Polyphonic sound event detection refers to the task of automatically identifying sound events occurring simultaneously in an auditory scene. Due to the inherent complexity and variability of real-world auditory scenes, building robust detectors for polyphonic sound event detection poses a significant challenge. The task becomes furthermore challenging without sufficient annotated data to develop sound event detection systems under a supervised learning regime. In this article, we explore the recent developments in polyphonic sound event detection, with a particular emphasis on the application of Teacher-Student techniques within the semi-supervised learning paradigm. Unlike previous works, we have consolidated and organized the fragmented literature on Teacher-Student techniques for polyphonic sound event detection. By examining the latest research, categorizing Teacher-Student approaches, and conducting an empirical study to assess the performance of each approach, this survey offers valuable insights and practical guidance for researchers and practitioners in the field. Our findings highlight the potential benefits of utilizing multiple learners, ensuring consistent predictions, and making thoughtful choices regarding perturbation strategies.

Ontology matching is an efficient method to establish interoperability among heterogeneous ontologies. Large-scale ontology matching still remains a big challenge for its long time and large memory space consumption. The actual solution to this problem is ontology partitioning which is also challenging. This paper presents DeepOM, an ontology matching system to deal with this large-scale heterogeneity problem without partitioning using deep learning techniques. It consists on creating semantic embeddings for concepts of input ontologies using a reference ontology, and use them to train an auto-encoder in order to learn more accurate and less dimensional representations for concepts. The experimental results of its evaluation on large ontologies, and its comparison with different ontology matching systems which have participated to the same test challenge, are very encouraging with a precision score of 0.99. They demonstrate the higher efficiency of the proposed system to increase the performance of the large-scale ontology matching task.

In spite of the undeniable success of the ontologies, where they have been widely applied successfully to represent the knowledge in lots of real-world problems, they cannot represent and reason with uncertain knowledge which inherently appears in most domains. To cope with this issue, this article presents a new approach for dealing with rich-uncertainty domains. In fact, it is mainly based on integrating hybrid models which combine both fuzzy logic and Bayesian networks. On the other hand, the Fuzzy multi-entity Bayesian network (FzMEBN) proposed as a hybrid model which enhances the classical multi-entity Bayesian network using fuzzy logic, it can be used to represent and reason with probabilistic and vague knowledge simultaneously. Thus, as a language belongs to the proposed approach, this study proposes a promising solution to overcome the weakness of the Probabilistic Ontology Web Language (PR-OWL) based on FzMEBN to allow dealing with vague and probabilistic knowledge in ontologies. The proposed extension is evaluated with a case study in the medical field (diabetes diseases).