An official website of the United States government
The joint analysis of audio and video is a powerful tool that can be applied to various contexts, including action, speech, and sound recognition, audio-visual video parsing, emotion recognition in affective computing, and self-supervised training of deep learning models. Solving these problems often involves tackling core audio-visual tasks, such as audio-visual source localization, audio-visual correspondence, and audio-visual source separation, which can be combined in various ways to achieve the desired results. This paper provides a review of the literature in this area, discussing the advancements, history, and datasets of audio-visual learning methods for various application domains. It also presents an overview of the reported performances on standard datasets and suggests promising directions for future research.
more »
« less
Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos
Generating realistic audio for human actions is critical for applications such as film sound effects and virtual reality games. Existing methods assume complete correspondence between video and audio during training, but in real-world settings, many sounds occur off-screen or weakly correspond to visuals, leading to uncontrolled ambient sounds or hallucinations at test time. This paper introduces AV-LDM, a novel ambient-aware audio generation model that disentangles foreground action sounds from ambient background noise in in-the-wild training videos. The approach leverages a retrieval-augmented generation framework to synthesize audio that aligns both semantically and temporally with the visual input. Trained and evaluated on Ego4D and EPIC-KITCHENS datasets, along with the newly introduced Ego4D-Sounds dataset (1.2M curated clips with action-audio correspondence), the model outperforms prior methods, enables controllable ambient sound generation, and shows promise for generalization to synthetic video game clips. This work is the first to emphasize faithful video-to-audio generation focused on observed visual content despite noisy, uncurated training data.
more »
« less
- Award ID(s):
- 2505865
- PAR ID:
- 10631944
- Publisher / Repository:
- https://doi.org/10.48550/arXiv.2406.09272
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
As two of the five traditional human senses (sight, hearing, taste, smell, and touch), vision and sound are basic sources through which humans understand the world. Often correlated during natural events, these two modalities combine to jointly affect human perception. In this paper, we pose the task of generating sound given visual input. Such capabilities could help enable applications in virtual reality (generating sound for virtual scenes automatically) or provide additional accessibility to images or videos for people with visual impairments. As a first step in this direction, we apply learning-based methods to generate raw waveform samples given input video frames. We evaluate our models on a dataset of videos containing a variety of sounds (such as ambient sounds and sounds from people/animals). Our experiments show that the generated sounds are fairly realistic and have good temporal synchronization with the visual inputs.more » « less
-
The Sound Travels research team will share a recording that exemplifies affective associations made with specific sounds by visitors to free-choice learning environments (a science museum, a park, a zoo, and a botanical garden). This recording reflects direct collaboration with visitors and demonstrates the variation in how people make sense of sound, both in identifying its sources and in describing its effects on their emotional and cognitive states. Our US-based, federally funded project explores the impacts of ambient and designed sound on STEM learning and leisure experiences. Beyond addressing our research questions, we embrace the larger goals of seeking meaningful input from professionals in and visitors to these spaces and directly informing educational design practice. Our methods include multiple stationary ambient recordings within spaces of interest, a post-experience visitor questionnaire, and a “sound search” instrument in which visitors record video clips during their experience to represent sounds that make them feel curious, energized, uneasy, and peaceful. Together, the resulting data reveal not only how visitors are affected by sound but also how visitors experience and notice sound in context, and in what ways a person’s embodied and culturally informed associations with sound relate to their experiences of learning and leisure.more » « less
-
We present Sketch2Sound, a generative audio model capable of creating high-quality sounds from a set of interpretable time-varying control signals: loudness, brightness, and pitch, as well as text prompts. Sketch2Sound can synthesize arbitrary sounds from sonic imitations (i.e.,~a vocal imitation or a reference sound-shape). Sketch2Sound can be implemented on top of any text-to-audio latent diffusion transformer (DiT), and requires only 40k steps of fine-tuning and a single linear layer per control, making it more lightweight than existing methods like ControlNet. To synthesize from sketchlike sonic imitations, we propose applying random median filters to the control signals during training, allowing Sketch2Sound to be prompted using controls with flexible levels of temporal specificity. We show that Sketch2Sound can synthesize sounds that follow the gist of input controls from a vocal imitation while retaining the adherence to an input text prompt and audio quality compared to a text-only baseline. Sketch2Sound allows sound artists to create sounds with the semantic flexibility of text prompts and the expressivity and precision of a sonic gesture or vocal imitation.more » « less
-
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.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
