No abstract

No abstract

New theory is presented to calculate the entropy of a liquid of flexible molecules from a molecular dynamics simulation. Entropy is expressed in two terms: a vibrational term, representing the average number of configurations and momentum states in an energy well, and a topographical term, representing the effective number of energy wells. The vibrational term is derived in a hierarchical manner from two force-torque covariance matrices, one at the molecular level and one at the united-atom level. The topographical term comprises conformations and orientations, which are derived from the dihedral distributions and 1 coordination numbers, respectively. The method is tested on fourteen liquids, ranging from argon to cyclohexane. For most molecules our results lie within the experimental range, and are slightly higher than those by the 2PT method, the only other method currently capable of directly calculating entropy for such systems. As well as providing an efficient and practical way to calculate entropy, the theory serves to give a comprehensive characterization and quantification of molecular structure.

In this paper, we introduce a novel attentional similarity module for the problem of few-shot sound recognition. Given a few examples of an unseen sound event, a classifier must be quickly adapted to recognize the new sound event without much fine-tuning. The proposed attentional similarity module can be plugged into any metric-based learning method for few-shot learning, allowing the resulting model to especially match related short sound events. Extensive experiments on two datasets show that the proposed module consistently improves the performance of five different metricbased learning methods for few-shot sound recognition. The relative improvement ranges from +4.1% to +7.7% for 5-shot 5-way accuracy for the ESC-50 dataset, and from +2.1% to +6.5% for noiseESC-50. Qualitative results demonstrate that our method contributes in particular to the recognition of transient sound events.

No abstract

Making sense of the surrounding context and ongoing events through not only the visual inputs but also acoustic cues is critical for various AI applications. This paper presents an attempt to learn a neural network model that recognizes more than 500 different sound events from the audio part of user generated videos (UGV). Aside from the large number of categories and the diverse recording conditions found in UGV, the task is challenging because a sound event may occur only for a short period of time in a video clip. Our model specifically tackles this issue by combining a main subnet that aggregates information from the entire clip to make clip-level predictions, and a supplementary subnet that examines each short segment of the clip for segment-level predictions. As the labeled data available for model training are typically on the clip level, the latter subnet learns to pay attention to segments selectively to facilitate attentional segment-level supervision. We call our model the M&mnet, for it leverages both “M”acro (clip-level) supervision and “m”icro (segment-level) supervision derived from the macro one. Our experiments show that M&mnet works remarkably well for recognizing sound events, establishing a new state-of-theart for DCASE17 and AudioSet data sets. Qualitative analysis suggests that our model exhibits strong gains for short events. In addition, we show that the micro subnet is computationally light and we can use multiple micro subnets to better exploit information in different temporal scales.

No abstract

No abstract