T-VSL: Text-Guided Visual Sound Source Localization in Mixtures

• URL: http://arxiv.org/abs/2404.01751v2
• Date: Sun, 7 Jul 2024 06:30:25 GMT
• Title: T-VSL: Text-Guided Visual Sound Source Localization in Mixtures
• Authors: Tanvir Mahmud, Yapeng Tian, Diana Marculescu,
• Abstract summary: We develop a framework to disentangle audio-visual source correspondence from multi-source mixtures. Our framework exhibits promising zero-shot transferability to unseen classes during test time. Experiments conducted on the MUSIC, VGGSound, and VGGSound-Instruments datasets demonstrate significant performance improvements over state-of-the-art methods.
• Score: 33.28678401737415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual sound source localization poses a significant challenge in identifying the semantic region of each sounding source within a video. Existing self-supervised and weakly supervised source localization methods struggle to accurately distinguish the semantic regions of each sounding object, particularly in multi-source mixtures. These methods often rely on audio-visual correspondence as guidance, which can lead to substantial performance drops in complex multi-source localization scenarios. The lack of access to individual source sounds in multi-source mixtures during training exacerbates the difficulty of learning effective audio-visual correspondence for localization. To address this limitation, in this paper, we propose incorporating the text modality as an intermediate feature guide using tri-modal joint embedding models (e.g., AudioCLIP) to disentangle the semantic audio-visual source correspondence in multi-source mixtures. Our framework, dubbed T-VSL, begins by predicting the class of sounding entities in mixtures. Subsequently, the textual representation of each sounding source is employed as guidance to disentangle fine-grained audio-visual source correspondence from multi-source mixtures, leveraging the tri-modal AudioCLIP embedding. This approach enables our framework to handle a flexible number of sources and exhibits promising zero-shot transferability to unseen classes during test time. Extensive experiments conducted on the MUSIC, VGGSound, and VGGSound-Instruments datasets demonstrate significant performance improvements over state-of-the-art methods. Code is released at https://github.com/enyac-group/T-VSL/tree/main

Related papers

• OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation [9.453883041423468]
  We propose OpenSep, a novel framework that leverages large language models (LLMs) for automated audio separation. OpenSep uses textual inversion to generate captions from audio mixtures with off-the-shelf audio captioning models, effectively parsing the sound sources present. It then employs few-shot LLM prompting to extract detailed audio properties of each parsed source, facilitating separation in unseen mixtures.
  arXiv  Detail & Related papers  (2024-09-28T06:59:52Z)
• Semantic Grouping Network for Audio Source Separation [41.54814517077309]
  We present a novel Semantic Grouping Network, termed as SGN, that can directly disentangle sound representations and extract high-level semantic information for each source from input audio mixture. We conducted extensive experiments on music-only and universal sound separation benchmarks: MUSIC, FUSS, MUSDB18, and VGG-Sound.
  arXiv  Detail & Related papers  (2024-07-04T08:37:47Z)
• Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge [14.801564966406486]
  The goal of the multi-sound source localization task is to localize sound sources from the mixture individually. We present a novel multi-sound source localization method that can perform localization without prior knowledge of the number of sound sources.
  arXiv  Detail & Related papers  (2024-03-26T06:27:50Z)
• Sound Source Localization is All about Cross-Modal Alignment [53.957081836232206]
  Cross-modal semantic understanding is essential for genuine sound source localization. We propose a joint task with sound source localization to better learn the interaction between audio and visual modalities. Our method outperforms the state-of-the-art approaches in both sound source localization and cross-modal retrieval.
  arXiv  Detail & Related papers  (2023-09-19T16:04:50Z)
• Audio-Visual Grouping Network for Sound Localization from Mixtures [30.756247389435803]
  Previous single-source methods mainly used the audio-visual association as clues to localize sounding objects in each image. We propose a novel audio-visual grouping network, namely AVGN, that can directly learn category-wise semantic features for each source from the input audio mixture and image. Compared to existing multi-source methods, our new framework can localize a flexible number of sources and disentangle category-aware audio-visual representations for individual sound sources.
  arXiv  Detail & Related papers  (2023-03-29T22:58:55Z)
• Separate What You Describe: Language-Queried Audio Source Separation [53.65665794338574]
  We introduce the task of language-queried audio source separation (LASS) LASS aims to separate a target source from an audio mixture based on a natural language query of the target source. We propose LASS-Net, an end-to-end neural network that is learned to jointly process acoustic and linguistic information.
  arXiv  Detail & Related papers  (2022-03-28T23:47:57Z)
• Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos [101.83513408195692]
  We propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video. The proposed method outperforms 12 state-of-the-art saliency prediction methods, and achieves competitive results in sound source localization.
  arXiv  Detail & Related papers  (2021-11-05T14:35:08Z)
• Visual Scene Graphs for Audio Source Separation [65.47212419514761]
  State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. We propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and segments this graph into subgraphs. Our pipeline is trained end-to-end via a self-supervised task consisting of separating audio sources using the visual graph from artificially mixed sounds.
  arXiv  Detail & Related papers  (2021-09-24T13:40:51Z)
• A Review of Sound Source Localization with Deep Learning Methods [71.18444724397486]
  This article is a review on deep learning methods for single and multiple sound source localization. We provide an exhaustive topography of the neural-based localization literature in this context. Tables summarizing the literature review are provided at the end of the review for a quick search of methods with a given set of target characteristics.
  arXiv  Detail & Related papers  (2021-09-08T07:25:39Z)
• Multiple Sound Sources Localization from Coarse to Fine [41.56420350529494]
  How to visually localize multiple sound sources in unconstrained videos is a formidable problem. We develop a two-stage audiovisual learning framework that disentangles audio and visual representations of different categories from complex scenes. Our model achieves state-of-the-art results on public dataset of localization.
  arXiv  Detail & Related papers  (2020-07-13T12:59:40Z)
• Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text [69.55642178336953]
  We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection.
  arXiv  Detail & Related papers  (2020-03-27T07:37:15Z)

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.