Hey everyone, I built NOVA-VAD, a lightweight explainable Voice Activity Detector that outperforms every major open source VAD on real-world noisy audio. GitHub: https://github.com/monishmal3375/nova-vad

작성자

카테고리:

← 피드로
DEV Community · M M · 2026-06-24 개발(SW)

M M

Top comments (2)

Subscribe

Collapse Expand

nazar-boyko profile image

Nazar Boyko

Software engineer, backend & AI-focused. Node.js, TypeScript, Go, PHP/Laravel, AWS. I write a lot about reliable systems and AI agents that actually ship. More at nazarboyko.com

  • Email

  • Location

    Austin, TX

  • Education

    M.S. Computer Science

  • Joined

    Aug 2, 2024

Jun 24

Explainable VAD is a genuinely useful angle, since most of them are black boxes you just have to trust. What did you benchmark against, and how does it do on the false trigger rate for music and other non-speech, where the lightweight ones usually fall apart?

For further actions, you may consider blocking this person and/or reporting abuse

원문에서 계속 ↗

코멘트

답글 남기기

이메일 주소는 공개되지 않습니다. 필수 필드는 *로 표시됩니다