D. Dimitriadis

Most-cited papers

A Review of Speaker Diarization: Recent Advances with Deep Learning
Tae Jin Park, Naoyuki Kanda, D. Dimitriadis, Kyu J. Han +2 more
2021Computer Speech and Language472 citations Open access
Semantic Scholar
English Conversational Telephone Speech Recognition by Humans and Machines
G. Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi +8 more
2017Interspeech377 citations Open access
Semantic Scholar
Federated benchmarking of medical artificial intelligence with MedPerf
A. Karargyris, Renato Umeton, Micah J. Sheller, Alejandro Aristizabal +70 more
2021Nature Machine Intelligence203 citations Open access
Semantic Scholar
Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
Y. Cho, Andre Manoel, Gauri Joshi, Robert Sim +1 more
2022International Joint Conference on Artificial Intelligence200 citations Open access
Semantic Scholar
Progressive Neural Networks for Transfer Learning in Emotion Recognition
John Gideon, Soheil Khorram, Zakaria Aldeneh, D. Dimitriadis +1 more
2017Interspeech127 citations Open access
Semantic Scholar
Personalized Federated Learning With Adaptive Batchnorm for Healthcare
Wang Lu, Jin-Dong Wang, Yi-Qiang Chen, Xin Qin +3 more
2021IEEE Transactions on Big Data104 citations Open access
Semantic Scholar
Developing On-Line Speaker Diarization System
D. Dimitriadis, P. Fousek
2017Interspeech88 citations
Semantic Scholar
Advances in Online Audio-Visual Meeting Transcription
T. Yoshioka, Yan Huang, Aviv Hurvitz, Li Jiang +22 more
2019Automatic Speech Recognition & Understanding84 citations Open access
Semantic Scholar
Single-channel Speech Extraction Using Speaker Inventory and Attention Network
Xiong Xiao, Zhuo Chen, T. Yoshioka, Hakan Erdogan +4 more
2019IEEE International Conference on Acoustics, Speech, and Signal Processing78 citations
Semantic Scholar
Auditory Teager energy cepstrum coefficients for robust speech recognition
D. Dimitriadis, P. Maragos, A. Potamianos
2005Interspeech76 citations Open access
Semantic Scholar
A Comparison of the Squared Energy and Teager-Kaiser Operators for Short-Term Energy Estimation in Additive Noise
D. Dimitriadis, A. Potamianos, P. Maragos
2009IEEE Transactions on Signal Processing74 citations Open access
Semantic Scholar
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
Mirian Hipolito Garcia, Andre Manoel, Daniel Diaz, Fatemehsadat Mireshghallah +2 more
2022arXiv.org70 citations Open access
Semantic Scholar
Acoustic and Lexical Sentiment Analysis for Customer Service Calls
Bryan Li, D. Dimitriadis, A. Stolcke
2019IEEE International Conference on Acoustics, Speech, and Signal Processing57 citations
Semantic Scholar
A Federated Approach in Training Acoustic Models
D. Dimitriadis, K. Kumatani, R. Gmyr, Yashesh Gaur +1 more
2020Interspeech45 citations
Semantic Scholar
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick +2 more
2021North American Chapter of the Association for Computational Linguistics44 citations Open access
Semantic Scholar
Pooling acoustic and lexical features for the prediction of valence
Zakaria Aldeneh, Soheil Khorram, D. Dimitriadis, E. Provost
2017International Conference on Multimodal Interaction44 citations
Semantic Scholar
Capturing Long-Term Temporal Dependencies with Convolutional Networks for Continuous Emotion Recognition
Soheil Khorram, Zakaria Aldeneh, D. Dimitriadis, M. McInnis +1 more
2017Interspeech44 citations Open access
Semantic Scholar
Meeting Transcription Using Asynchronous Distant Microphones
T. Yoshioka, D. Dimitriadis, A. Stolcke, William Fu-Hinthorn +3 more
2019Interspeech38 citations
Semantic Scholar
Robust energy demodulation based on continuous models with application to speech recognition
D. Dimitriadis, P. Maragos
2003Interspeech38 citations Open access
Semantic Scholar
On the Effects of Filterbank Design and Energy Computation on Robust Speech Recognition
D. Dimitriadis, P. Maragos, A. Potamianos
2011IEEE Transactions on Audio, Speech, and Language Processing37 citations Open access
Semantic Scholar
Continuous energy demodulation methods and application to speech analysis
D. Dimitriadis, P. Maragos
2006Speech Communication36 citations Open access
Semantic Scholar
Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout
Dun Chen, Mirian Hipolito Garcia, C. Jermaine, D. Dimitriadis +1 more
2022International Conference on Artificial Intelligence and Statistics30 citations Open access
Semantic Scholar
Low-latency Speaker-independent Continuous Speech Separation
T. Yoshioka, Zhuo Chen, Changliang Liu, Xiong Xiao +2 more
2019IEEE International Conference on Acoustics, Speech, and Signal Processing30 citations Open access
Semantic Scholar
An improved energy demodulation algorithm using splines
D. Dimitriadis, P. Maragos
20012001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)28 citations Open access
Semantic Scholar
Improving End-of-Turn Detection in Spoken Dialogues by Detecting Speaker Intentions as a Secondary Task
Zakaria Aldeneh, D. Dimitriadis, E. Provost
2018IEEE International Conference on Acoustics, Speech, and Signal Processing24 citations Open access
Semantic Scholar
Spectral Moment Features Augmented by Low Order Cepstral Coefficients for Robust ASR
Pirros Tsiakoulis, A. Potamianos, D. Dimitriadis
2010IEEE Signal Processing Letters24 citations
Semantic Scholar
Distribution Inference Risks: Identifying and Mitigating Sources of Leakage
Valentin Hartmann, Léo Meynent, Maxime Peyrard, D. Dimitriadis +2 more
20222023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)23 citations Open access
Semantic Scholar
GAN-Based Data Generation for Speech Emotion Recognition
Sefik Emre Eskimez, D. Dimitriadis, R. Gmyr, Kenichi Kumanati
2020Interspeech23 citations
Semantic Scholar
An optimum microphone array post-filter for speech applications
Stamatios Lefkimmiatis, D. Dimitriadis, P. Maragos
2006Interspeech23 citations Open access
Semantic Scholar
Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
Tae Jin Park, K. Kumatani, D. Dimitriadis
2021arXiv.org22 citations
Semantic Scholar
Ensemble Approaches for Large-Scale Multi-Label Classification and Question Answering in Biomedicine
Yannis Papanikolaou, D. Dimitriadis, Grigorios Tsoumakas, Manos Laliotis +2 more
2014Conference and Labs of the Evaluation Forum20 citations
Semantic Scholar
Federated Multilingual Models for Medical Transcript Analysis
Andre Manoel, Mirian Hipolito Garcia, Tal Baumel, Shize Su +5 more
2022ACM Conference on Health, Inference, and Learning19 citations Open access
Semantic Scholar
Federated Transfer Learning with Dynamic Gradient Aggregation
D. Dimitriadis, K. Kumatani, R. Gmyr, Yashesh Gaur +1 more
2020arXiv.org17 citations
Semantic Scholar
Emotion classification of speech using modulation features
T. Chaspari, D. Dimitriadis, P. Maragos
2014European Signal Processing Conference17 citations
Semantic Scholar
Meeting Transcription Using Virtual Microphone Arrays
T. Yoshioka, Zhuo Chen, D. Dimitriadis, William Fu-Hinthorn +3 more
2019arXiv.org15 citations
Semantic Scholar
Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels
Y. Cho, Gauri Joshi, D. Dimitriadis
2023IEEE International Conference on Computer Vision14 citations Open access
Semantic Scholar
Modulation features for speech recognition
D. Dimitriadis, P. Maragos, A. Potamianos
2002IEEE International Conference on Acoustics, Speech, and Signal Processing13 citations Open access
Semantic Scholar
Investigating deep neural network based transforms of robust audio features for LVCSR
E. Bocchieri, D. Dimitriadis
2013IEEE International Conference on Acoustics, Speech, and Signal Processing11 citations
Semantic Scholar
Speech recognition modeling advances for mobile voice search
E. Bocchieri, D. Caseiro, D. Dimitriadis
2011IEEE International Conference on Acoustics, Speech, and Signal Processing10 citations
Semantic Scholar
Short-time instantaneous frequency and bandwidth features for speech recognition
Pirros Tsiakoulis, A. Potamianos, D. Dimitriadis
20092009 IEEE Workshop on Automatic Speech Recognition & Understanding10 citations Open access
Semantic Scholar
Speaker diarization: A perspective on challenges and opportunities from theory to practice
Kenneth Ward Church, Wei-Zhong Zhu, J. Vopicka, Jason W. Pelecanos +2 more
2017IEEE International Conference on Acoustics, Speech, and Signal Processing9 citations
Semantic Scholar
Investigating factor analysis features for deep neural networks in noisy speech recognition
Sriram Ganapathy, S. Thomas, D. Dimitriadis, Steven J. Rennie
2015Interspeech9 citations
Semantic Scholar
Instantaneous frequency and bandwidth estimation using filterbank arrays
Pirros Tsiakoulis, A. Potamianos, D. Dimitriadis
2013IEEE International Conference on Acoustics, Speech, and Signal Processing9 citations
Semantic Scholar
Use of Micro-Modulation Features in Large Vocabulary Continuous Speech Recognition Tasks
D. Dimitriadis, E. Bocchieri
2015IEEE/ACM Transactions on Audio Speech and Language Processing8 citations
Semantic Scholar
Advanced front-end for robust speech recognition in extremely adverse environments
D. Dimitriadis, J. C. Segura, L. García, A. Potamianos +2 more
2007Interspeech8 citations Open access
Semantic Scholar
Modulation and chaotic acoustic features for speech recognition
D. Dimitriadis, P. Maragos, Vassilis Pitsikalis, A. Potamianos
20028 citations
Semantic Scholar
Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
Yehya Farhat, Hamza ElMokhtar Shili, Fang-Shuo Liao, Dun Chen +6 more
2023Neural Information Processing Systems7 citations Open access
Semantic Scholar
Enhancements for Audio-only Diarization Systems
D. Dimitriadis
2019arXiv.org7 citations
Semantic Scholar
An alternative front-end for the AT&T WATSON LV-CSR system
D. Dimitriadis, E. Bocchieri, D. Caseiro
2011IEEE International Conference on Acoustics, Speech, and Signal Processing7 citations
Semantic Scholar
A Memory Augmented Architecture for Continuous Speaker Identification in Meetings
Nikolaos Flemotomos, D. Dimitriadis
2020IEEE International Conference on Acoustics, Speech, and Signal Processing6 citations Open access
Semantic Scholar