Computational Analysis of Everyday Soundscapes

DCASE 2017 challenge setup: tasks, datasets and baseline system

Auteurs: Annamaria Mesaros, Toni Heittola, Aleksandr Diment, Benjamin Elizalde, Ankit Shah, Emmanuel Vincent, Bhiksha Raj, and Tuomas Virtanen
Publié dans: Proceedings of the Workshop on Detection and Classification of Sound Scenes and Events, 2017
Éditeur: Tampere University of Technology

Convolutional recurrent neural networks for bird audio detection

Auteurs: Emre Cakir, Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos, Tuomas Virtanen
Publié dans: 2017 25th European Signal Processing Conference (EUSIPCO), 2017, Page(s) 1744-1748, ISBN 978-0-9928626-7-1
Éditeur: IEEE
DOI: 10.23919/eusipco.2017.8081508

Assessment of human and machine performance in acoustic scene classification: Dcase 2016 case study

Auteurs: Annamaria Mesaros, Toni Heittola, Tuomas Virtanen
Publié dans: 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2017, Page(s) 319-323, ISBN 978-1-5386-1632-1
Éditeur: IEEE
DOI: 10.1109/waspaa.2017.8170047

Active learning for sound event classification by clustering unlabeled data

Auteurs: Zhao Shuyang, Toni Heittola, Tuomas Virtanen
Publié dans: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Page(s) 751-755, ISBN 978-1-5090-4117-6
Éditeur: IEEE
DOI: 10.1109/icassp.2017.7952256

Stacked convolutional and recurrent neural networks for bird audio detection

Auteurs: Sharath Adavanne, Konstantinos Drossos, Emre Cakir, Tuomas Virtanen
Publié dans: 2017 25th European Signal Processing Conference (EUSIPCO), 2017, Page(s) 1729-1733, ISBN 978-0-9928626-7-1
Éditeur: IEEE
DOI: 10.23919/eusipco.2017.8081505

Convolutional Recurrent Neural Networks for Rare Sound Event Detection

Auteurs: Emre Cakir and Tuomas Virtanen
Publié dans: Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events 2017 (DCASE 2017), 2017
Éditeur: Tampere University of Technology

Sound event detection using spatial features and convolutional recurrent neural network

Auteurs: Sharath Adavanne, Pasi Pertila, Tuomas Virtanen
Publié dans: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Page(s) 771-775, ISBN 978-1-5090-4117-6
Éditeur: IEEE
DOI: 10.1109/icassp.2017.7952260

Learning vocal mode classifiers from heterogeneous data sources

Auteurs: Zhao Shuyang, Toni Heittola, Tuomas Virtanen
Publié dans: 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2017, Page(s) 16-20, ISBN 978-1-5386-1632-1
Éditeur: IEEE
DOI: 10.1109/waspaa.2017.8169986

Automated audio captioning with recurrent neural networks

Auteurs: Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen
Publié dans: 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2017, Page(s) 374-378, ISBN 978-1-5386-1632-1
Éditeur: IEEE
DOI: 10.1109/waspaa.2017.8170058

Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network

Auteurs: Sharath Adavanne and Tuomas Virtanen
Publié dans: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017), 2017
Éditeur: Tampere University of Technology

Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features

Auteurs: Sharath Adavanne, Giambattista Parascandolo, Pasi Pertila, Toni Heittola, Tuomas Virtanen
Publié dans: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016), 2016, ISBN 978-952-15-3807-0
Éditeur: Tampere University of Technology. Department of Signal Processing

TUT database for acoustic scene classification and sound event detection

Auteurs: Annamaria Mesaros, Toni Heittola, Tuomas Virtanen
Publié dans: 2016 24th European Signal Processing Conference (EUSIPCO), 2016, Page(s) 1128-1132, ISBN 978-0-9928-6265-7
Éditeur: IEEE
DOI: 10.1109/EUSIPCO.2016.7760424

DCASE 2016 Acoustic Scene Classification Using Convolutional Neural Networks

Auteurs: Michele Valenti, Aleksandr Diment, Giambattista Parascandolo, Stefano Squartini, Tuomas Virtanen
Publié dans: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016), 2016, ISBN 978-952-15-3807-0
Éditeur: Tampere University of Technology. Department of Signal Processing

Filterbank learning for deep neural network based polyphonic sound event detection

Auteurs: Emre Cakir, Ezgi Can Ozan, Tuomas Virtanen
Publié dans: 2016 International Joint Conference on Neural Networks (IJCNN), 2016, Page(s) 3399-3406, ISBN 978-1-5090-0620-5
Éditeur: IEEE
DOI: 10.1109/IJCNN.2016.7727634

A multi-device dataset for urban acoustic scene classification

Auteurs: Mesaros, Annamaria; Heittola, Toni; Virtanen, Tuomas
Publié dans: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop, Numéro 1, 2018
Éditeur: Tampere University of Technology

Direction of Arrival Estimation for Multiple Sound Sources Using Convolutional Recurrent Neural Network

Auteurs: Sharath Adavanne, Archontis Politis, Tuomas Virtanen
Publié dans: 2018 26th European Signal Processing Conference (EUSIPCO), 2018, Page(s) 1462-1466, ISBN 978-9-0827-9701-5
Éditeur: IEEE
DOI: 10.23919/eusipco.2018.8553182

Unsupervised Adversarial Domain Adaptation Based on The Wasserstein Distance For Acoustic Scene Classification

Auteurs: Konstantinos Drossos, Paul Magron, Tuomas Virtanen
Publié dans: 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2019, Page(s) 259-263, ISBN 978-1-7281-1123-0
Éditeur: IEEE
DOI: 10.1109/waspaa.2019.8937231

Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features

Auteurs: Sharath Adavanne, Archontis Politis, Tuomas Virtanen
Publié dans: 2018 International Joint Conference on Neural Networks (IJCNN), 2018, Page(s) 1-7, ISBN 978-1-5090-6014-6
Éditeur: IEEE
DOI: 10.1109/IJCNN.2018.8489542

End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input

Auteurs: Emre Cakir, Tuomas Virtanen
Publié dans: 2018 International Joint Conference on Neural Networks (IJCNN), 2018, Page(s) 1-7, ISBN 978-1-5090-6014-6
Éditeur: IEEE
DOI: 10.1109/ijcnn.2018.8489470

A multi-room reverberant dataset for sound event localization and detection

Auteurs: Adavanne, Sharath; Politis, Archontis; Virtanen, Tuomas
Publié dans: Proceedings of Workshop on Detection and Classification of Acoustic Scenes and Events 2019, Numéro 1, 2019
Éditeur: New York University

Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling

Auteurs: Konstantinos Drossos, Shayan Gharib, Paul Magron, Tuomas Virtanen
Publié dans: Proceedings of Workshop on Detection and Classification of Acoustic Scenes and Events 2019, 2019
Éditeur: New York University

Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition

Auteurs: Miroslav Malik, Sharath Adavanne, Konstantinos Drossos, Tuomas Virtanen, Dasa Ticha, Roman Jarina
Publié dans: Proceedings of the 14th Sound and Music Computing Conference, 2017, 2017
Éditeur: Aalto University

Unsupervised adversarial domain adaptation for acoustic scene classification

Auteurs: Gharib, Shayan; Drossos, Konstantinos; Çakir, Emre; Serdyuk, Dmitriy; Virtanen, Tuomas
Publié dans: Proceedings of Workshop on Detection and Classification of Acoustic Scenes and Events 2018, Numéro 1, 2018
Éditeur: Tampere University of Technology

Close Miking Empirical Practice Verification: A Source Separation Approach

Auteurs: Konstantinos Drossos, Stylianos Ioannis Mimilakis, Andreas Floros, Tuomas Virtanen, Gerald Schuller
Publié dans: In proceedings Audio Engineering Society 142th Convention, 2017
Éditeur: Audio Engineering Society

A recurrent encoder-decoder approach with skip-filtering connections for monaural singing voice separation

Auteurs: Stylianos Ioannis Mimilakis, Konstantinos Drossos, Tuomas Virtanen, Gerald Schuller
Publié dans: 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), 2017, Page(s) 1-6, ISBN 978-1-5090-6341-3
Éditeur: IEEE
DOI: 10.1109/MLSP.2017.8168117

Harmonic-Percussive Source Separation with Deep Neural Networks and Phase Recovery

Auteurs: Konstantinos Drossos, Paul Magron, Stylianos Ioannis Mimilakis, Tuomas Virtanen
Publié dans: 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), 2018, Page(s) 421-425, ISBN 978-1-5386-8151-0
Éditeur: IEEE
DOI: 10.1109/iwaenc.2018.8521371

Reducing Interference with Phase Recovery in DNN-based Monaural Singing Voice Separation

Auteurs: Paul Magron, Konstantinos Drossos, Stylianos Ioannis Mimilakis, Tuomas Virtanen
Publié dans: Interspeech 2018, 2018, Page(s) 332-336
Éditeur: ISCA
DOI: 10.21437/interspeech.2018-1845

City Classification from Multiple Real-World Sound Scenes

Auteurs: Helen L. Bear, Toni Heittola, Annamaria Mesaros, Emmanouil Benetos, Tuomas Virtanen
Publié dans: 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2019, Page(s) 11-15, ISBN 978-1-7281-1123-0
Éditeur: IEEE
DOI: 10.1109/waspaa.2019.8937271

ACOUSTIC SCENE CLASSIFICATION: A COMPETITION REVIEW

Auteurs: Shayan Gharib, Honain Derrar, Daisuke Niizumi, Tuukka Senttula, Janne Tommola, Toni Heittola, Tuomas Virtanen, Heikki Huttunen
Publié dans: 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP), 2018, Page(s) 1-6, ISBN 978-1-5386-5477-4
Éditeur: IEEE
DOI: 10.1109/mlsp.2018.8517000

Acoustic scene classification in DCASE 2019 Challenge: closed and open set classification and data mismatch setups

Auteurs: Annamaria Mesaros, Toni Heittola, Tuomas Virtanen
Publié dans: Proceedings of Workshop on Detection and Classification of Acoustic Scenes and Events 2019, 2019
Éditeur: New York University

Crowdsourcing a Dataset of Audio Captions

Auteurs: Samuel Lipping, Konstantinos Drossos, Tuomas Virtanen
Publié dans: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop, 2019
Éditeur: New York University

Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network

Auteurs: Sharath Adavanne, Archontis Politis, Tuomas Virtanen
Publié dans: Proceedings of Workshop on Detection and Classification of Acoustic Scenes and Events, 2019., 2019
Éditeur: New York University

Zero-Shot Audio Classification Based On Class Label Embeddings

Auteurs: Huang Xie, Tuomas Virtanen
Publié dans: 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2019, Page(s) 264-267, ISBN 978-1-7281-1123-0
Éditeur: IEEE
DOI: 10.1109/waspaa.2019.8937283

Sound Event Envelope Estimation in Polyphonic Mixtures

Auteurs: Irene Martin-Morato, Annamaria Mesaros, Toni Heittola, Tuomas Virtanen, Maximo Cobos, Francesc J. Ferri
Publié dans: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 935-939, ISBN 978-1-4799-8131-1
Éditeur: IEEE
DOI: 10.1109/icassp.2019.8682858

Joint Measurement of Localization and Detection of Sound Events

Auteurs: Annamaria Mesaros, Sharath Adavanne, Archontis Politis, Toni Heittola, Tuomas Virtanen
Publié dans: 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2019, Page(s) 333-337, ISBN 978-1-7281-1123-0
Éditeur: IEEE
DOI: 10.1109/waspaa.2019.8937220

Acoustic Scene Classification: An Overview of Dcase 2017 Challenge Entries

Auteurs: Annamaria Mesaros, Toni Heittola, Tuomas Virtanen
Publié dans: 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), 2018, Page(s) 411-415, ISBN 978-1-5386-8151-0
Éditeur: IEEE
DOI: 10.1109/iwaenc.2018.8521242

Using Sequential Information in Polyphonic Sound Event Detection

Auteurs: Guangpu Huang, Toni Heittola, Tuomas Virtanen
Publié dans: 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), 2018, Page(s) 291-295, ISBN 978-1-5386-8151-0
Éditeur: IEEE
DOI: 10.1109/iwaenc.2018.8521367

An Active Learning Method Using Clustering and Committee-Based Sample Selection for Sound Event Classification

Auteurs: Zhao Shuyang, Toni Heittola, Tuomas Virtanen
Publié dans: 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), 2018, Page(s) 116-120, ISBN 978-1-5386-8151-0
Éditeur: IEEE
DOI: 10.1109/iwaenc.2018.8521336

Sound Event Detection with Depthwise Separable and Dilated Convolutions

Auteurs: Konstantinos Drossos, Stylianos I. Mimilakis, Shayan Gharib, Yanxiong Li, Tuomas Virtanen
Publié dans: In proceedings of International Joint Conference on Neural Networks, 2020., 2020
Éditeur: IEEE

Clotho: an Audio Captioning Dataset

Auteurs: Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen
Publié dans: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 736-740, ISBN 978-1-5090-6631-5
Éditeur: IEEE
DOI: 10.1109/icassp40776.2020.9052990

Sound Event Detection Via Dilated Convolutional Recurrent Neural Networks

Auteurs: Yanxiong Li, Mingle Liu, Konstantinos Drossos, Tuomas Virtanen
Publié dans: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 286-290, ISBN 978-1-5090-6631-5
Éditeur: IEEE
DOI: 10.1109/icassp40776.2020.9054433

Frequency-Dependent Directional Feedback Delay Network

Auteurs: Benoit Alary, Archontis Politis
Publié dans: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 176-180, ISBN 978-1-5090-6631-5
Éditeur: IEEE
DOI: 10.1109/icassp40776.2020.9054717

Computational Analysis of Sound Scenes and Events

Auteurs: Tuomas Virtanen, Mark D. Plumbley, Dan Ellis
Publié dans: 2018, ISBN 978-3-319-63450-0
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-63450-0

Proceedings of the detection and classification of acoustic scenes and events 2016 workshop (DCASE2016)

Auteurs: Tuomas Virtanen, Annamaria Mesaros, Toni Heittola, Mark D. Plumbley, Peter Foster, Emmanouil Benetos, and Mathieu Lagrange. (Eds.)
Publié dans: 2016
Éditeur: Tampere University of Technology

Proceedings of the detection and classification of acoustic scenes and events 2017 workshop (DCASE2017)

Auteurs: Tuomas Virtanen, Annamaria Mesaros, Toni Heittola, Aleksandr Diment, Emmanuel Vincent, Emmanouil Benetos, and Benjamin Martinez Elizalde. (Eds.)
Publié dans: 2017
Éditeur: Tampere University of Technology

The Machine Learning Approach for Analysis of Sound Scenes and Events

Auteurs: Toni Heittola, Emre Çakır, Tuomas Virtanen
Publié dans: Computational Analysis of Sound Scenes and Events, 2018, Page(s) 13-40
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-63450-0_2

Datasets and Evaluation

Auteurs: Annamaria Mesaros, Toni Heittola, Dan Ellis
Publié dans: Computational Analysis of Sound Scenes and Events, 2018, Page(s) 147-179
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-63450-0_6

Environmental noise monitoring using source classification in sensors

Auteurs: Panu Maijala, Zhao Shuyang, Toni Heittola, Tuomas Virtanen
Publié dans: Applied Acoustics, Numéro 129, 2018, Page(s) 258-267, ISSN 0003-682X
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.apacoust.2017.08.006

Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge

Auteurs: Annamaria Mesaros, Toni Heittola, Emmanouil Benetos, Peter Foster, Mathieu Lagrange, Tuomas Virtanen, Mark D. Plumbley
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 26/2, 2018, Page(s) 379-393, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2017.2778423

Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Auteurs: Emre Cakir, Giambattista Parascandolo, Toni Heittola, Heikki Huttunen, Tuomas Virtanen
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 25/6, 2017, Page(s) 1291-1303, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2017.2690575

Metrics for Polyphonic Sound Event Detection

Auteurs: Annamaria Mesaros, Toni Heittola, Tuomas Virtanen
Publié dans: Applied Sciences, Numéro 6, 2016, ISSN 2076-3417
Éditeur: Multidisciplinary Digital Publishing Institute
DOI: 10.3390/app6060162

On the Impact of The Semantic Content of Sound Events in Emotion Elicitation

Auteurs: Konstantinos Drossos, Maximos Kaliakatsos-Papakostas, Andreas Floros, Tuomas Virtanen
Publié dans: Journal of the Audio Engineering Society, Numéro 64/7/8, 2016, Page(s) 525-532, ISSN 1549-4950
Éditeur: Audio Engineering Society
DOI: 10.17743/jaes.2016.0024

Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks

Auteurs: Sharath Adavanne, Archontis Politis, Joonas Nikunen, Tuomas Virtanen
Publié dans: IEEE Journal of Selected Topics in Signal Processing, Numéro 13/1, 2019, Page(s) 34-48, ISSN 1932-4553
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/JSTSP.2018.2885636

Sound Event Detection in the DCASE 2017 Challenge

Auteurs: Annamaria Mesaros, Aleksandr Diment, Benjamin Elizalde, Toni Heittola, Emmanuel Vincent, Bhiksha Raj, Tuomas Virtanen
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 27/6, 2019, Page(s) 992-1006, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/TASLP.2019.2907016

Deep Learning for Audio Signal Processing

Auteurs: Hendrik Purwins, Bo Li, Tuomas Virtanen, Jan Schluter, Shuo-Yiin Chang, Tara Sainath
Publié dans: IEEE Journal of Selected Topics in Signal Processing, Numéro 13/2, 2019, Page(s) 206-219, ISSN 1932-4553
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/jstsp.2019.2908700

Publications

Partager cette page

Télécharger