Invisible Neighbors: An AI Field Notebook for the Sounds Around Us

Описание и применение

Приложение позволяет пользователям записывать звуки окружающей среды, выполнять локальную идентификацию птиц с помощью модели BirdNET в браузере и экспортировать отчёт с оригинальными записями и доказательствами.

Задача

Walkers and beginner birders lack a simple way to capture and analyze ambient sounds to identify nearby wildlife without relying on external services.

Результат

The application enables offline, privacy‑preserving bird identification by running BirdNET locally in the browser, allowing users to capture, analyze, and export sound passports without external servers or paid APIs.

Рабочий процесс

• 1. Record or import a short outdoor audio or video file.
• 2. Open the listening‑stop page to play the media and request analysis.
• 3. Browser downloads BirdNET v2.4 model from Zenodo and runs TensorFlow.js inference in a worker.
• 4. App splits audio into 3‑second clips, analyzes the first 60 seconds, and keeps top five predictions per clip.
• 5. User reviews timestamped evidence, adjusts the minimum score threshold, adds field notes.
• 6. Export a ZIP with original recordings, an HTML report, and structured JSON (sound passport).

Доказательства

BirdNET suggests possible birds, and each suggestion links back to the moment in the recording that produced it.

Источник

The application has three pages: Notebook, Listening stop, Sound passport.

Источник

When someone requests analysis, the browser fetches the official model archive from Zenodo. TensorFlow.js runs inference in a worker, keeping the work separate from the interface.

Источник

Export creates a ZIP containing original recordings, a readable HTML report, and structured JSON.

Источник