Filters








7 Hits in 5.3 sec

A Joint Framework for Audio Tagging and Weakly Supervised Acoustic Event Detection Using DenseNet with Global Average Pooling [article]

Chieh-Chi Kao, Bowen Shi, Ming Sun, Chao Wang
2020 arXiv   pre-print
This paper proposes a network architecture mainly designed for audio tagging, which can also be used for weakly supervised acoustic event detection (AED).  ...  The proposed network consists of a modified DenseNet as the feature extractor, and a global average pooling (GAP) layer to predict frame-level labels at inference time.  ...  Layers DenseNet-63 DenseNet-120 (for DCASE2017) (for DCASE2018) Convolution 7 × 7 conv, stride 2 Dense Block (1) 1 : DenseNet architectures for audio tagging and weakly supervised acoustic event detection  ... 
arXiv:2008.03350v1 fatcat:osbobruvjzci5pvqp4mlr2l46i

A Joint Framework for Audio Tagging and Weakly Supervised Acoustic Event Detection Using DenseNet with Global Average Pooling

Chieh-Chi Kao, Bowen Shi, Ming Sun, Chao Wang
2020 Interspeech 2020  
This paper proposes a network architecture mainly designed for audio tagging, which can also be used for weakly supervised acoustic event detection (AED).  ...  The proposed network consists of a modified DenseNet as the feature extractor, and a global average pooling (GAP) layer to predict frame-level labels at inference time.  ...  DenseNet architectures for audio tagging and weakly supervised acoustic event detection.  ... 
doi:10.21437/interspeech.2020-2791 dblp:conf/interspeech/KaoSSW20 fatcat:mhmkkbq55rggngiwiczujaq3ee

A State-of-the-Art Survey on Deep Learning Theory and Architectures

Md Zahangir Alom, Tarek M. Taha, Chris Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Mahmudul Hasan, Brian C. Van Essen, Abdul A. S. Awwal, Vijayan K. Asari
2019 Electronics  
We also included recently developed frameworks, SDKs, and benchmark datasets that are used for implementing and evaluating deep learning approaches.  ...  There are some surveys that have been published on DL using neural networks and a survey on Reinforcement Learning (RL).  ...  Acknowledgments: We would like to thank all authors mentioned in the reference of this paper from whom we have learned a lot and thus made this review paper possible.  ... 
doi:10.3390/electronics8030292 fatcat:2i64q7g6kjbjvfalvzwgiggnyq

The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches [article]

Md Zahangir Alom, Tarek M. Taha, Christopher Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Brian C Van Esesn, Abdul A S. Awwal, Vijayan K. Asari
2018 arXiv   pre-print
We have also comprised recently developed frameworks, SDKs, and benchmark datasets that are used for implementing and evaluating deep learning approaches.  ...  There are different methods have been proposed on different category of learning approaches, which includes supervised, semi-supervised and un-supervised learning.  ...  Doctoral research scientist on deep Learning, computer vision for remote sensing and hyper spectral imaging (e-mail: pehedings@slu.edu). Brian C Van Esesn 3 and Abdul A S.  ... 
arXiv:1803.01164v2 fatcat:eo353y77tvckbdjcfexpaadeh4

Deep Learning in Mobile and Wireless Networking: A Survey

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 IEEE Communications Surveys and Tutorials  
We complete this survey by pinpointing current challenges and open future directions for research.  ...  We first briefly introduce essential background and state-of-theart in deep learning techniques with potential applications to networking.  ...  Their proposal accepts acoustic signals as input, allowing users to register different acoustic events of interest.  ... 
doi:10.1109/comst.2019.2904897 fatcat:xmmrndjbsfdetpa5ef5e3v4xda

Deep Learning in Mobile and Wireless Networking: A Survey [article]

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 arXiv   pre-print
We complete this survey by pinpointing current challenges and open future directions for research.  ...  We first briefly introduce essential background and state-of-the-art in deep learning techniques with potential applications to networking.  ...  Their proposal accepts acoustic signals as input, allowing users to register different acoustic events of interest.  ... 
arXiv:1803.04311v3 fatcat:awuvyviarvbr5kd5ilqndpfsde

Affect recognition & generation in-the-wild

Dimitrios Kollias, Stefanos Zafeiriou
2021
Then we use AffWildNet as a robust prior for dimensional and categorical affect recognition and extend it by extracting low-/mid-/high-level latent information and analysing this via multiple RNNs.  ...  We generate an image with a given affect, or a sequence of images with evolving affect, by annotating a 4-D database a [...]  ...  ANet is a VGG16 network with average pooling and accepts as input STFT maps extracted from the audio.  ... 
doi:10.25560/87156 fatcat:cuh7si4f7bao7c3jsousrulbla