mavwaked has no wake word, only an energy VAD — add silero-vad and a keyword gate #220

Merged
claude merged 2 commits from task/487-wake-word-threshold into master 2026-08-09 13:46:42 +02:00
Contributor

Closes Vikunja #487.

Acceptance criteria and quality gate are in TASK.md on this branch.
Review the review, not the diff — leave comments and the agent will apply them via task start 487.

Closes Vikunja #487. Acceptance criteria and quality gate are in `TASK.md` on this branch. Review the review, not the diff — leave comments and the agent will apply them via `task start 487`.
claude added 2 commits 2026-08-09 13:43:53 +02:00
The first head woke 22 times per hour of continuous Russian speech. Two rounds
of hard negative mining over 40000 unseen Common Voice clips took that to 3.4,
and the second round recovered the recall the first had cost.

The number is crossings per hour, not accuracy per window. A 1.7% false-accept
rate on a gate that scores twelve times a second reads as small and is a wake
every few seconds.

Two things are stated rather than buried: Golos scores 2 wakes in 14 minutes at
every threshold, so a handful of real utterances sit above 0.999 and no
threshold moves them; and no negative in any table is a room recording.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ptwopxyo3Z2kwFckHkLvN
Over 65.1 minutes of held-out Common Voice the built binary woke three times
at 0.99 and once at 0.999. The recall difference was one render out of 126.
One render is worth two thirds of the false wakes.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ptwopxyo3Z2kwFckHkLvN
claude merged commit ff202c0c35 into master 2026-08-09 13:46:42 +02:00
Sign in to join this conversation.
No Reviewers
No Label
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: kami/Maven#220