[Backend] Feed campaign proper nouns to the ASR as vocabulary bias

claude-bot commented

2026-08-25 20:39:17 +00:00

Collaborator

Found in the August 2026 session lifecycle review (#319).

Why

Fantasy proper nouns are precisely what a generic speech model gets wrong, and no amount of downstream prompting repairs a name the ASR never heard. Quest Board is unusually well placed here: it already holds every PC name, NPC name, place and faction for the campaign in its own wiki.

Most providers accept some form of vocabulary bias — keyterms, keyword boosting, custom dictionaries, or an initial prompt. The provider contract already carries a vocabulary input; this issue fills it.

Proposed fix

Assemble a per-campaign term list from the wiki: character names, NPC names, places, factions, and aliases, ranked by recency and appearance count so the list stays inside provider limits (commonly a couple of hundred terms). Pass it on every transcription request for that campaign. Refresh it as the wiki grows.

Measure the effect on the golden corpus rather than assuming it, and record the result — this is the kind of change that is easy to believe in and hard to verify.

Acceptance criteria

Term list assembled per campaign from wiki entities and aliases
Ranked and truncated to the provider's declared limit
Passed through the contract's vocabulary input on every request
Refreshed as the wiki changes
Measured effect recorded against the golden corpus

Found in the August 2026 session lifecycle review (#319). ## Why Fantasy proper nouns are precisely what a generic speech model gets wrong, and no amount of downstream prompting repairs a name the ASR never heard. Quest Board is unusually well placed here: it already holds every PC name, NPC name, place and faction for the campaign in its own wiki. Most providers accept some form of vocabulary bias — keyterms, keyword boosting, custom dictionaries, or an initial prompt. The provider contract already carries a `vocabulary` input; this issue fills it. ## Proposed fix Assemble a per-campaign term list from the wiki: character names, NPC names, places, factions, and aliases, ranked by recency and appearance count so the list stays inside provider limits (commonly a couple of hundred terms). Pass it on every transcription request for that campaign. Refresh it as the wiki grows. Measure the effect on the golden corpus rather than assuming it, and record the result — this is the kind of change that is easy to believe in and hard to verify. ## Acceptance criteria - [ ] Term list assembled per campaign from wiki entities and aliases - [ ] Ranked and truncated to the provider's declared limit - [ ] Passed through the contract's `vocabulary` input on every request - [ ] Refreshed as the wiki changes - [ ] Measured effect recorded against the golden corpus

claude-bot added this to the v4.2.0 - AI Provider Abstraction & BYO-AI milestone

2026-08-25 20:39:17 +00:00

claude-bot added the

enhancement

backend

recording

labels

condition	marker detection	WER
control, no vocabulary (reproduces the calibration)	72.2 %	baseline
the 24 script markers as the term list (ceiling)	96.3 %	unchanged
the 24 markers diluted in a 100-term list (realistic)	81.5 %	unchanged

Rows
Columns

[Backend] Feed campaign proper nouns to the ASR as vocabulary bias #355

Why

Proposed fix

Acceptance criteria