d3ro-voice/docs/map
Yun Chan 9c2b6a9782 feat(meeting): correct transcripts with vocabulary learned from typing
Meeting and caption transcription never used what the app had already
learned: speech recognition ran with a fixed Korean prompt, the refine
prompt had no glossary, refined lines stopped inside the caption service,
and the saved transcript was a raw join of segments. Names and jargon the
user types every day were therefore re-mangled on every recording.

The learned corpus (user dictionary plus personal phrases) now feeds one
glossary that biases recognition, fixes mistyped words deterministically
right after each line is finalized, and is handed to the local model when
it polishes a line. Refined lines also reach the meeting transcript and
screen through a new segment-updated event.

Corrections never touch words the user actually wrote, refuse ties between
equally likely candidates, and keep particles intact.
2026-11-05 21:58:28 +09:00
..
00-index.md docs: 1.16.1 배포 결과 기록 2026-11-04 07:15:37 +09:00
01-system-overview.md chore(ops): the admin console lives only at d3ro-admin.chanpaca.net; release admin.chanpaca.net 2026-09-26 23:11:46 +09:00
02-infrastructure.md docs: 1.16.1 배포 결과 기록 2026-11-04 07:15:37 +09:00
03-shared-packages.md feat(input,voice): instant first-word-after-focus PC layout fix and speech disfluency post-processing (INPUT-04, INPUT-19, AI-03, AI-05) 2026-10-29 19:05:01 +09:00
04-desktop-app.md feat(meeting): correct transcripts with vocabulary learned from typing 2026-11-05 21:58:28 +09:00
05-web-app.md feat(input): expand Araso Han/Eng contractions, acronyms, typo recovery, and fast cursor-tail replacement 2026-10-28 10:41:26 +09:00
06-mobile-app.md docs: 1.16.0 배포와 검증 결과 기록 2026-11-01 20:05:28 +09:00
07-api-server.md docs: record Wave 3 surface consolidation and fold NAS-only whisper into compose 2026-09-26 16:02:44 +09:00
08-admin-console.md feat(input): expand Araso Han/Eng contractions, acronyms, typo recovery, and fast cursor-tail replacement 2026-10-28 10:41:26 +09:00
09-supabase-backend.md docs(map): transcript segments and preset prompts now sync 2026-09-27 16:24:26 +09:00
10-feature-catalog.md feat(meeting): correct transcripts with vocabulary learned from typing 2026-11-05 21:58:28 +09:00
11-gap-backlog.md feat(meeting): correct transcripts with vocabulary learned from typing 2026-11-05 21:58:28 +09:00
12-update-protocol.md docs: record the 1.1.0 release and add the infrastructure map 2026-09-16 23:27:52 +09:00