Следене
Efthymios Tzinis
Efthymios Tzinis
Sr. Research Scientist at Google | Ex. UIUC, MERL, Meta
Потвърден имейл адрес: google.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
Unsupervised sound separation using mixture invariant training
S Wisdom, E Tzinis, H Erdogan, RJ Weiss, K Wilson, JR Hershey
Advances in Neural Information Processing Systems 33, 3846-3857, 2020
2192020
Asteroid: the pytorch-based audio source separation toolkit for researchers
M Pariente, S Cornell, J Cosentino, S Sivasankaran, E Tzinis, ...
Proc. Interspeech 2020, 2637-2641, 2020
203*2020
Sudo rm-rf: Efficient networks for universal audio source separation
E Tzinis, Z Wang, P Smaragdis
2020 IEEE 30th International Workshop on Machine Learning for Signal …, 2020
1682020
Improving universal sound separation using sound classification
E Tzinis, S Wisdom, JR Hershey, A Jansen, DPW Ellis
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
972020
Two-step sound source separation: Training on learned latent targets
E Tzinis, S Venkataramani, Z Wang, C Subakan, P Smaragdis
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
912020
Segment-based speech emotion recognition using recurrent neural networks
E Tzinis, A Potamianos
Affective Computing and Intelligent Interaction (ACII), 2017 Seventh …, 2017
912017
Into the wild with audioscope: Unsupervised audio-visual separation of on-screen sounds
E Tzinis, S Wisdom, A Jansen, S Hershey, T Remez, DPW Ellis, ...
International Conference on Learning Representations (ICLR) 2021, 2021
802021
Unsupervised deep clustering for source separation: Direct learning from mixtures using spatial information
E Tzinis, S Venkataramani, P Smaragdis
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
602019
Remixit: Continual self-training of speech enhancement models via bootstrapped remixing
E Tzinis, Y Adi, VK Ithapu, B Xu, P Smaragdis, A Kumar
IEEE Journal of Selected Topics in Signal Processing 16 (6), 1329-1341, 2022
582022
Compute and memory efficient universal sound source separation
E Tzinis, Z Wang, X Jiang, P Smaragdis
Journal of Signal Processing Systems 94 (2), 245-259, 2021
502021
Beta 1, beta 2 and beta 3 adrenergic receptor gene polymorphisms in a southeastern European population
MS Katsarou, A Karathanasopoulou, A Andrianopoulou, V Desiniotis, ...
Frontiers in genetics 9, 560, 2018
402018
Audioscopev2: Audio-visual attention architectures for calibrated open-domain on-screen sound separation
E Tzinis, S Wisdom, T Remez, JR Hershey
European Conference on Computer Vision, 368-385, 2022
332022
Engagement detection for children with Autism Spectrum Disorder
A Chorianopoulou, E Tzinis, E Iosif, A Papoulidi, C Papailiou, ...
ICASSP 2017-2017 IEEE International Conference on Acoustics, Speech and …, 2017
322017
Integrating Recurrence Dynamics for Speech Emotion Recognition
E Tzinis, G Paraskevopoulos, C Baziotis, A Potamianos
Proc. Interspeech 2018, 927-931, 2018
312018
Separate but together: Unsupervised federated learning for speech enhancement from non-iid data
E Tzinis, J Casebeer, Z Wang, P Smaragdis
2021 IEEE Workshop on Applications of Signal Processing to Audio and …, 2021
282021
Continual learning of new sound classes using generative replay
Z Wang, C Subakan, E Tzinis, P Smaragdis, L Charlin
2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019
262019
Continual self-training with bootstrapped remixing for speech enhancement
E Tzinis, Y Adi, VK Ithapu, B Xu, A Kumar
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
202022
Heterogeneous Target Speech Separation
E Tzinis, G Wichern, A Subramanian, P Smaragdis, JL Roux
Proc. Interspeech 2022, 1796-1800, 2022
202022
Learning representations for new sound classes with continual self-supervised learning
Z Wang, C Subakan, X Jiang, J Wu, E Tzinis, M Ravanelli, P Smaragdis
IEEE Signal Processing Letters 29, 2607-2611, 2022
182022
The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement
S Leglaive, L Borne, E Tzinis, M Sadeghi, M Fraticelli, S Wisdom, ...
arXiv preprint arXiv:2307.03533, 2023
172023
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20