… n is the input sequence length, e is the embeddings size, each multi-head attention layer
projects each input sample to h query Q, key K, and value V matrices, where h is the number of …

This report describes the 4 submissions for Task 1 (Audio scene classification) of the
DCASE-2016 challenge of the CP-JKU team. We propose 4 different approaches for Audio Scene …

This paper presents DCASE 2018 task 4. The task evaluates systems for the large-scale
detection of sound events using weakly labeled data (without time boundaries). The target of the …

… For instance, Eghbal-zadeh et al. [4] adapted the VGG architecture taken from the computer
vision domain and achieved good performance in acoustic scene classification, using spec…

… the spectral envelope are also a musically meaningful representation (Eghbal-Zadeh et al.
2015), and are used to capture acoustic scenes (Eghbal-Zadeh et al. 2016). Even though it is …

In this paper, we study the performance of variants of well-known Convolutional Neural
Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (…

In a partially observable Markov decision process (POMDP), an agent typically uses a
representation of the past to approximate the underlying MDP. We propose to utilize a frozen …

This technical report describes the CP-JKU team’s submissions for Task 1-Subtask A (Acoustic
Scene Classification, ASC) of the DCASE-2018 challenge. Our approach is still related to …

… Koutini, H. Eghbal-zadeh, and G. Widmer, “Iterative knowledge distillation in R-CNNs for
weakly-labeled semisupervised sound event detection,” in Proceedings of the Detection and …

Music recommender systems have become a key technology to support the interaction of
users with the increasingly larger music catalogs of on-line music streaming services, on-line …