio
174
15k
WCS-LA-2024
lcolladotor
0
670
Fashionably flexible responsive web design (full day workshop)
malarkey
408
66k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
360
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
Transcript
SpeechAnalyzer ʹΑΔ Speech to Text ͷਐԽΛ୳Δ
Տล խ࢙ɹMasashi Kawabe NOT A HOTEL גࣜձࣾ Smart Home νʔϜ
ιϑτΣΞΤϯδχΞ
ࣨʹεΠονϦϞίϯͳ͘ɺͯ͢ Home Controller͔Βૢ࡞ɻ ੈքதɺͲ͜ͷNOT A HOTELʹߦͬͯɺ ·ΔͰࣗͷΑ͏ʹ໎͏͜ͱͳͯ͘͢ͷػ ثͷૢ࡞͕Ͱ͖·͢ɻ Home Controller
͓෦ʹ͋ΔػثʢΤΞίϯɺর໌ɺ ΧʔςϯͳͲʣΛɺ؆୯ͳԻίϚϯυͰૢ ࡞Ͱ͖·͢ɻ ϦϞίϯεΠονʹ৮ΕΔ͜ͱͳ͘ɺ ͓෦ΛշదʹௐͰ͖·͢ɻ Իίϯτϩʔϧ
SpeechAnalyzer • iOS 26 Ͱಋೖ͞ΕͨɺԻͷੳ, ੳηογϣϯΛཧ͢ΔAPI • SpeechModule Protocol ʹ४ڌ͍ͯ͠ΔϞδϡʔϧΛՃ͢Δ͜ͱͰɺ
ಛఆͷछྨͷੳΛ࣮ߦͰ͖Δ • SpeechTranscriber • Speech to Text • DictationTranscriber • SpeechTranscriber ͕ରԠ͍ͯ͠ͳ͍ݴޠ σόΠεͰͷ Speech to Text • SpeechDetector • Ի۠ؒݕग़ ( VAD )
SFSpeechRecognizer • SpeechAnalyzer Λར༻Ͱ͖ͳ͍ iOS 26 ະຬͰɺͪ͜ΒΛར༻ • iOS 10.0
Ҏ߱Ͱར༻Մೳ • ΦϯσόΠεͰͷ Speech to Text ͕Մೳ • ຊޠαϙʔτ
SpeechTranscriber • iOS 26.0 Ҏ߱Ͱར༻Մೳ • ΦϯσόΠεͰͷ Speech to Text
͕Մೳ • ࣌ؒͷԻʹରԠ • ϚΠΫ͔ΒΕͨҐஔͰͷԻʹରԠ • Siri ΩʔϘʔυͷԻೖྗͷ༗ޮԽ͕ෆཁ • ຊޠαϙʔτ
SpeechTranscriber • iOS 26.0 Ҏ߱Ͱར༻Մೳ • ΦϯσόΠεͰͷ Speech to Text
͕Մೳ • ࣌ؒͷԻʹରԠ • ϚΠΫ͔ΒΕͨҐஔͰͷԻʹରԠ • Siri ΩʔϘʔυͷԻೖྗͷ༗ޮԽ͕ෆཁ • ຊޠαϙʔτ
ϚΠΫ͔ΒΕͨҐஔͰҰఆͷਫ਼Λ୲อ SFSpeechRecognizer SpeechTranscriber
SpeechTranscriber • iOS 26.0 Ҏ߱Ͱར༻Մೳ • ΦϯσόΠεͰͷ Speech to Text
͕Մೳ • ࣌ؒͷԻʹରԠ • ϚΠΫ͔ΒΕͨҐஔͰͷԻʹରԠ • Siri ΩʔϘʔυͷԻೖྗͷ༗ޮԽ͕ෆཁ • ຊޠαϙʔτ
Իೖྗͷ༗ޮԽपΓͷۤ࿑͕ͳ͘ͳΔ • SFSpeechRecognizer ͰɺiPadOS ͷόʔδϣϯΛ্͛Δʹ Իೖྗͷ༗ޮԽ͕ඞཁͩͬͨ • OSͷόʔδϣϯΞοϓσʔτͱ߹ΘͤͯԻೖྗͷ༗ޮԽΛ ͠ͳ͔ͬͨ߹ɺҎԼͷΤϥʔʹͳΔ •
Error Domain=kLSRErrorDomain Code=201 "Siri and Dictation are disabled" UserInfo={NSLocalizedDescription=Siri and Dictation are disabled}
( ༨ஊ ) SpeechDetector • SpeechModule Protocol ʹ·ͩ४ڌ͍ͯ͠ͳ͍ • Apple
Developer Forum ͰɺࣗͰ SpeechModule Protocol ʹ४ڌͤ͞Δํ๏͕հ͞Ε͍ͯΔ • There's wrong with speech detector ios26 • https://developer.apple.com/forums/thread/794439