Konstantinos Drossos

98 papers A 3B 3C 4Misc 7Journal 51Unranked 30

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Discriminating real and synthetic super-resolved audio samples using embedding-based classifiers. CoRR Mikhail Silaev, Konstantinos Drossos, Tuomas Virtanen
2026	J	`jnl`	Moving Speaker Separation via Parallel Spectral-Spatial Processing. CoRR Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2025	A	`conf`	Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers. INTERSPEECH Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2025	J	`jnl`	Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers. CoRR Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2025	Misc	`conf`	Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays. ICASSP Mikko Heikkinen, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2025	J	`jnl`	Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays. CoRR Mikko Heikkinen, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2025	J	`jnl`	Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance. CoRR Diep Luong, Mikko Heikkinen, Konstantinos Drossos, Tuomas Virtanen
2025	C	`conf`	Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns. MMSP Konstantinos Drossos, Mikko Heikkinen, Paschalis Tsiaflakis
2025	J	`jnl`	Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns. CoRR Konstantinos Drossos, Mikko Heikkinen, Paschalis Tsiaflakis
2025	—	`conf`	Multi-Utterance Speech Separation and Association Trained on Short Segments. WASPAA Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2025	J	`jnl`	Multi-Utterance Speech Separation and Association Trained on Short Segments. CoRR Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
2023	J	`jnl`	Adversarial Representation Learning for Robust Privacy Preservation in Audio. CoRR Shayan Gharib, Minh Tran, Diep Luong, Konstantinos Drossos, Tuomas Virtanen
2023	J	`jnl`	Development of a speech emotion recognizer for large-scale child-centered audio recordings from a hospital environment. Speech Commun. Einari Vaaras, Sari Ahlqvist-Björkroth, Konstantinos Drossos, Liisa Lehtonen, Okko Räsänen
2023	—	`conf`	Representation Learning for Audio Privacy Preservation Using Source Separation and Robust Adversarial Learning. WASPAA Diep Luong, Minh Tran, Shayan Gharib, Konstantinos Drossos, Tuomas Virtanen
2023	J	`jnl`	Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning. CoRR Diep Luong, Minh Tran, Shayan Gharib, Konstantinos Drossos, Tuomas Virtanen
2022	—	`conf`	Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering. EUSIPCO Samuel Lipping, Parthasaarathy Sudarsanam, Konstantinos Drossos, Tuomas Virtanen
2022	J	`jnl`	Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering. CoRR Samuel Lipping, Parthasaarathy Sudarsanam, Konstantinos Drossos, Tuomas Virtanen
2022	C	`conf`	Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network. MMSP Yanxiong Li, Wenchang Cao, Konstantinos Drossos, Tuomas Virtanen
2022	J	`jnl`	Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network. CoRR Yanxiong Li, Wenchang Cao, Konstantinos Drossos, Tuomas Virtanen
2022	Misc	`conf`	Unsupervised Audio-Caption Aligning Learns Correspondences Between Individual Sound Events and Textual Phrases. ICASSP Huang Xie, Okko Räsänen, Konstantinos Drossos, Tuomas Virtanen
2021	—	`conf`	Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection. DCASE Parthasaarathy Sudarsanam, Archontis Politis, Konstantinos Drossos
2021	J	`jnl`	Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection. CoRR Parthasaarathy Sudarsanam, Archontis Politis, Konstantinos Drossos
2021	A	`conf`	Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit. Interspeech Einari Vaaras, Sari Ahlqvist-Björkroth, Konstantinos Drossos, Okko Räsänen
2021	J	`jnl`	Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit. CoRR Einari Vaaras, Sari Ahlqvist-Björkroth, Konstantinos Drossos, Okko Räsänen
2021	J	`jnl`	Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach. CoRR Jan Berg, Konstantinos Drossos
2021	—	`conf`	Continual Learning for Automated Audio Captioning Using the Learning without Forgetting Approach. DCASE Jan Berg, Konstantinos Drossos
2021	J	`jnl`	Enriched Music Representations With Multiple Cross-Modal Contrastive Learning. IEEE Signal Process. Lett. Andres Ferraro, Xavier Favory, Konstantinos Drossos, Yuntae Kim, Dmitry Bogdanov
2021	J	`jnl`	Enriched Music Representations with Multiple Cross-modal Contrastive Learning. CoRR Andres Ferraro, Xavier Favory, Konstantinos Drossos, Yuntae Kim, Dmitry Bogdanov
2021	—	`conf`	Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning. DCASE Benno Weck, Xavier Favory, Konstantinos Drossos, Xavier Serra
2021	J	`jnl`	Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning. CoRR Benno Weck, Xavier Favory, Konstantinos Drossos, Xavier Serra
2021	—	`conf`	Fairness and Underspecification in Acoustic Scene Classification: The Case for Disaggregated Evaluations. DCASE Andreas Triantafyllopoulos, Manuel Milling, Konstantinos Drossos, Björn W. Schuller
2021	J	`jnl`	Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations. CoRR Andreas Triantafyllopoulos, Manuel Milling, Konstantinos Drossos, Björn W. Schuller
2021	Misc	`conf`	Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags. ICASSP Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra
2021	J	`jnl`	Towards Citizen Science for Smart Cities: A Framework for a Collaborative Game of Bird Call Recognition Based on Internet of Sound Practices. CoRR Emmanuel Rovithis, Nikolaos Moustakas, Konstantinos Vogklis, Konstantinos Drossos, Andreas Floros
2021	B	`conf`	Towards Sonification in Multimodal and User-friendlyExplainable Artificial Intelligence. ICMI Björn W. Schuller, Tuomas Virtanen, Maria Riveiro, Georgios Rizos, Jing Han, Annamaria Mesaros, Konstantinos Drossos
2021	—	`conf`	WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information. EUSIPCO An Tran, Konstantinos Drossos, Tuomas Virtanen
2020	J	`jnl`	COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations. CoRR Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra
2020	Misc	`conf`	Clotho: an Audio Captioning Dataset. ICASSP Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen
2020	J	`jnl`	Conditioned Time-Dilated Convolutions for Sound Event Detection. CoRR Konstantinos Drossos, Stylianos Ioannis Mimilakis, Tuomas Virtanen
2020	C	`conf`	Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation. MMSP Pyry Pyykkönen, Stylianos I. Mimilakis, Konstantinos Drossos, Tuomas Virtanen
2020	J	`jnl`	Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation. CoRR Pyry Pyykkönen, Stylianos Ioannis Mimilakis, Konstantinos Drossos, Tuomas Virtanen
2020	J	`jnl`	Examining the Mapping Functions of Denoising Autoencoders in Singing Voice Separation. IEEE ACM Trans. Audio Speech Lang. Process. Stylianos Ioannis Mimilakis, Konstantinos Drossos, Estefanía Cano, Gerald Schuller
2020	J	`jnl`	Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags. CoRR Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra
2020	—	`conf`	Memory Requirement Reduction of Deep Neural Networks for Field Programmable Gate Arrays Using Low-Bit Quantization of Parameters. EUSIPCO Niccolò Nicodemo, Gaurav Naithani, Konstantinos Drossos, Tuomas Virtanen, Roberto Saletti
2020	—	`conf`	Multi-Task Regularization Based on Infrequent Classes for Audio Captioning. DCASE Emre Çakir, Konstantinos Drossos, Tuomas Virtanen
2020	J	`jnl`	Multi-task Regularization Based on Infrequent Classes for Audio Captioning. CoRR Emre Çakir, Konstantinos Drossos, Tuomas Virtanen
2020	C	`conf`	Multichannel Singing Voice Separation by Deep Neural Network Informed DOA Constrained CMNMF. MMSP Antonio Jesús Muñoz-Montoro, Archontis Politis, Konstantinos Drossos, Julio J. Carabias-Orti
2020	J	`jnl`	Multichannel Singing Voice Separation by Deep Neural Network Informed DOA Constrained CNMF. CoRR Antonio Jesús Muñoz-Montoro, Julio J. Carabias-Orti, Archontis Politis, Konstantinos Drossos
2020	J	`jnl`	Revisiting Representation Learning for Singing Voice Separation with Sinkhorn Distances. CoRR Stylianos Ioannis Mimilakis, Konstantinos Drossos, Gerald Schuller
2020	Misc	`conf`	Sound Event Detection Via Dilated Convolutional Recurrent Neural Networks. ICASSP Yanxiong Li, Mingle Liu, Konstantinos Drossos, Tuomas Virtanen
2020	B	`conf`	Sound Event Detection with Depthwise Separable and Dilated Convolutions. IJCNN Konstantinos Drossos, Stylianos I. Mimilakis, Shayan Gharib, Yanxiong Li, Tuomas Virtanen
2020	J	`jnl`	Sound Event Detection with Depthwise Separable and Dilated Convolutions. CoRR Konstantinos Drossos, Stylianos Ioannis Mimilakis, Shayan Gharib, Yanxiong Li, Tuomas Virtanen
2020	—	`conf`	Temporal Sub-Sampling of Audio Feature Sequences for Automated Audio Captioning. DCASE Khoa Nguyen, Konstantinos Drossos, Tuomas Virtanen
2020	J	`jnl`	Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning. CoRR Khoa Nguyen, Konstantinos Drossos, Tuomas Virtanen
2020	—	`conf`	Unsupervised Interpretable Representation Learning for Singing Voice Separation. EUSIPCO Stylianos I. Mimilakis, Konstantinos Drossos, Gerald Schuller
2020	J	`jnl`	Unsupervised Interpretable Representation Learning for Singing Voice Separation. CoRR Stylianos Ioannis Mimilakis, Konstantinos Drossos, Gerald Schuller
2020	J	`jnl`	WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information. CoRR An Tran, Konstantinos Drossos, Tuomas Virtanen
2019	J	`jnl`	Clotho: An Audio Captioning Dataset. CoRR Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen
2019	—	`conf`	Crowdsourcing a Dataset of Audio Captions. DCASE Samuel Lipping, Konstantinos Drossos, Tuomas Virtanen
2019	J	`jnl`	Crowdsourcing a Dataset of Audio Captions. CoRR Samuel Lipping, Konstantinos Drossos, Tuomas Virtanen
2019	J	`jnl`	Examining the Mapping Functions of Denoising Autoencoders in Music Source Separation. CoRR Stylianos Ioannis Mimilakis, Konstantinos Drossos, Estefanía Cano, Gerald Schuller
2019	—	`conf`	Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling. DCASE Konstantinos Drossos, Shayan Gharib, Paul Magron, Tuomas Virtanen
2019	J	`jnl`	Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling. CoRR Konstantinos Drossos, Shayan Gharib, Paul Magron, Tuomas Virtanen
2019	J	`jnl`	Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters. CoRR Niccolò Nicodemo, Gaurav Naithani, Konstantinos Drossos, Tuomas Virtanen, Roberto Saletti
2019	J	`jnl`	Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification. CoRR Konstantinos Drossos, Paul Magron, Tuomas Virtanen
2019	—	`conf`	Unsupervised Adversarial Domain Adaptation Based on The Wasserstein Distance For Acoustic Scene Classification. WASPAA Konstantinos Drossos, Paul Magron, Tuomas Virtanen
2019	J	`jnl`	VOICe: A Sound Event Detection Dataset For Generalizable Domain Adaptation. CoRR Shayan Gharib, Konstantinos Drossos, Eemi Fagerlund, Tuomas Virtanen
2018	J	`jnl`	Close Miking Empirical Practice Verification: A Source Separation Approach. CoRR Konstantinos Drossos, Stylianos Ioannis Mimilakis, Andreas Floros, Tuomas Virtanen, Gerald Schuller
2018	Misc	`conf`	Examining the Perceptual Effect of Alternative Objective Functions for Deep Learning Based Music Source Separation. ACSSC Stylianos Ioannis Mimilakis, Estefanía Cano, Derry FitzGerald, Konstantinos Drossos, Gerald Schuller
2018	—	`conf`	Harmonic-Percussive Source Separation with Deep Neural Networks and Phase Recovery. IWAENC Konstantinos Drossos, Paul Magron, Stylianos Ioannis Mimilakis, Tuomas Virtanen
2018	J	`jnl`	Harmonic-Percussive Source Separation with Deep Neural Networks and Phase Recovery. CoRR Konstantinos Drossos, Paul Magron, Stylianos Ioannis Mimilakis, Tuomas Virtanen
2018	B	`conf`	MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation. IJCNN Konstantinos Drossos, Stylianos Ioannis Mimilakis, Dmitriy Serdyuk, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio
2018	J	`jnl`	MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation. CoRR Konstantinos Drossos, Stylianos Ioannis Mimilakis, Dmitriy Serdyuk, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio
2018	Misc	`conf`	Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask. ICASSP Stylianos Ioannis Mimilakis, Konstantinos Drossos, João Felipe Santos, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio
2018	A	`conf`	Reducing Interference with Phase Recovery in DNN-based Monaural Singing Voice Separation. INTERSPEECH Paul Magron, Konstantinos Drossos, Stylianos Ioannis Mimilakis, Tuomas Virtanen
2018	—	`conf`	Unsupervised adversarial domain adaptation for acoustic scene classification. DCASE Shayan Gharib, Konstantinos Drossos, Emre Cakir, Dmitriy Serdyuk, Tuomas Virtanen
2018	J	`jnl`	Unsupervised adversarial domain adaptation for acoustic scene classification. CoRR Shayan Gharib, Konstantinos Drossos, Emre Çakir, Dmitriy Serdyuk, Tuomas Virtanen
2017	J	`jnl`	A Recurrent Encoder-Decoder Approach with Skip-filtering Connections for Monaural Singing Voice Separation. CoRR Stylianos Ioannis Mimilakis, Konstantinos Drossos, Tuomas Virtanen, Gerald Schuller
2017	—	`conf`	A recurrent encoder-decoder approach with skip-filtering connections for monaural singing voice separation. MLSP Stylianos Ioannis Mimilakis, Konstantinos Drossos, Tuomas Virtanen, Gerald Schuller
2017	J	`jnl`	Automated Audio Captioning with Recurrent Neural Networks. CoRR Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen
2017	—	`conf`	Automated audio captioning with recurrent neural networks. WASPAA Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen
2017	J	`jnl`	Convolutional Recurrent Neural Networks for Bird Audio Detection. CoRR Emre Çakir, Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos, Tuomas Virtanen
2017	—	`conf`	Convolutional recurrent neural networks for bird audio detection. EUSIPCO Emre Cakir, Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos, Tuomas Virtanen
2017	J	`jnl`	Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask. CoRR Stylianos Ioannis Mimilakis, Konstantinos Drossos, João Felipe Santos, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio
2017	J	`jnl`	Stacked Convolutional and Recurrent Neural Networks for Bird Audio Detection. CoRR Sharath Adavanne, Konstantinos Drossos, Emre Çakir, Tuomas Virtanen
2017	J	`jnl`	Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition. CoRR Miroslav Malik, Sharath Adavanne, Konstantinos Drossos, Tuomas Virtanen, Dasa Ticha, Roman Jarina
2017	—	`conf`	Stacked convolutional and recurrent neural networks for bird audio detection. EUSIPCO Sharath Adavanne, Konstantinos Drossos, Emre Cakir, Tuomas Virtanen
2015	—	`conf`	Accessible games for blind children, empowered by binaural sound. PETRA Konstantinos Drossos, Nikolaos Zormpas, George Giannakopoulos, Andreas Floros
2015	J	`jnl`	Investigating the Impact of Sound Angular Position on the Listener Affective State. IEEE Trans. Affect. Comput. Konstantinos Drossos, Andreas Floros, Andreas Giannakoulopoulos, Nikolaos Kanellopoulos
2014	—	`conf`	A socially-intelligent multi-robot service team for in-home monitoring. IISA Konstantinos Drossos, Andreas Floros, Stelios M. Potirakis, Nicolas-Alexander Tatlas, Gurkan Tuna
2014	—	`conf`	BEADS: A dataset of Binaural Emotionally Annotated Digital Sounds. IISA Konstantinos Drossos, Andreas Floros, Andreas Giannakoulopoulos
2014	—	`conf`	Swarm Lake: A Game of Swarm Intelligence, Human Interaction and Collaborative Music Composition. ICMC Maximos Kaliakatsos-Papakostas, Andreas Floros, Konstantinos Drossos, Konstantinos Koukoudis, Manolis Kyzalas, Achilleas Kalantzis
2013	—	`conf`	Gestural user interface for audio multitrack real-time stereo mixing. Audio Mostly Conference Konstantinos Drossos, Andreas Floros, Konstantinos Koukoudis
2013	—	`conf`	Sound events and emotions: Investigating the relation of rhythmic characteristics and arousal. IISA Konstantinos Drossos, Rigas Kotsakis, George Kalliris, Andreas Floros
2012	—	`conf`	Affective acoustic ecology: towards emotionally enhanced sound events. Audio Mostly Conference Konstantinos Drossos, Andreas Floros, Nikolaos-Grigorios Kanellopoulos
2012	—	`conf`	Stereo Goes Mobile: Spatial Enhancement for Short-distance Loudspeaker Setups. IIH-MSP Konstantinos Drossos, Stylianos Ioannis Mimilakis, Andreas Floros, Nikolaos Kanellopoulos
2011	J	`jnl`	Emotional control and visual representation using advanced audiovisual interaction. Int. J. Arts Technol. Vasillis Psarras, Andreas Floros, Konstantinos Drossos, Marianne Strapatsakis
2010	—	`conf`	Binaural mixing using gestural control interaction. Audio Mostly Conference Nikolas Grigoriou, Andreas Floros, Konstantinos Drossos