AudioSeal — localized audio watermarking

Meta's localized sample-level audio watermarking with fast detector, robust to compression/re-encoding; MIT with weights.

Link

• Visit resource

Related resources

• audiowmark — robust audio watermarkingRobust blind audio watermarking that survives mp3/ogg re-encoding at ≥128kbit/s, with tunable strength.
• Cavern — object-based audio engine (Atmos render)Object-based audio engine and codec pack: Dolby Atmos rendering, HRTF, room correction, unlimited objects (C#).
• libspatialaudio — VideoLAN spatial audio rendererSpatial audio renderer supporting ADM objects, Higher-Order Ambisonics and IAMF; from VideoLAN, actively maintained.
• loudgain — ReplayGain 2.0 / EBU R128 CLI normalizerCLI loudness normalizer implementing ReplayGain 2.0 on EBU R128/BS.1770 with non-destructive tagging for FLAC/Opus/AAC and more.
• fast-ssim2 — SIMD Rust SSIMULACRA2Fast SIMD Rust implementation of the SSIMULACRA2 perceptual image/video quality metric.
• SceneSeg (Local-to-Global Scene Segmentation)CVPR 2020 multimodal movie scene segmentation using place and audio features on the MovieNet dataset; reference ML baseline with code.
• IMFTool — IMF CPL editor with IMSC subtitlesOpen-source editor for IMF (Interoperable Master Format) Composition Playlists with IMSC1 text-profile subtitle decode/render/preview.
• AutoSubSyncSubtitle auto-sync GUI wrapping ffsubsync/autosubsync/alass; can sync against a reference subtitle instead of the video.
• butteraugli (Rust port)Pure Rust port of Butteraugli from libjxl with XYB color, visual masking, and multi-scale bands, validated to within 0.001% of the referenc…
• SimpleVQADeep-learning no-reference video quality assessment for user-generated content, in PyTorch with SlowFast feature extraction.