Sci-Phi: A Large Language Model Spatial Audio Descriptor

• URL: http://arxiv.org/abs/2510.05542v1
• Date: Tue, 07 Oct 2025 03:06:02 GMT
• Title: Sci-Phi: A Large Language Model Spatial Audio Descriptor
• Authors: Xilin Jiang, Hannes Gamper, Sebastian Braun,
• Abstract summary: Sci-Phi is a spatial audio model with dual spatial and spectral encoders.<n>It enumerates and describes up to four directional sound sources in one pass.<n>It generalizes to real room impulse responses with only minor performance degradation.
• Score: 25.302416479626974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Acoustic scene perception involves describing the type of sounds, their timing, their direction and distance, as well as their loudness and reverberation. While audio language models excel in sound recognition, single-channel input fundamentally limits spatial understanding. This work presents Sci-Phi, a spatial audio large language model with dual spatial and spectral encoders that estimates a complete parameter set for all sound sources and the surrounding environment. Learning from over 4,000 hours of synthetic first-order Ambisonics recordings including metadata, Sci-Phi enumerates and describes up to four directional sound sources in one pass, alongside non-directional background sounds and room characteristics. We evaluate the model with a permutation-invariant protocol and 15 metrics covering content, location, timing, loudness, and reverberation, and analyze its robustness across source counts, signal-to-noise ratios, reverberation levels, and challenging mixtures of acoustically, spatially, or temporally similar sources. Notably, Sci-Phi generalizes to real room impulse responses with only minor performance degradation. Overall, this work establishes the first audio LLM capable of full spatial-scene description, with strong potential for real-world deployment. Demo: https://sci-phi-audio.github.io/demo

Related papers

• ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation [55.76423101183408]
  ViSAudio is an end-to-end framework that employs conditional flow matching with a dual-branch audio generation architecture.<n>It generates high-quality audio with spatial immersion that adapts to viewpoint changes, sound-source motion, and diverse acoustic environments.
  arXiv  Detail & Related papers  (2025-12-02T18:56:12Z)
• SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models [62.14165748145729]
  We introduce SPUR, a lightweight, plug-in approach that equips large audio-speaker models with spatial perception.<n>SPUR consists of: (i) a First-Order Ambisonics (FOA) encoder that maps channels to rotation-aware, listener-centric spatial features, integrated into target LALMs via a multimodal adapter; and (ii) SPUR-Set, a spatial QA dataset combining open-source FOA recordings with controlled simulations, emphasizing relative direction, elevation, distance, and overlap for supervised spatial reasoning.
  arXiv  Detail & Related papers  (2025-11-10T01:29:26Z)
• Spatial Audio Motion Understanding and Reasoning [8.029049649310211]
  spatial audio reasoning enables machines to interpret auditory scenes by understanding events and their spatial attributes.<n>We introduce a spatial audio encoder that processes spatial audio to detect multiple overlapping events and estimate their spatial attributes, Direction of Arrival (DoA) and source distance, at the frame level.<n>Second, to answer complex queries about dynamic audio scenes involving moving sources, we condition a large language model (LLM) on structured spatial attributes extracted by our model.
  arXiv  Detail & Related papers  (2025-09-18T06:53:22Z)
• SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation [50.03810359300705]
  SpA2V decomposes the generation process into two stages: audio-guided video planning and layout-grounded video generation.<n>We show that SpA2V excels in generating realistic videos with semantic and spatial alignment to the input audios.
  arXiv  Detail & Related papers  (2025-08-01T17:05:04Z)
• DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model [46.60765174200236]
  We propose a text-to-spatial-audio (TTSA) generation framework named DualSpec.<n>It first trains variational autoencoders (VAEs) for extracting the latent acoustic representations from sound event audio.<n>Finally, it trains a diffusion model from the latent acoustic representations and text features for the spatial audio generation.
  arXiv  Detail & Related papers  (2025-02-26T09:01:59Z)
• ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model [2.2927722373373247]
  We introduce ImmerseDiffusion, an end-to-end generative audio model that produces 3D immersive soundscapes conditioned on the spatial, temporal, and environmental conditions of sound objects.
  arXiv  Detail & Related papers  (2024-10-19T02:28:53Z)
• Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation [32.24603883810094]
  Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models.<n>We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions.<n>By leveraging spatial guidance, our model achieves the objective of generating immersive and controllable spatial audio from text.
  arXiv  Detail & Related papers  (2024-10-14T16:18:29Z)
• AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis [62.33446681243413]
  view acoustic synthesis aims to render audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene.<n>Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition for synthesizing audio.<n>We propose a novel Audio-Visual Gaussian Splatting (AV-GS) model to characterize the entire scene environment.<n>Experiments validate the superiority of our AV-GS over existing alternatives on the real-world RWAS and simulation-based SoundSpaces datasets.
  arXiv  Detail & Related papers  (2024-06-13T08:34:12Z)
• BAT: Learning to Reason about Spatial Sounds with Large Language Models [45.757161909533714]
  We present BAT, which combines the sound perception ability of a spatial scene analysis model with the natural language reasoning capabilities of a large language model (LLM)<n>Our experiments demonstrate BAT's superior performance on both spatial sound perception and reasoning.
  arXiv  Detail & Related papers  (2024-02-02T17:34:53Z)
• Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video [94.42811508809994]
  We propose an audio spatialization method that draws on visual information in videos to convert their monaural (single-channel) audio to audio. Whereas existing approaches leverage visual features extracted directly from video frames, our approach explicitly disentangles the geometric cues present in the visual stream to guide the learning process.
  arXiv  Detail & Related papers  (2021-11-21T19:26:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.