REVIEW 4 cited by
SyncNet: correlating objective for time delay estimation in audio signals
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
This study addresses the task of performing robust and reliable time-delay estimation in signals in noisy and reverberating environments. In contrast to the popular signal processing based methods, this paper proposes to transform the input signals using a deep neural network into another pair of sequences which show high cross correlation at the actual time delay. This is achieved with the help of a novel correlation function based objective function for training the network. The proposed approach is also intrinsically interpretable as it does not lose temporal information. Experimental evaluations are performed for estimating mutual time delays for different types of audio signals such as pulse, speech and musical beats. SyncNet outperforms other classical approaches, such as GCC-PHAT, and some other learning based approaches.
Forward citations
Cited by 4 Pith papers
-
OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model
A zero-shot model that generates a video of a reference face speaking user-chosen text with a reference voice timbre.
-
SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
SpeakerVid-5M provides 5.2 million audio-visual human clips (8,743 hours) with rich annotations and a dyadic interaction benchmark for training interactive virtual humans.
-
OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
A 52.3M-clip human-centric video dataset with captions, skeletons, and audio, plus a LoRA training recipe, improves human video generation metrics when used to fine-tune a diffusion transformer.
-
GenSync: A Generalized Talking Head Framework for Audio-driven Multi-Subject Lip-Sync using 3D Gaussian Splatting
A single 3D Gaussian Splatting network learns to lip-sync multiple speakers from audio, matching per-speaker models in quality while training about 6.8x faster.
Discussion (0). Continue with ORCID to comment.