Frustrating the user on purpose: a step toward building an affective computer J Scheirer, R Fernandez, J Klein, RW Picard Interacting with computers 14 (2), 93-118, 2002 | 526 | 2002 |
Modeling drivers’ speech under stress R Fernandez, RW Picard Speech communication 40 (1-2), 145-159, 2003 | 310 | 2003 |
The IBM expressive text-to-speech synthesis system for American English JF Pitrelli, R Bakis, EM Eide, R Fernandez, W Hamza, MA Picheny IEEE Transactions on Audio, Speech, and Language Processing 14 (4), 1099-1108, 2006 | 178 | 2006 |
Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks. R Fernandez, A Rendel, B Ramabhadran, R Hoory Interspeech, 2268-2272, 2014 | 137 | 2014 |
A computational model for the automatic recognition of affect in speech R Fernandez Massachusetts Institute of Technology, 2004 | 137 | 2004 |
Classical and novel discriminant features for affect recognition from speech. R Fernandez, RW Picard Interspeech, 473-476, 2005 | 105 | 2005 |
Frustrating the user on purpose: Using biosignals in a pilot study to detect the user's emotional state J Riseberg, J Klein, R Fernandez, RW Picard CHI 98 conference summary on Human factors in computing systems, 227-228, 1998 | 97 | 1998 |
Dialog act classification from prosodic features using support vector machines R Fernandez, RW Picard Speech Prosody 2002, International Conference, 2002 | 85 | 2002 |
Recognizing affect from speech prosody using hierarchical graphical models R Fernandez, R Picard Speech Communication 53 (9-10), 1088-1103, 2011 | 51 | 2011 |
F0 contour prediction with a deep belief network-Gaussian process hybrid model R Fernandez, A Rendel, B Ramabhadran, R Hoory 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 48 | 2013 |
Using deep bidirectional recurrent neural networks for prosodic-target prediction in a unit-selection text-to-speech system R Fernandez, A Rendel, B Ramabhadran, R Hoory Sixteenth Annual Conference of the International Speech Communication …, 2015 | 46 | 2015 |
Data Augmentation Improves Recognition of Foreign Accented Speech. T Fukuda, R Fernandez, A Rosenberg, S Thomas, B Ramabhadran, ... Interspeech, 2409-2413, 2018 | 42 | 2018 |
Using continuous lexical embeddings to improve symbolic-prosody prediction in a text-to-speech front-end A Rendel, R Fernandez, R Hoory, B Ramabhadran 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 35 | 2016 |
Modeling phrasing and prominence using deep recurrent learning A Rosenberg, R Fernandez, B Ramabhadran Sixteenth Annual Conference of the International Speech Communication …, 2015 | 34 | 2015 |
Automatic exploration of corpus-specific properties for expressive text-to-speech: a case study in emphasis. R Fernandez, B Ramabhadran SSW, 34-39, 2007 | 29 | 2007 |
Method, apparatus and computer program product providing prosodic-categorical enhancement to phrase-spliced text-to-speech synthesis E Eide, R Fernandez, J Pitrelli, M Viswanathan US Patent App. 11/212,432, 2007 | 26 | 2007 |
An autoencoder neural-network based low-dimensionality approach to excitation modeling for HMM-based text-to-speech S Vishnubhotla, R Fernandez, B Ramabhadran 2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010 | 24 | 2010 |
Discriminative training and unsupervised adaptation for labeling prosodic events with limited training data R Fernandez, B Ramabhadran Eleventh Annual Conference of the International Speech Communication Association, 2010 | 22 | 2010 |
Supervised and unsupervised approaches for controlling narrow lexical focus in sequence-to-sequence speech synthesis S Shechtman, R Fernandez, D Haws 2021 IEEE Spoken Language Technology Workshop (SLT), 431-437, 2021 | 17 | 2021 |
Phrase boundary assignment from text in multiple domains A Rosenberg, R Fernandez, B Ramabhadran Thirteenth Annual Conference of the International Speech Communication …, 2012 | 17 | 2012 |