| 2025 | IJCNLP | Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization. | Iigo Pikabea, Iaki Lacunza, Oriol Pareras Velasco, Carlos Escolano, Aitor Gonzalez-Agirre, Javier Hernando, Marta Villegas |
| 2025 | Interspeech | Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios. | Gerard I. Gllego, Oriol Pareras, Mart Cortada Garcia, Lucas Takanori, Javier Hernando |
| 2025 | Interspeech | Optimizing ASR for Catalan-Spanish Code-Switching: A Comparative Analysis of Methodologies. | Carlos Mena, Pol Serra, Jacobo Romero, Abir Messaoudi, Jos Giraldo, Carme Armentano-Oller, Rodolfo Zevallos, Ivn Meza, Javier Hernando |
| 2025 | Interspeech | Assessing the Performance and Efficiency of Mamba ASR in Low-Resource Scenarios. | Rodolfo Zevallos, Mart Cortada Garcia, Sarah Solito, Carlos Mena, Alex Peir Lilja, Javier Hernando |
| 2024 | ACL | Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge. | Daniel Mela, Aitor Gonzalez-Agirre, Javier Hernando, Marta Villegas |
| 2021 | ICASSP | Double Multi-Head Attention for Speaker Verification. | Miquel India, Pooyan Safari, Javier Hernando |
| 2020 | ICASSP | I-Vector Transformation Using K-Nearest Neighbors for Speaker Verification. | Umair Khan, Miquel India, Javier Hernando |
| 2020 | Interspeech | Unsupervised Training of Siamese Networks for Speaker Verification. | Umair Khan, Javier Hernando |
| 2020 | Interspeech | Self-Attention Encoding and Pooling for Speaker Recognition. | Pooyan Safari, Miquel India, Javier Hernando |
| 2019 | Interspeech | Self Multi-Head Attention for Speaker Recognition. | Miquel India, Pooyan Safari, Javier Hernando |
| 2019 | Interspeech | Auto-Encoding Nearest Neighbor i-Vectors for Speaker Verification. | Umair Khan, Miquel India, Javier Hernando |
| 2017 | CBMI | Towards large scale multimedia indexing: A case study on person discovery in broadcast news. | Nam Le, Herv Bredin, Gabriel Sargent, Miquel India, Paula Lopez-Otero, Claude Barras, Camille Guinaudeau, Guillaume Gravier, Gabriel Barbosa da Fonseca, Izabela Lyon Freire, Zenilton K. G. Patrocnio Jr., Silvio Jamil Ferzoli Guimares, Gerard Mart, Josep Ramon Morros, Javier Hernando, Laura Doco Fernndez, Carmen Garca-Mateo, Sylvain Meignier, Jean-Marc Odobez |
| 2017 | Interspeech | LSTM Neural Network-Based Speaker Segmentation Using Acoustic and Language Modelling. | Miquel India, Jos A. R. Fonollosa, Javier Hernando |
| 2016 | ICASSP | Work-efficient parallel non-maximum suppression for embedded GPU architectures. | David Oro, Carles Fernndez, Xavier Martorell, Javier Hernando |
| 2016 | Interspeech | Deep Neural Networks for i-Vector Language Identification of Short Utterances in Cars. | Omid Ghahabi, Antonio Bonafonte, Javier Hernando, Asuncin Moreno |
| 2016 | Interspeech | Improving i-Vector and PLDA Based Speaker Clustering with Long-Term Features. | Abraham Woubie, Jordi Luque, Javier Hernando |
| 2016 | LREC | The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media Documents. | Johann Poignant, Mateusz Budnik, Herv Bredin, Claude Barras, Mickal Stefas, Pierrick Bruneau, Gilles Adda, Laurent Besacier, Hazim Kemal Ekenel, Gil Francopoulo, Javier Hernando, Joseph Mariani, Ramon Morros, Georges Qunot, Sophie Rosset, Thomas Tamisier |
| 2015 | ICASSP | Restricted Boltzmann Machine supervectors for speaker recognition. | Omid Ghahabi, Javier Hernando |
| 2015 | Interspeech | Using voice-quality measurements with prosodic and spectral features for speaker diarization. | Abraham Woubie, Jordi Luque, Javier Hernando |
| 2014 | ICASSP | Deep belief networks for i-vector based speaker recognition. | Omid Ghahabi, Javier Hernando |
| 2012 | ICPP | Accelerating Boosting-Based Face Detection on GPUs. | David Oro, Carles Fernndez, Carlos Segura, Xavier Martorell, Javier Hernando |
| 2012 | Interspeech | GCC-PHAT based Head Orientation Estimation. | Carlos Segura, Javier Hernando |
| 2011 | Interspeech | The Detection of Overlapping Speech with Prosodic Features for Speaker Diarization. | Martin Zelenk, Javier Hernando |
| 2010 | Interspeech | Overlap detection for speaker diarization by fusing spectral and spatial features. | Martin Zelenk, Carlos Segura, Javier Hernando |
| 2009 | CVPR | Audiovisual event detection towards scene understanding. | Cristian Canton-Ferrer, Taras Butko, Carlos Segura, Xavier Gir, Climent Nadeu, Javier Hernando, Josep R. Casas |
| 2009 | Interspeech | Improving detection of acoustic events using audiovisual data and feature level fusion. | Taras Butko, Cristian Canton-Ferrer, Carlos Segura, Xavier Gir, Climent Nadeu, Javier Hernando, Josep R. Casas |
| 2008 | CVPR | Multimodal real-time focus of attention estimation in SmartRooms. | Cristian Canton-Ferrer, Carlos Segura, Montse Pards, Josep R. Casas, Javier Hernando |
| 2008 | Interspeech | Bi-Gaussian score equalization in an audio-visual SVM-based person verification system. | Pascual Ejarque, Javier Hernando |
| 2008 | Interspeech | Robustness of prosodic features to voice imitation. | Mireia Farrs, Michael Wagner, Jan Anguita, Javier Hernando |
| 2008 | Interspeech | Clustering initialization based on spatial information for speaker diarization of meetings. | Jordi Luque, Carlos Segura, Javier Hernando |
| 2008 | Interspeech | Speaker orientation estimation based on hybridation of GCC-PHAT and HLBR. | Carlos Segura, Alberto Abad, Javier Hernando, Climent Nadeu |
| 2007 | ICASSP | Model Complexity Selection and Cross-Validation EM Training for Robust Speaker Diarization. | Xavier Anguera Mir, Takahiro Shinozaki, Chuck Wooters, Javier Hernando |
| 2007 | ICASSP | Automatic Weighting for the Combination of TDOA and Acoustic Features in Speaker Diarization for Meetings. | Xavier Anguera Mir, Chuck Wooters, Jos Manuel Pardo, Javier Hernando |
| 2007 | ICASSP | Multimodal Head Orientation Towards Attention Tracking in Smartrooms. | Carlos Segura, Cristian Canton-Ferrer, Alberto Abad, Josep R. Casas, Javier Hernando |
| 2007 | Interspeech | Audio-based approaches to head orientation estimation in a smart-room. | Alberto Abad, Carlos Segura, Climent Nadeu, Javier Hernando |
| 2007 | Interspeech | Jitter and shimmer measurements for speaker recognition. | Mireia Farrs, Javier Hernando, Pascual Ejarque |
| 2007 | SECRYPT | On the Effect of Score Equalization in SVM Multimodal Biometric Systems. | Pascual Ejarque, Javier Hernando |
| 2006 | ICASSP | Purity Algorithms for Speaker Diarization of Meetings Data. | Xavier Anguera, Chuck Wooters, Javier Hernando |
| 2006 | Interspeech | Audio person tracking in a smart-room environment. | Alberto Abad, Carlos Segura, Dusan Macho, Javier Hernando, Climent Nadeu |
| 2006 | Interspeech | Friends and enemies: a novel initialization for speaker diarization. | Xavier Anguera, Chuck Wooters, Javier Hernando |
| 2006 | Interspeech | On the use of Jacobian adaptation in real speaker verification applications. | Jan Anguita, Javier Hernando |
| 2006 | Interspeech | On the fusion of prosody, voice spectrum and face features for multimodal person verification. | M. Farrs, Ainara Garde, Pascual Ejarque, Jordi Luque, Javier Hernando |
| 2006 | SECRYPT | Person Verification by Fusion of Prosodic, Voice Spectral and Facial Parameters. | Javier Hernando, Mireia Farrs, Pascual Ejarque, Ainara Garde, Jordi Luque |
| 2005 | Interspeech | Effect of head orientation on the speaker localization performance in smart-room environment. | Alberto Abad, Dusan Macho, Carlos Segura, Javier Hernando, Climent Nadeu |
| 2005 | Interspeech | Variance reduction by using separate genuine- impostor statistics in multimodal biometrics. | Pascual Ejarque, Javier Hernando |
| 2004 | Interspeech | Speech enhancement and recognition by integrating adaptive beamforming and wiener filtering. | Alberto Abad, Javier Hernando |
| 2004 | Interspeech | Jacobian adaptation with improved noise reference for speaker verification. | Jan Anguita, Javier Hernando, Alberto Abad |
| 2004 | Interspeech | Word confusability prediction in automatic speech recognition. | Jan Anguita, Stphane Peillon, Javier Hernando, Alexandre Bramoulle |
| 2004 | Interspeech | Model quality evaluation during enrolment for speaker verification. | Javier R. Saeta, Javier Hernando |
| 2003 | Interspeech | Jacobian adaptation based on the frequency-filtered spectral energies. | Alberto Abad, Climent Nadeu, Javier Hernando, Jaume Padrell |
| 2003 | Interspeech | Covariation and weighting of harmonically decomposed streams for ASR. | Philip J. B. Jackson, David M. Moreno, Martin J. Russell, Javier Hernando |
| 2002 | Interspeech | ACIMET: access to meteorological information by telephone. | Jaume Padrell, Javier Hernando |
| 2001 | Interspeech | Speaker identification for car infotainment applications. | Javier Rodrguez Saeta, Christian Koechling, Javier Hernando |
| 2000 | Interspeech | On the use of filter-bank energies driven from the autocorrelation sequence for noisy speech recognition. | Javier Hernando |
| 1999 | Interspeech | Comparison of time & frequency filtering and cepstral-time matrix approaches in ASR. | Dusan Macho, Climent Nadeu, Peter Jancovic, Gregor Rozinaj, Javier Hernando |
| 1998 | Interspeech | Speaker verification on the polycost database using frequency filtered spectral energies. | Javier Hernando, Climent Nadeu |
| 1997 | ICASSP | Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition. | Javier Hernando |
| 1997 | Interspeech | Robust speech parameters located in the frequency domain. | Javier Hernando, Climent Nadeu |
| 1997 | Interspeech | CDHMM speaker recognition by means of frequency filtering of filter-bank energies. | Javier Hernando, Climent Nadeu |
| 1996 | Interspeech | Frequency and time filtering of filter-bank energies for HMM speech recognition. | Climent Nadeu, Jos B. Mario, Javier Hernando, Albino Nogueiras |
| 1995 | Interspeech | On the decorrelation of filter-bank energies in speech recognition. | Climent Nadeu, Javier Hernando, Mnica Gorricho |
| 1995 | Interspeech | Robust hos-based techniques applied to speech recognition and enhancement. | Josep M. Salavedra, Javier Hernando, Enrique Masgrau, Asuncin Moreno |
| 1994 | ICASSP | Speech recognition in noisy car environment based on OSALPC representation and robust similarity measuring techniques. | Javier Hernando, Climent Nadeu |
| 1994 | Interspeech | Speaker identification in noisy conditions using linear prediction of the one-sided autocorrelation sequence. | Javier Hernando, Climent Nadeu, Carlos Villagrasa, Enric Monte |
| 1994 | Interspeech | Some fast higher order AR estimation techniques applied to parametric wiener filtering. | Josep M. Salavedra, Enrique Masgrau, Asuncin Moreno, Joan Estarellas, Javier Hernando |
| 1993 | Interspeech | Multiple multilabeling to improve HMM-based speech recognition in noise. | Javier Hernando, Jos B. Mario, Climent Nadeu |
| 1992 | Interspeech | On the AR modelling of the one-sided autocorrelation sequence for noisy speech recognition. | Javier Hernando, Climent Nadeu, Eduardo Lleida |
| 1991 | ICASSP | Pitch determination using the cepstrum of the one-sided autocorrelation sequence. | Climent Nadeu, Jordi Pascual, Javier Hernando |
| 1991 | Interspeech | A comparative study of parameters and distances for noisy speech recognition. | Javier Hernando, Climent Nadeu |
| 1989 | Interspeech | Modeling of the analytic spectrum for speech recognition. | Climent Nadeu, Eduardo Lleida, Javier Hernando |