Skip to content

Add blog post: speaker verification comes to OVOS#78

Open
JarbasAl wants to merge 1 commit into
masterfrom
add-speaker-verifier-post
Open

Add blog post: speaker verification comes to OVOS#78
JarbasAl wants to merge 1 commit into
masterfrom
add-speaker-verifier-post

Conversation

@JarbasAl

@JarbasAl JarbasAl commented Jun 16, 2026

Copy link
Copy Markdown
Member

What

Adds a new blog post announcing speaker verification for OpenVoiceOS:

  • ovos-ww-verifier-plugin-speaker — a wake word verifier plugin that extracts a speaker embedding after a wake word fires and only lets through voices enrolled in the household.
  • ovos-dinkum-listener#191 — the underlying wake word verifier framework that runs verifier plugins (fail-open) before any recording/intent handling.

Why it matters

  • Fewer false activations — stray "Hey Mycroft" from the TV/radio won't match an enrolled voice, so it's dropped.
  • More privacy & control — only authorised users can issue commands. No more "Hey Mycroft, order a thousand cheeseburgers" from a guest who thinks he's funny.
  • Privacy by design — profiles are stored as local, non-reversible numeric embeddings; no audio retained; everything runs locally.

Post details

  • File: _posts/2026-06-16-speaker-verifier.md
  • Author: JarbasAl (consistent with prior plugin-announcement posts)
  • Cover image: reuses /assets/blog/common/cover.png (no new asset / no broken link)
  • Config, enrollment command, default model/threshold, and tuning notes taken verbatim from the plugin README.

🤖 Generated with Claude Code

Summary by CodeRabbit

  • Documentation
    • Added documentation for the OVOS Wake Word Verifier Plugin—Speaker, covering speaker verification mechanisms, privacy behavior, installation and enrollment procedures, configuration options, and threshold tuning guidance.

@coderabbitai

coderabbitai Bot commented Jun 16, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

Warning

Review limit reached

@JarbasAl, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 25 minutes and 22 seconds. Learn how PR review limits work.

Your organization has run out of usage credits. Purchase more credits in the billing tab to continue.

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: add37837-1993-4143-b874-82a8875ba3e1

📥 Commits

Reviewing files that changed from the base of the PR and between d835c41 and 4dc31d4.

📒 Files selected for processing (1)
  • _posts/2026-06-16-speaker-verifier.md
📝 Walkthrough

Walkthrough

A new blog post is added at _posts/2026-06-16-speaker-verifier.md introducing the OVOS Wake Word Verifier Plugin for speaker verification. It covers the verification concept, privacy design using local speaker embeddings and cosine similarity, installation/enrollment steps, mycroft.conf configuration, threshold tuning, and project attribution.

Changes

OVOS Speaker Verifier Blog Post

Layer / File(s) Summary
Front matter, concept narrative, and privacy design
_posts/2026-06-16-speaker-verifier.md
Post metadata is defined; the article describes the false-activation problem, the wake-word gating framework, speaker-embedding verification flow, and privacy-by-design properties (local-only, non-reversible numeric embeddings, no audio retention).
Setup, configuration, tuning, and attribution
_posts/2026-06-16-speaker-verifier.md
Installation and enrollment commands are shown alongside a mycroft.conf hotword/verifier configuration example; threshold tuning, per-profile thresholds, and fail_open semantics are explained; attribution, funding, and contribution prompts close the post.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐇 A voice at the gate, a cosine to weigh,
No strangers shall trick my assistant today!
I enrolled every hop in my household with care,
With embeddings so local, no cloud in the air.
"Help build voice for all!" cries the rabbit with glee,
One blog post at a time — open, private, and free! 🎙️

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title 'Add blog post: speaker verification comes to OVOS' clearly and accurately summarizes the main change—adding a blog post announcing speaker verification capabilities for OpenVoiceOS.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch add-speaker-verifier-post

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@JarbasAl JarbasAl force-pushed the add-speaker-verifier-post branch from 6e24562 to b5126b0 Compare June 16, 2026 02:56
Announce ovos-ww-verifier-plugin-speaker + the wake word verifier framework
(ovos-dinkum-listener#191): speaker verification cuts false activations and
keeps commands to enrolled household members. Cross-links the Pre-Wake-VAD and
Transcription Validator posts and the NGI Zero Commons Fund grant, uses the real
listener.ww_verifiers config, and is upfront that CLI enrollment isn't yet
user-friendly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@JarbasAl JarbasAl force-pushed the add-speaker-verifier-post branch from b5126b0 to 4dc31d4 Compare June 16, 2026 03:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant