User profiles for H. Eghbal-zadeh
Hamid EghbalzadehOther name: Hamid Eghbal-zadeh Meta Verified email at meta.com Cited by 1733 |
Efficient training of audio transformers with patchout
… 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 …
projects each input sample to h query Q, key K, and value V matrices, where h is the number of …
[PDF][PDF] CP-JKU submissions for DCASE-2016: a hybrid approach using binaural i-vectors and deep convolutional neural networks
H Eghbal-Zadeh, B Lehner, M Dorfer… - IEEE AASP Challenge …, 2016 - dcase.community
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 …
DCASE-2016 challenge of the CP-JKU team. We propose 4 different approaches for Audio Scene …
Large-scale weakly labeled semi-supervised sound event detection in domestic environments
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 …
detection of sound events using weakly labeled data (without time boundaries). The target of the …
The receptive field as a regularizer in deep convolutional neural networks for acoustic scene classification
K Koutini, H Eghbal-Zadeh, M Dorfer… - 2019 27th European …, 2019 - ieeexplore.ieee.org
… 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…
vision domain and achieved good performance in acoustic scene classification, using spec…
[HTML][HTML] Movie genome: alleviating new item cold start in movie recommendation
… 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 …
2015), and are used to capture acoustic scenes (Eghbal-Zadeh et al. 2016). Even though it is …
Receptive field regularization techniques for audio classification and tagging with deep convolutional neural networks
K Koutini, H Eghbal-zadeh… - IEEE/ACM Transactions …, 2021 - ieeexplore.ieee.org
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 (…
Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (…
History compression via language models in reinforcement learning
…, S Lehner, H Eghbal-Zadeh… - International …, 2022 - proceedings.mlr.press
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 …
representation of the past to approximate the underlying MDP. We propose to utilize a frozen …
[PDF][PDF] Acoustic scene classification with fully convolutional neural networks and I-vectors
…, B Lehner, H Eghbal-zadeh, H Christop… - Proceedings of the …, 2018 - dcase.community
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 …
Scene Classification, ASC) of the DCASE-2018 challenge. Our approach is still related to …
[PDF][PDF] CP-JKU submissions to DCASE'19: Acoustic scene classification and audio tagging with receptive-field-regularized CNNs
… 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 …
weakly-labeled semisupervised sound event detection,” in Proceedings of the Detection and …
[HTML][HTML] Feature-combination hybrid recommender systems for automated music playlist continuation
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 …
users with the increasingly larger music catalogs of on-line music streaming services, on-line …