output
19922026
most citedAttention-Based Models for Speech Recognition

1.8k citations

Showing 2016Show all

153 papers · 1 filter

hep-ph2016★ 12 cited

Generalized Beth-Uhlenbeck approach to the equation of state for quark-hadron matter

D. Blaschke, A. Dubinin, L. Turko

A unified equation of state for quark-hadron matter is presented in the generalized Beth-Uhlenbeck form. It follows from a derivable approach to the thermodynamic potential whe…

astro-ph.SR2016★ 8 cited

Revising the evolutionary stage of HD 163899: the effects of convective overshooting and rotation

Jakub Ostrowski, Jadwiga Daszyńska-Daszkiewicz, Henryk Cugier

We revise the evolutionary status of the B-type supergiant HD\,163899 based on the new determinations of the mass-luminosity ratio, effective temperature and rotational velocity as…

astro-ph.SR2016★ 51 cited

Interpretation of the BRITE oscillation data of the hybrid pulsator Eridani: a call for the modification of stellar opacities

J. Daszynska-Daszkiewicz, A. A. Pamyatnykh, P. Walczak +3

The analysis of the BRITE oscillation spectrum of the main sequence early B-type star Eridani is presented. Only models with the modified mean opacity profile can account for t…

gr-qc2016★ 5 cited

Quantum reduced loop gravity: extension to gauge vector field

Jakub Bilski, Emanuele Alesci, Francesco Cianfrani +2

Within the framework of Quantum Reduced Loop Gravity we quantize the Hamiltonian for a gauge vector field. The regularization can be performed using tools analogous to the ones ado…

astro-ph.HE2016★ 95 cited

In-vacuo-dispersion features for GRB neutrinos and photons

Giovanni Amelino-Camelia, Giacomo D'Amico, Giacomo Rosati +1

Over the last 15 years there has been considerable interest in the possibility of quantum-gravity-induced in-vacuo dispersion, the possibility that spacetime itself might behave es…

cs.NE2016★ 58 cited

Towards better decoding and language model integration in sequence to sequence models

Jan Chorowski, Navdeep Jaitly

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a…