The article describes how an individual discovered that a subtle background sound in a YouTube video can reveal the viewer’s exact location. By extracting faint plane noises from the soundtrack, analyzing their Doppler shifts, and matching these patterns with ADS‑B flight data, the author can pinpoint the video’s geographic origin based on aircraft speed, distance, and flight gaps. This method demonstrates a novel privacy vulnerability in seemingly innocuous media.
arXiv:2606. 14141v1 Announce Type: cross Abstract: Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content.
arXiv:2505. 18726v3 Announce Type: replace-cross Abstract: Can we determine someone's geographic location solely from the sounds they hear?
The paper introduces a method for learning binaural sound localization by using egomotion as a supervisory signal. By tracking how a camera’s direction changes relative to a sound source during a video, the authors train an audio model to predict sound directions that align with visual estimates of camera motion derived from multi‑view geometry. They evaluate this approach on a newly proposed dataset of real‑world audio‑visual videos with egomotion, demonstrating that the model can learn from real data and perform well on sound localization tasks.
arXiv:2607. 16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes.
arXiv:2510. 02916v2 Announce Type: replace-cross Abstract: We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content.
arXiv:2608. 14916v1 Announce Type: cross Abstract: AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or otherwise edited.
arXiv:2609.38444v1 Announce Type: new Abstract: Text- and image-conditioned world generators can create visually rich 3D environments, yet these worlds often remain silent or rely on soundtracks synt...
arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at...
arXiv:2605.07593v2 Announce Type: replace Abstract: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory str...
Passing is an interactive audiovisual installation that transforms a single continuous monorail-window recording into an endless journey by reconstructing it as a spatiotemporal volume and resampling its spatial and temporal structure along nonlinear trajectories. A camera-based viewer‑presence detection system influences transitions among rendered video sequences, and the resulting video stream is fed into SpecMaskFoley, a real‑time video‑to‑audio synthesis model that generates a synchronized soundscape. The work distributes creative agency among the artist, the AI model, and the audience, exploring how authorship and listening can be negotiated among human intention, machine inference, and audience interpretation.
SepGen is a single model that extends a pretrained audio‑video generator to produce a video, its mixed soundtrack, and individual waveforms for each captioned sound source in one sampling run. It offers two modes: generation, where captions dictate the content of each stem (e.g., separate stems for each speaker in a dialogue), and separation, where the model extracts specified sources from a clean audio mix based on free‑text descriptions. The authors evaluate SepGen on text‑generated scenes, scenes rendered by other generators, and real recordings of speech, music, and sound effects, showing it outperforms language‑conditioned separators, especially on speech tasks.
arXiv:2503.00389v2 Announce Type: replace-cross Abstract: We propose BGM2Pose, a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals....