Tianshu Qu

Yuhuan You, Lai Wei, Xihong Wu et al.

Large audio-language models have made rapid progress in recognizing what is present in an audio clip, but spatial audio-language understanding still lacks a clear task interface. A model must also decide where sound events occur, which semantic and spatial attributes belong to the same auditory object, how multiple objects are arranged, and whether a scene-level answer is physically plausible. We formalize this capability as audio scene analysis (ASA), a three-level problem spanning atomic perception, relational integration, and cognitive reasoning. We propose The World is Not Mono (TWNM), a framework that equips audio-language models with explicit spatial evidence. TWNM uses physically grounded First-Order Ambisonics (FOA) simulation for controllable supervision, learns slot-regularized spatial representations from multichannel audio, fuses them with semantic audio features, and trains with a progressive curriculum ending in preference optimization over metadata-derived answers and auxiliary format/evidence rewards. To operationalize ASA, we build a controlled benchmark from scene metadata, covering localization, attribute binding, spatial comparison, scene abduction, and counterfactual reasoning. On this benchmark, TWNM achieves 70.8% overall accuracy, 66.4% on spatial-family tasks, and 79.76% on mixed L3 scene-level multiple-choice QA. We also audit monaural and binaural reference systems as diagnostic references with explicit audit labels, since they differ in spatial input, training interface, and output format. The supported claim is that a clearly defined ASA hierarchy, FOA-conditioned spatial representations, and metadata-grounded training enable controlled, auditable spatial audio-language reasoning, with STARSS23 providing a limited real-recording diagnostic.

Donghang Wu, Xihong Wu, Tianshu Qu

Existing methods utilizing spatial information for sound source separation require prior knowledge of the direction of arrival (DOA) of the source or utilize estimated but imprecise localization results, which impairs the separation performance, especially when the sound sources are moving. In fact, sound source localization and separation are interconnected problems, that is, sound source localization facilitates sound separation while sound separation contributes to refined source localization. This paper proposes a method utilizing the mutual facilitation mechanism between sound source localization and separation for moving sources. The proposed method comprises three stages. The first stage is initial tracking, which tracks each sound source from the audio mixture based on the source signal envelope estimation. These tracking results may lack sufficient accuracy. The second stage involves mutual facilitation: Sound separation is conducted using preliminary sound source tracking results. Subsequently, sound source tracking is performed on the separated signals, thereby refining the tracking precision. The refined trajectories further improve separation performance. This mutual facilitation process can be iterated multiple times. In the third stage, a neural beamformer estimates precise single-channel separation results based on the refined tracking trajectories and multi-channel separation outputs. Simulation experiments conducted under reverberant conditions and with moving sound sources demonstrate that the proposed method can achieve more accurate separation based on refined tracking results.

Yuhuan You, Xihong Wu, Tianshu Qu

As artificial intelligence-generated content (AIGC) continues to evolve, video-to-audio (V2A) generation has emerged as a key area with promising applications in multimedia editing, augmented reality, and automated content creation. While Transformer and Diffusion models have advanced audio generation, a significant challenge persists in extracting precise semantic information from videos, as current models often lose sequential context by relying solely on frame-based features. To address this, we present TA-V2A, a method that integrates language, audio, and video features to improve semantic representation in latent space. By incorporating large language models for enhanced video comprehension, our approach leverages text guidance to enrich semantic expression. Our diffusion model-based system utilizes automated text modulation to enhance inference quality and efficiency, providing personalized control through text-guided interfaces. This integration enhances semantic expression while ensuring temporal alignment, leading to more accurate and coherent video-to-audio generation.

Shan Gao, Xihong Wu, Tianshu Qu

This paper proposes a deconvolution-based network (DCNN) model for DOA estimation of direct source and early reflections under reverberant scenarios. Considering that the first-order reflections of the sound source also contain spatial directivity like the direct source, we treat both of them as the sources in the learning process. We use the covariance matrix of high order Ambisonics (HOA) signals in the time domain as the input feature of the network, which is concise while containing precise spatial information under reverberant scenarios. Besides, we use the deconvolution-based network for the spatial pseudo-spectrum (SPS) reconstruction in the 2D polar space, based on which the spatial relationship between elevation and azimuth can be depicted. We have carried out a series of experiments based on simulated and measured data under different reverberant scenarios, which prove the robustness and accuracy of the proposed DCNN model.