Efthymios Tzinis

Efthymios Tzinis

Auto-generated profile, based on publicly available information

Efthymios Tzinis

University of Illinois Urbana-Champaign,Department of Computer Science,Urbana,IL,USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2022 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Open access
ETEfthymios Tzinis
Efthymios Tzinis
YAYossi Adi
Yossi Adi
VIVamsi K. Ithapu
Vamsi K. Ithapu
BXBuye Xu
Buye Xu
PSParis Smaragdis
Paris Smaragdis
AKAnurag Kumar
Anurag Kumar
We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make them dependent on clean in-domain target signals and thus, sensitive to any domain mismatch between train and test samples. RemixIT is based on a continuous self-training scheme in which a pre-trained teacher model on out-of-domain data infers estimated pseudo-target signals for in-domain mixtures. Then, by permuting the estimated clean and noise signals and remixing them together, we generate a new set of bootstrapped mixtures and corresponding pseudo-targets which are used to train the student network. Vice-versa, the teacher periodically refines its estimates using the updated parameters of the latest student models. Experimental results on multiple speech enhancement datasets and tasks not only show the superiority of our method over prior approaches but also showcase that RemixIT can be combined with any separation model as well as be applied towards any semi-supervised and unsupervised domain adaptation task. Our analysis, paired with empirical evidence, sheds light on the inside functioning of our self-training scheme wherein the student model keeps obtaining better performance while observing severely degraded pseudo-targets.

30 July 2021 in Journal of Signal Processing Systems
Verified
Journal Article
Closed access
PDF file
ETEfthymios Tzinis
Efthymios Tzinis
ZWZhepei Wang
Zhepei Wang
XJXilin Jiang
Xilin Jiang
PSParis Smaragdis
Paris Smaragdis


15 December 2022 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ZWZhepei Wang
Zhepei Wang
CSCem Subakan
Cem Subakan
XJXilin Jiang
Xilin Jiang
JWJunkai Wu
Junkai Wu
ETEfthymios Tzinis
Efthymios Tzinis
PSParis Smaragdis
Paris Smaragdis
In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.

15 September 2019
Verified
Conference Paper
Open access
GPGeorgios Paraskevopoulos
Georgios Paraskevopoulos
ETEfthymios Tzinis
Efthymios Tzinis
NENikolaos Ellinas
Nikolaos Ellinas
TGTheodoros Giannakopoulos
Theodoros Giannakopoulos
APAlexandros Potamianos
Alexandros Potamianos

24 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
SWScott Wisdom
Scott Wisdom
ETEfthymios Tzinis
Efthymios Tzinis
HEHakan Erdogan
Hakan Erdogan
RWRon J. Weiss
Ron J. Weiss
KWKevin Wilson
Kevin Wilson
JHJohn R. Hershey
John R. Hershey
In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from synthetic mixtures created by adding up isolated ground-truth sources. Reliance on this synthetic training data is problematic because good performance depends upon the degree of match between the training data and real-world audio, especially in terms of the acoustic conditions and distribution of sources. The acoustic properties can be challenging to accurately simulate, and the distribution of sound types may be hard to replicate. In this paper, we propose a completely unsupervised method, mixture invariant training (MixIT), that requires only single-channel acoustic mixtures. In MixIT, training examples are constructed by mixing together existing mixtures, and the model separates them into a variable number of latent sources, such that the separated sources can be remixed to approximate the original mixtures. We show that MixIT can achieve competitive performance compared to supervised methods on speech separation. Using MixIT in a semi-supervised learning setting enables unsupervised domain adaptation and learning from large amounts of real world data without ground-truth source waveforms. In particular, we significantly improve reverberant speech separation performance by incorporating reverberant mixtures, train a speech enhancement system from noisy mixtures, and improve universal sound separation by incorporating a large amount of in-the-wild data.