author = {Wajdi Ghezaiel and Luc Brun and Olivier L{'{e}}zoray}, title = {Hybrid Network For End-To-End Text-Independent Speaker Identification}, booktitle = {25th International Conference on Pattern Recognition, {ICPR} 2020, Virtual Event / Milan, Italy, January 10-15, 2021}, pages = {2352--2359}, publisher = {{IEEE}}, year = {2020}, url = {IEEXplore:=https://doi.org/10.1109/ICPR48806.2021.9413293, Slides:=https://brunl01.users.greyc.fr/ARTICLES/Presentation_Ghezaiel_ICPR2020.pdf, PDF:=https://brunl01.users.greyc.fr/ARTICLES/Ghezaiel_icpr2020.pdf,HAL:=https://hal.archives-ouvertes.fr/hal-03086433v1}, timestamp = {Fri, 07 May 2021 12:53:57 +0200}, abstract = "Deep learning has recently improved the performance of Speaker Identification (SI) systems. Promising results have been obtained with Convolutional Neural Networks (CNNs). This success is mostly driven by the advent of large datasets. However in the context of decentralized commercial applications, collection of large amount of training data is not always possible. In addition, robustness of a SI system is adversely effected by short utterances. Therefore, in this paper, we propose a novel text-independent speaker identification system able to identify speakers by learning from only few training short utterances examples. To achieve this, we combine a two-layer wavelet scattering network coupled with a CNN. The proposed architecture takes variable length speech segments. To evaluate the effectiveness of the proposed approach, Timit and Librispeech datasets are used in the experiments. Our experiments shows that our hybrid architecture provides satisfactory results under the constraints of short and limited number of utterances. These experiments also show that our hybrid architecture are competitive with the state of the art.", theme = "pattern"