arXiv:2610.07061v1 Announce Type: cross Abstract: Impact sound rendering synthesizes the sound produced when a 3D object is struck, but practical renderers often rely on fixed material presets such a...
The paper introduces a pipeline that combines generated video and audio to produce force-aware manipulation trajectories for a Franka Panda robot. By using the loudness of contact sounds to shape a bounded, time-varying desired-force profile, the system can execute tasks that require precise contact forces, outperforming kinematic-only baselines. The approach also serves as a data generation engine for training closed-loop policies.
arXiv:2603. 07584v2 Announce Type: replace-cross Abstract: Computational engine sound modeling is central to the automotive audio industry, particularly for active sound design applications and virtual prototyping.
Recent advances in video generation allow robots to learn manipulation trajectories from generated videos. However, these approaches produce purely kinematic trajectories that lack force information,...
arXiv:2506. 20995v4 Announce Type: replace-cross Abstract: We propose a step-by-step video-to-audio (V2A) generation method that provides finer control over the generation process and more realistic audio synthesis.
arXiv:2512.23994v5 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to...
SsgCaps is a publicly available dataset of human-engineered sound scenes, each paired with a precisely structured prompt that guides the sampling process. The prompts are drawn from a predefined action-based typology, enabling extensive yet plausible sampling. A comparative quantitative analysis shows only small differences between the open and private versions, supporting the recommendation of the open version for benchmarking sound scene generation algorithms.
arXiv:2509. 15210v2 Announce Type: replace-cross Abstract: Realistic sound simulation plays a critical role in many applications.
arXiv:2608. 13724v1 Announce Type: cross Abstract: PLAUD (Performative Latents and Unsupervised DDSP) is a neural synthesizer and Max for Live instrument for live electronic music, built on NoiseBandNet and trained on small personal sound corpora.
The paper demonstrates that high linear decodability in continuous‑latent TTS does not guarantee causal controllability of speaker identity. In VoxCPM2, probes at the final residual acoustic language model layer show strong accuracy, yet aligned edits fail to produce target‑dominant dyads, whereas early‑position edits succeed. Cross‑architecture experiments reveal that backbone edits shift the source voice without attracting the target, while x‑vector ablation eliminates source similarity, underscoring the need for geometric specificity and a computational path that embeds the intended speaker condition into synthesis.
TAPE (Transformations of Audio Parameter Embeddings) is a system that learns to infer the signal‑processing chain applied to a reference audio recording and then applies the same chain to new material. It uses an encoder to map the processed reference to an embedding that a differentiable DSP decoder translates into editable parameters for equalization, compression, waveshaping, a residual network, and reverberation. Compared to prior methods, TAPE achieves lower spectral error while being 275× faster than exhaustive search and can run causally in real time on 128‑sample buffers.
arXiv:2607. 08863v1 Announce Type: cross Abstract: We present Clean2FX, a study and demo of label-conditioned clean-to-effect transformation for electric guitar audio.