REVIEW 7 cited by
BAT: Learning to Reason about Spatial Sounds with Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we present BAT, which combines the spatial sound perception ability of a binaural acoustic scene analysis model with the natural language reasoning capabilities of a large language model (LLM) to replicate this innate ability. To address the lack of existing datasets of in-the-wild spatial sounds, we synthesized a binaural audio dataset using AudioSet and SoundSpaces 2.0. Next, we developed SpatialSoundQA, a spatial sound-based question-answering dataset, offering a range of QA tasks that train BAT in various aspects of spatial sound perception and reasoning. The acoustic front end encoder of BAT is a novel spatial audio encoder named Spatial Audio Spectrogram Transformer, or Spatial-AST, which by itself achieves strong performance across sound event detection, spatial localization, and distance estimation. By integrating Spatial-AST with LLaMA-2 7B model, BAT transcends standard Sound Event Localization and Detection (SELD) tasks, enabling the model to reason about the relationships between the sounds in its environment. Our experiments demonstrate BAT's superior performance on both spatial sound perception and reasoning, showcasing the immense potential of LLMs in navigating and interpreting complex spatial audio environments.
Forward citations
Cited by 7 Pith papers
-
EgoSound: Benchmarking Sound Understanding in Egocentric Videos
EgoSound is a new benchmark with 7315 QA pairs across seven tasks to evaluate egocentric sound understanding in multimodal large language models.
-
Probing Spatial Structure in Pretrained Audio Representations
Introduces SARL benchmark showing pretrained audio encoders encode source-level spatial factors more readily than room-level factors, with patterns shaped by input configuration and training paradigm.
-
The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models
TWNM framework equips audio-language models with spatial scene analysis via FOA simulation and metadata-grounded training, reaching 70.8% accuracy on a new ASA benchmark.
-
Dual-BEATs: Unlocking Zero-Shot Stereo Audio Perception in Audio Large Language Models via Dithering
Uncorrelated dither noise lets dual frozen BEATs encoders preserve inter-channel amplitude differences across LLM normalizers, yielding up to 97% left/center/right accuracy and zero-shot spatial generalization.
-
Probing Spatial Structure in Pretrained Audio Representations
A controlled benchmark of 13 pretrained audio models shows source direction, distance, and class are much more decodable than room size, shape, and reverb time.
-
ASAudio: A Survey of Advanced Spatial Audio Research
A comprehensive survey that systematically categorizes spatial audio research by representation, task, dataset, and evaluation.
-
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.
Discussion (0). Sign in to comment.