Abstract:Recently, audio-visual separation approaches have taken advantage of the natural synchronization between the two modalities to boost audio source separation performance. They extracted high-level semantics from visual inputs as the guidance to help disentangle sound representation for individual sources. Can we directly learn to disentangle the individual semantics from the sound itself? The dilemma is that multiple sound sources are mixed together in the original space. To tackle the difficulty, in this paper, 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. Specifically, SGN aggregates category-wise source features through learnable class tokens of sounds. Then, the aggregated semantic features can be used as the guidance to separate the corresponding audio sources from the mixture. We conducted extensive experiments on music-only and universal sound separation benchmarks: MUSIC, FUSS, MUSDB18, and VGG-Sound. The results demonstrate that our SGN significantly outperforms previous audio-only methods and audio-visual models without utilizing additional visual cues.
Abstract:Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can efficiently denoise the Gaussian noises towards superb multimodal content creation. To bridge this gap, we introduce AV-DiT, a novel and efficient audio-visual diffusion transformer designed to generate high-quality, realistic videos with both visual and audio tracks. To minimize model complexity and computational costs, AV-DiT utilizes a shared DiT backbone pre-trained on image-only data, with only lightweight, newly inserted adapters being trainable. This shared backbone facilitates both audio and video generation. Specifically, the video branch incorporates a trainable temporal attention layer into a frozen pre-trained DiT block for temporal consistency. Additionally, a small number of trainable parameters adapt the image-based DiT block for audio generation. An extra shared DiT block, equipped with lightweight parameters, facilitates feature interaction between audio and visual modalities, ensuring alignment. Extensive experiments on the AIST++ and Landscape datasets demonstrate that AV-DiT achieves state-of-the-art performance in joint audio-visual generation with significantly fewer tunable parameters. Furthermore, our results highlight that a single shared image generative backbone with modality-specific adaptations is sufficient for constructing a joint audio-video generator. Our source code and pre-trained models will be released.
Abstract:Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audio-visual transformers. In this paper, we propose MA-AVT, a new parameter-efficient audio-visual transformer employing deep modality alignment for corresponding multimodal semantic features. Specifically, we introduce joint unimodal and multimodal token learning for aligning the two modalities with a frozen modality-shared transformer. This allows the model to learn separate representations for each modality, while also attending to the cross-modal relationships between them. In addition, unlike prior work that only aligns coarse features from the output of unimodal encoders, we introduce blockwise contrastive learning to align coarse-to-fine-grain hierarchical features throughout the encoding phase. Furthermore, to suppress the background features in each modality from foreground matched audio-visual features, we introduce a robust discriminative foreground mining scheme. Through extensive experiments on benchmark AVE, VGGSound, and CREMA-D datasets, we achieve considerable performance improvements over SOTA methods.
Abstract:In recent developments, the Mamba architecture, known for its selective state space approach, has shown potential in the efficient modeling of long sequences. However, its application in image generation remains underexplored. Traditional diffusion transformers (DiT), which utilize self-attention blocks, are effective but their computational complexity scales quadratically with the input length, limiting their use for high-resolution images. To address this challenge, we introduce a novel diffusion architecture, Diffusion Mamba (DiM), which foregoes traditional attention mechanisms in favor of a scalable alternative. By harnessing the inherent efficiency of the Mamba architecture, DiM achieves rapid inference times and reduced computational load, maintaining linear complexity with respect to sequence length. Our architecture not only scales effectively but also outperforms existing diffusion transformers in both image and video generation tasks. The results affirm the scalability and efficiency of DiM, establishing a new benchmark for image and video generation techniques. This work advances the field of generative models and paves the way for further applications of scalable architectures.
Abstract:In this paper, we introduce the first comprehensive multilingual sign language dataset named Prompt2Sign, which builds from public data including American Sign Language (ASL) and seven others. Our dataset transforms a vast array of videos into a streamlined, model-friendly format, optimized for training with translation models like seq2seq and text2text. Building on this new dataset, we propose SignLLM, the first multilingual Sign Language Production (SLP) model, which includes two novel multilingual SLP modes that allow for the generation of sign language gestures from input text or prompt. Both of the modes can use a new loss and a module based on reinforcement learning, which accelerates the training by enhancing the model's capability to autonomously sample high-quality data. We present benchmark results of SignLLM, which demonstrate that our model achieves state-of-the-art performance on SLP tasks across eight sign languages.
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.
Abstract:This paper addresses the issue of active speaker detection (ASD) in noisy environments and formulates a robust active speaker detection (rASD) problem. Existing ASD approaches leverage both audio and visual modalities, but non-speech sounds in the surrounding environment can negatively impact performance. To overcome this, we propose a novel framework that utilizes audio-visual speech separation as guidance to learn noise-free audio features. These features are then utilized in an ASD model, and both tasks are jointly optimized in an end-to-end framework. Our proposed framework mitigates residual noise and audio quality reduction issues that can occur in a naive cascaded two-stage framework that directly uses separated speech for ASD, and enables the two tasks to be optimized simultaneously. To further enhance the robustness of the audio features and handle inherent speech noises, we propose a dynamic weighted loss approach to train the speech separator. We also collected a real-world noise audio dataset to facilitate investigations. Experiments demonstrate that non-speech audio noises significantly impact ASD models, and our proposed approach improves ASD performance in noisy environments. The framework is general and can be applied to different ASD approaches to improve their robustness. Our code, models, and data will be released.
Abstract:In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models to learn the correlation between audio and text embeddings, fall short when it comes to maintaining a seamless synchronization between the produced audio and its video. This often results in discernible audio-visual mismatches. To bridge this gap, we introduce a groundbreaking benchmark for Text-to-Audio generation that aligns with Videos, named T2AV-Bench. This benchmark distinguishes itself with three novel metrics dedicated to evaluating visual alignment and temporal consistency. To complement this, we also present a simple yet effective video-aligned TTA generation model, namely T2AV. Moving beyond traditional methods, T2AV refines the latent diffusion approach by integrating visual-aligned text embeddings as its conditional foundation. It employs a temporal multi-head attention transformer to extract and understand temporal nuances from video data, a feat amplified by our Audio-Visual ControlNet that adeptly merges temporal visual representations with text embeddings. Further enhancing this integration, we weave in a contrastive learning objective, designed to ensure that the visual-aligned text embeddings resonate closely with the audio features. Extensive evaluations on the AudioCaps and T2AV-Bench demonstrate that our T2AV sets a new standard for video-aligned TTA generation in ensuring visual alignment and temporal consistency.
Abstract:The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing complex visual environments, identifying active objects, and interpreting their changes as conveyed through language. Traditional methods, which isolate object captioning and state change detection, offer a limited view of dynamic environments. Moreover, relying on a small set of symbolic words to represent changes has restricted the expressiveness of language. To address these challenges, in this paper, we introduce the Object State Captioning and State Change Representation (OSCaR) dataset and benchmark. OSCaR consists of 14,084 annotated video segments with nearly 1,000 unique objects from various egocentric video collections. It sets a new testbed for evaluating multimodal large language models (MLLMs). Our experiments demonstrate that while MLLMs show some skill, they lack a full understanding of object state changes. The benchmark includes a fine-tuned model that, despite initial capabilities, requires significant improvements in accuracy and generalization ability for effective understanding of these changes. Our code and dataset are available at https://github.com/nguyennm1024/OSCaR.
Abstract:Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that leverages linguistic knowledge from a large text corpus to replace the traditional one-hot encoding used in auto-regressive scene text spotting and recognition models. This allows the model to capture the relationship between characters in the same word. Additionally, we introduce a technique to generate text distributions that align well with scene text datasets, removing the need for in-domain fine-tuning. As a result, the newly created text distributions are more informative than pure one-hot encoding, leading to improved spotting and recognition performance. Our method is simple and efficient, and it can easily be integrated into existing auto-regressive-based approaches. Experimental results show that our method not only improves recognition accuracy but also enables more accurate localization of words. It significantly improves both state-of-the-art scene text spotting and recognition pipelines, achieving state-of-the-art results on several benchmarks.