Ramon Fernandez Astudillo
Ramon Fernandez Astudillo
Verified email at astudillo.com
TitleCited byYear
Finding function in form: Compositional character models for open vocabulary word representation
W Ling, T Luís, L Marujo, RF Astudillo, S Amir, C Dyer, AW Black, ...
arXiv preprint arXiv:1508.02096, 2015
From softmax to sparsemax: A sparse model of attention and multi-label classification
A Martins, R Astudillo
International Conference on Machine Learning, 1614-1623, 2016
Not all contexts are created equal: Better word representations with variable attention
W Ling, Y Tsvetkov, S Amir, R Fernandez Astudillo, C Dyer, AW Black, ...
Proceedings of the 2015 Conference on Empirical Methods in Natural Language …, 2015
Integration of Short Time Fourier Domain Speech Enhancement and Observation Uncertainty Techniques for Robust Automatic Speech Recognition
RF Astudillo
Independent component analysis and time-frequency masking for speech recognition in multitalker conditions
D Kolossa, RF Astudillo, E Hoffmann, R Orglmeister
EURASIP Journal on Audio, Speech, and Music Processing 2010 (1), 651420, 2010
The L2F Spoken Web Search system for Mediaeval 2012.
A Abad, RF Astudillo, I Trancoso
MediaEval, 2012
Computing MMSE estimates and residual uncertainty directly in the feature domain of ASR using STFT domain speech distortion models
RF Astudillo, R Orglmeister
IEEE transactions on audio, speech, and language processing 21 (5), 1023-1034, 2013
Inesc-id: A regression model for large scale twitter sentiment lexicon induction
S Amir, R Astudillo, W Ling, B Martins, MJ Silva, I Trancoso
Proceedings of the 9th International Workshop on Semantic Evaluation …, 2015
An uncertainty propagation approach to robust ASR using the ETSI advanced front-end
RF Astudillo, D Kolossa, P Mandelartz, R Orglmeister
IEEE Journal of Selected Topics in Signal Processing 4 (5), 824-833, 2010
Learning word representations from scarce and noisy data with embedding subspaces
R Astudillo, S Amir, W Ling, M Silva, I Trancoso
Proceedings of the 53rd Annual Meeting of the Association for Computational …, 2015
Propagation of uncertainty through multilayer perceptrons for robust automatic speech recognition
RF Astudillo, JPS Neto
Twelfth Annual Conference of the International Speech Communication Association, 2011
CHiME challenge: Approaches to robustness using beamforming and uncertainty-of-observation techniques
D Kolossa, R Fernandez_Astudillo, A Abad, S Zeiler, R Saeidi, ...
Machine Listening in Multisource Environments, 2011
Uncertain LDA: Including observation uncertainties in discriminative transforms
R Saeidi, RF Astudillo, D Kolossa
IEEE transactions on pattern analysis and machine intelligence 38 (7), 1479-1488, 2015
A flexible spatial blind source extraction framework for robust speech recognition in noisy environments
F Nesta, M Matassoni, RF Astudillo
Proc. CHiME, 33-40, 2013
Accounting for the uncertainty of speech estimates in the complex domain for minimum mean square error speech enhancement
RF Astudillo, D Kolossa, R Orglmeister
Tenth Annual Conference of the International Speech Communication Association, 2009
Pushing the limits of translation quality estimation
AFT Martins, M Junczys-Dowmunt, FN Kepler, R Astudillo, C Hokamp, ...
Transactions of the Association for Computational Linguistics 5, 205-218, 2017
Unbabel’s participation in the WMT16 word-level translation quality estimation shared task
AFT Martins, R Astudillo, C Hokamp, F Kepler
Proceedings of the First Conference on Machine Translation: Volume 2, Shared …, 2016
The DIRHA-GRID corpus: baseline and tools for multi-room distant speech recognition using distributed microphones
M Matassoni, RF Astudillo, A Katsamanis, M Ravanelli
Fifteenth Annual Conference of the International Speech Communication …, 2014
Back-translation-style data augmentation for end-to-end ASR
T Hayashi, S Watanabe, Y Zhang, T Toda, T Hori, R Astudillo, K Takeda
2018 IEEE Spoken Language Technology Workshop (SLT), 426-433, 2018
Noise-adaptive LDA: A new approach for speech recognition under observation uncertainty
D Kolossa, S Zeiler, R Saeidi, RF Astudillo
IEEE Signal Processing Letters 20 (11), 1018-1021, 2013
The system can't perform the operation now. Try again later.
Articles 1–20