Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Ferrer, Jesús"'
Publikováno v:
Interspeech 2021
End-2-end (E2E) models have become increasingly popular in some ASR tasks because of their performance and advantages. These E2E models directly approximate the posterior distribution of tokens given the acoustic inputs. Consequently, the E2E systems
Externí odkaz:
http://arxiv.org/abs/2206.14623
RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction network ar
Externí odkaz:
http://arxiv.org/abs/2206.14618
Autor:
Weninger, Felix, Gaudesi, Marco, Haidar, Md Akmal, Ferri, Nicola, Andrés-Ferrer, Jesús, Zhan, Puming
In this paper, we present an in-depth study on online attention mechanisms and distillation techniques for dual-mode (i.e., joint online and offline) ASR using the Conformer Transducer. In the dual-mode Conformer Transducer model, layers can function
Externí odkaz:
http://arxiv.org/abs/2206.11157
Autor:
Gonzalez-Ferrer, Jesus, Lehrer, Julian, O’Farrell, Ash, Paten, Benedict, Teodorescu, Mircea, Haussler, David, Jonsson, Vanessa D., Mostajo-Radji, Mohammed A.
Publikováno v:
In Cell Genomics 12 June 2024 4(6)
Autor:
Aziel Alvarado-Ojeda, Zimri, Zamilpa, Alejandro, Costet-Mejia, Alejandro, Méndez-Martínez, Marisol, Trejo-Moreno, Celeste, Jiménez-Ferrer, Jesús Enrique, Salazar-Martínez, Ana Maria, Cruz-Muñoz, Mario Ernesto, Fragoso, Gladis, Rosas-Salgado, Gabriela
Publikováno v:
In Heliyon 30 January 2024 10(2)
In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image classification t
Externí odkaz:
http://arxiv.org/abs/2007.13876
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done on speaker independent (SI) ASR systems, though speaker adapted conve
Externí odkaz:
http://arxiv.org/abs/1907.04916
Autor:
Thornton, Matthew, Sakovich, Anton, Mikhalychev, Alexander, Ferrer, Jesus Diaz, de la Hoz, Pablo, Korolkova, Natalia, Mogilevtsev, Dmitri
Publikováno v:
Phys. Rev. Applied 12, 064051 (2019)
We suggest and discuss a concept of deterministic integrated source of non-classical light based on the coherent diffusive photonics, a coherent light flow in a system of dissipatively coupled waveguides. We show how this practical quantum device can
Externí odkaz:
http://arxiv.org/abs/1907.01973
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.