The addition of Foley sound effects during post-production is a common technique used to enhance the perceived acoustic properties of multimedia content. Traditionally, Foley sound has been produced by human Foley artists, which involves manual recording and mixing of sound. However, recent advances in sound synthesis and generative models have generated interest in machine-assisted or automatic Foley synthesis techniques. To promote further research in this area, we have organized a challenge in DCASE 2023: Task 7 - Foley Sound Synthesis. Our challenge aims to provide a standardized evaluation framework that is both rigorous and efficient, allowing for the evaluation of different Foley synthesis systems. We received 17 submissions, and performed both objective and subjective evaluation to rank them according to three criteria: audio quality, fit-to-category, and diversity. Through this challenge, we hope to encourage active participation from the research community and advance the state-of-the-art in automatic Foley synthesis. In this technical report, we provide a detailed overview of the Foley sound synthesis challenge, including task definition, dataset, baseline, evaluation scheme and criteria, challenge result, and discussion.
相關內容
We show that computing the strongest polynomial invariant for single-path loops with polynomial assignments is at least as hard as the Skolem problem, a famous problem whose decidability has been open for almost a century. While the strongest polynomial invariants are computable for affine loops, for polynomial loops the problem remained wide open. As an intermediate result of independent interest, we prove that reachability for discrete polynomial dynamical systems is Skolem-hard as well. Furthermore, we generalize the notion of invariant ideals and introduce moment invariant ideals for probabilistic programs. With this tool, we further show that the strongest polynomial moment invariant is (i) uncomputable, for probabilistic loops with branching statements, and (ii) Skolem-hard to compute for polynomial probabilistic loops without branching statements. Finally, we identify a class of probabilistic loops for which the strongest polynomial moment invariant is computable and provide an algorithm for it.
While direction of arrival (DOA) of sound events is generally estimated from multichannel audio data recorded in a microphone array, sound events usually derive from visually perceptible source objects, e.g., sounds of footsteps come from the feet of a walker. This paper proposes an audio-visual sound event localization and detection (SELD) task, which uses multichannel audio and video information to estimate the temporal activation and DOA of target sound events. Audio-visual SELD systems can detect and localize sound events using signals from a microphone array and audio-visual correspondence. We also introduce an audio-visual dataset, Sony-TAu Realistic Spatial Soundscapes 2023 (STARSS23), which consists of multichannel audio data recorded with a microphone array, video data, and spatiotemporal annotation of sound events. Sound scenes in STARSS23 are recorded with instructions, which guide recording participants to ensure adequate activity and occurrences of sound events. STARSS23 also serves human-annotated temporal activation labels and human-confirmed DOA labels, which are based on tracking results of a motion capture system. Our benchmark results demonstrate the benefits of using visual object positions in audio-visual SELD tasks. The data is available at //zenodo.org/record/7880637.
This is the first year of the TREC Product search track. The focus this year was the creation of a reusable collection and evaluation of the impact of the use of metadata and multi-modal data on retrieval accuracy. This year we leverage the new product search corpus, which includes contextual metadata. Our analysis shows that in the product search domain, traditional retrieval systems are highly effective and commonly outperform general-purpose pretrained embedding models. Our analysis also evaluates the impact of using simplified and metadata-enhanced collections, finding no clear trend in the impact of the expanded collection. We also see some surprising outcomes; despite their widespread adoption and competitive performance on other tasks, we find single-stage dense retrieval runs can commonly be noncompetitive or generate low-quality results both in the zero-shot and fine-tuned domain.
We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. This flash-only image is visually reflection-free and thus can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR. We extend our approach to handheld photography to address the misalignment between the flash and no-flash pair. With misaligned training data and the alignment module, our aligned model outperforms our previous version by more than 3.19dB in PSNR on a misaligned dataset. We also study using linear RGB images as training data. Our source code and dataset are publicly available at //github.com/ChenyangLEI/flash-reflection-removal.
Gradual verification, which supports explicitly partial specifications and verifies them with a combination of static and dynamic checks, makes verification more incremental and provides earlier feedback to developers. While an abstract, weakest precondition-based approach to gradual verification was previously proven sound, the approach did not provide sufficient guidance for implementation and optimization of the required run-time checks. More recently, gradual verification was implemented using symbolic execution techniques, but the soundness of the approach (as with related static checkers based on implicit dynamic frames) was an open question. This paper puts practical gradual verification on a sound footing with a formalization of symbolic execution, optimized run-time check generation, and run time execution. We prove our approach is sound; our proof also covers a core subset of the Viper tool, for which we are aware of no previous soundness result. Our formalization enabled us to find a soundness bug in an implemented gradual verification tool and describe the fix necessary to make it sound.
Binaural stereo audio is recorded by imitating the way the human ear receives sound, which provides people with an immersive listening experience. Existing approaches leverage autoencoders and directly exploit visual spatial information to synthesize binaural stereo, resulting in a limited representation of visual guidance. For the first time, we propose a visually guided generative adversarial approach for generating binaural stereo audio from mono audio. Specifically, we develop a Stereo Audio Generation Model (SAGM), which utilizes shared spatio-temporal visual information to guide the generator and the discriminator to work separately. The shared visual information is updated alternately in the generative adversarial stage, allowing the generator and discriminator to deliver their respective guided knowledge while visually sharing. The proposed method learns bidirectional complementary visual information, which facilitates the expression of visual guidance in generation. In addition, spatial perception is a crucial attribute of binaural stereo audio, and thus the evaluation of stereo spatial perception is essential. However, previous metrics failed to measure the spatial perception of audio. To this end, a metric to measure the spatial perception of audio is proposed for the first time. The proposed metric is capable of measuring the magnitude and direction of spatial perception in the temporal dimension. Further, considering its function, it is feasible to utilize it instead of demanding user studies to some extent. The proposed method achieves state-of-the-art performance on 2 datasets and 5 evaluation metrics. Qualitative experiments and user studies demonstrate that the method generates space-realistic stereo audio.
Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior works have applied Generative Adversarial Networks (GAN) to this task, but the promising diffusion model, which recently showed its advantages in terms of both training stability and output quality, has not been exploited in this context. This paper presents Diffusion-Conductor, a novel DDIM-based approach for music-driven conducting motion generation, which integrates the diffusion model to a two-stage learning framework. We further propose a random masking strategy to improve the feature robustness, and use a pair of geometric loss functions to impose additional regularizations and increase motion diversity. We also design several novel metrics, including Frechet Gesture Distance (FGD) and Beat Consistency Score (BC) for a more comprehensive evaluation of the generated motion. Experimental results demonstrate the advantages of our model.
Sensing performance is typically evaluated by classical metrics, such as Cramer-Rao bound and signal-to-clutter-plus-noise ratio. The recent development of the integrated sensing and communication (ISAC) framework motivated the efforts to unify the metric for sensing and communication, where researchers have proposed to utilize mutual information (MI) to measure the sensing performance with deterministic signals. However, the need to communicate in ISAC systems necessitates the use of random signals for sensing applications and the closed-form evaluation for the sensing mutual information (SMI) with random signals is not yet available in the literature. This paper investigates the achievable performance and precoder design for sensing applications with random signals. For that purpose, we first derive the closed-form expression for the SMI with random signals by utilizing random matrix theory. The result reveals some interesting physical insights regarding the relation between the SMI with deterministic and random signals. The derived SMI is then utilized to optimize the precoder by leveraging a manifold-based optimization approach. The effectiveness of the proposed methods is validated by simulation results.
Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. GeomCA can be applied to representations of any dimension, independently of the model that generated them. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191