Diamond Open Access - OA-Veröffentlichung ohne Publikationskosten (Sponsoring)
Refine
Year of publication
- 2022 (2) (remove)
Document Type
- conference proceeding (article) (2) (remove)
Language
- English (2)
Has Fulltext
- no (2)
Is part of the Bibliography
- no (2)
Keywords
- Industry 4.0 (1)
- audio-visual synchrony (1)
- cyber-physical system (1)
- decision support system (1)
- dubbing (1)
- purchasing (1)
- simulation (1)
- speech-lip synchrony (1)
- supply chain optimization, (1)
Institute
Begutachtungsstatus
- peer-reviewed (2)
Decision-making in supply chain management is complex because of the relations between planning tasks from different stages and planning levels. Uncertainties such as unpredictable supplier lead times and supply chain disruptions further complicate decision-making. Considering the case study of a company in printed circuit board assembly, a three-level concept is proposed that includes a decision support system. The global single-source supply network is characterized by highly variable lead times. Hence, the company maintains high inventory levels to prevent running out of stock. The decision support system considers the purchasing and scheduling decision problems in an integrated way. The prototypical implementation of the purchasing algorithm uses a genetic algorithm that recommends reorder days and order quantities using a simulation model. In addition, it evaluates the risks of the recommended solution by calculating the probability of stockouts for each order cycle.
We present a comprehensive analysis of the neural audio-visual synchrony evaluation tool SyncNet. We assess the agreement of SyncNet scores vis-a-vis human perception and whether we can use these as a reliable metric for evaluating audio-visual lip-synchrony in generation tasks with no ground truth reference audio-video pair. We further look into the underlying elements in audio and video which vitally affect synchrony using interpretable explanations from SyncNet predictions and analyse its susceptibility by introducing adversarial noise. SyncNet has been used in numerous papers on visually-grounded text-to-speech for scenarios such as dubbing. We focus on this scenario which features many local asynchronies (something that SyncNet isn’t made for).