Metraipolis › archive › dc_ff6805880394

PLACE: Positional Latent Adaptation via Conditioned Embeddings for Binaural Audio Generation — arXiv:2610.00630

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00630
License (as archived)
CC0-1.0
Archived
2026-10-07T12:38:42.450Z
SHA-256 of the archived text
2df59573701ab659a8245a9a15c62d9c9cad73b74c562c863194d0e310c6c332
Stable URL of this page
https://metraipolis.com/documento/dc_ff6805880394

How to cite

PLACE: Positional Latent Adaptation via Conditioned Embeddings for Binaural Audio Generation — arXiv:2610.00630 — arXiv (en), https://arxiv.org/abs/2610.00630 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff6805880394 (Metraipolis archive dc_ff6805880394, sha256 2df59573701ab659a8245a9a15c62d9c9cad73b74c562c863194d0e310c6c332)
BibTeX
@misc{dcff6805880394,
  title = {PLACE: Positional Latent Adaptation via Conditioned Embeddings for Binaural Audio Generation — arXiv:2610.00630},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00630},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff6805880394; sha256 2df59573701ab659a8245a9a15c62d9c9cad73b74c562c863194d0e310c6c332},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00630. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present PLACE, a method that extends the pretrained any-to-audio model AudioX for binaural generation from arbitrary combinations of text, video, and optional audio prompts. PLACE augments video conditioning with Perception Encoder Core features, aligns text and video representations to derive spatial cues, and applies a conditioning-dependent low-rank transformation to the generated latent. The adapter is supervised via decoded-audio interaural level and time difference objectives. Trained on MRSAudio, PLACE improves most metrics over ViSAGe on FAIR-Play and achieves an improved SpatialCLAP score over SpatialSonic on the BEWO-1M Single Static test split. Listener evaluations favor PLACE for video-to-audio and out-of-distribution text-to-audio generation, demonstrating flexible multimodal control and improved spatial consistency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in eess.AS).
Categorie arXiv: Sound (cs.SD) ; Multimedia (cs.MM); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.00630 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:11:28.590Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).