José A. R. Fonollosa

发表

Study and Comparison of Rule-Based and Statistical Catalan-Spanish Machine Translation Systems

Marta R. Costa-jussà, Mireia Farrús, José A. R. Fonollosa, 2012, Comput. Informatics.

Measuring acoustic reduction in feature space

José A. R. Fonollosa, Henrik Schulz, 2012 .

Adaptive blind equalization using weighted cumulant slices

José A. R. Fonollosa, Josep Vidal, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Syntax-based reordering for statistical machine translation

José A. R. Fonollosa, Maxim Khalilov, Maxim Khalilov, 2011, Comput. Speech Lang..

Smooth Bilingual N-Gram Translation

José A. R. Fonollosa, Holger Schwenk, Marta R. Costa-jussà, 2007, EMNLP.

New HOS-based parameter estimation methods for speech recognition in noisy environments

José A. R. Fonollosa, Josep Vidal, Asunción Moreno, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Causal AR modeling using a linear combination of cumulant slices

José A. R. Fonollosa, Josep Vidal, J. Vidal, 1994, Signal Process..

Analysis of HMM Temporal Evolution for Automatic Speech Recognition and Verification

José A. R. Fonollosa, Marta Casar, 2006, TSD.

Nearest-neighbor search algorithms based on subcodebook selection and its application to speech recognition

José A. R. Fonollosa, 2003, INTERSPEECH.

Terminal digital para la transmisión de voz y datos sobre banda fónica

José A. R. Fonollosa, Enrique José Masgrau Gómez, Marcelo Ymbern García, 1986 .

Correcting input noise in SMT as a char-based translation problem

José A. R. Fonollosa, Lluís Formiga Fanals, 2012 .

N-Gram-Based Statistical Machine Translation versus Syntax Augmented Machine Translation: Comparison and System Combination

José A. R. Fonollosa, Maxim Khalilov, Maxim Khalilov, 2009, EACL.

A path-based layered architecture using HMM for automatic speech recognition

Albino Nogueiras, José A. R. Fonollosa, Marta Casar, 2006, 2006 14th European Signal Processing Conference.

Robust LPC vector quantization based on kohonen's design algorithm

José A. R. Fonollosa, M. Asunción Moreno Bilbao, Enrique José Masgrau Gómez, 1990 .

Blind Multiuser Detection with Array Observations

José A. R. Fonollosa, Zoran Zvonar, Javier Rodríguez Fonollosa, 1998, Wirel. Pers. Commun..

Latest trends in hybrid machine translation and its applications

José A. R. Fonollosa, Marta R. Costa-jussà, M. Costa-jussà, 2015, Comput. Speech Lang..

Dealing with Input Noise in Statistical Machine Translation

José A. R. Fonollosa, Lluís Formiga, 2012, COLING.

Feature decorrelation methods in speech recognition. a comparative study

José A. R. Fonollosa, Climent Nadeu, Eloi Batlle, 1998, ICSLP.

SAT encodings for sorting networks, single-exception sorting networks and ε-halvers pdf

José A. R. Fonollosa, 2018, ArXiv.

N-gram-based SMT System Enhanced with Reordering Patterns

José B. Mariño, Marta R. Costa-jussà, José A. R. Fonollosa, 2006, WMT@HLT-NAACL.

AVPC-subband coding system for speech encoding

José B. Mariño, José A. R. Fonollosa, Enrique Masgrau, 1987, ECST.

Application of hidden Markov models to blind channel characterization and data detection

José A. R. Fonollosa, Josep Vidal, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Analysis of HMM temporal evolution for automatic speech recognition and utterance verification

José A. R. Fonollosa, Marta Casar, 2006, INTERSPEECH.

TALP Phrase-based statistical translation system for European language pairs

José B. Mariño, Marta R. Costa-jussà, José A. R. Fonollosa, 2006, WMT@HLT-NAACL.

Overcoming HMM time independence assumption using N-gram based modelling for continuous speech recognition

José A. R. Fonollosa, Marta Casar, Marta Casar, 2008, 2008 16th European Signal Processing Conference.

Comparación y combinación de los sistemas de traducción automática basados en n-gramas y en sintaxis

José A. R. Fonollosa, Maxim Khalilov, Maxim Khalilov, 2008, Proces. del Leng. Natural.

Acoustic cancellation of engine noise by fast adaptive IIR filtering

José A. R. Fonollosa, Enrique José Masgrau Gómez, 1990 .

Simplified gradient calculation in adaptive IIR lattice filters

José A. R. Fonollosa, Enrique Masgrau, 1991, IEEE Trans. Signal Process..

Modelling the effects of spontaneous speech in speech recognition

José A. R. Fonollosa, Henrik Shulz, 2013 .

Impulse response recovery of linear systems through weighted cumulant slices

José A. R. Fonollosa, Josep Vidal, J. Vidal, 1996, IEEE Trans. Signal Process..

Recursive alignment block classification technique for word reordering in statistical machine translation

José A. R. Fonollosa, Marta R. Costa-jussà, Enric Monte-Moreno, 2011, Lang. Resour. Evaluation.

LSTM Neural Network-Based Speaker Segmentation Using Acoustic and Language Modelling

José A. R. Fonollosa, Javier Hernando, Miquel India, 2017, INTERSPEECH.

Fast vector quantization based on subcodebook selection and its application to speech recognition

José A. R. Fonollosa, 2002 .

System identification using a linear combination of cumulant slices

José A. R. Fonollosa, Josep Vidal, J. Vidal, 1993, IEEE Trans. Signal Process..

A New Subtree-Transfer Approach to Syntax-Based Reordering for Statistical Machine Translation

José A. R. Fonollosa, Mark Dras, Maxim Khalilov, 2009, EAMT.

A N-gram approach to overcome time and parameter independence assumptions of HMM for speech recognition

José A. R. Fonollosa, Marta Casar, 2007, 2007 15th European Signal Processing Conference.

Transcription of Catalan Broadcast Conversation

José A. R. Fonollosa, Henrik Schulz, David Rybach, 2009, TSD.

The TALP Ngram-based SMT systems for IWSLT 2006

José B. Mariño, José A. R. Fonollosa, Rafael E. Banchs, 2006, IWSLT.

Joint Size and Depth Optimization of Sorting Networks pdf

José A. R. Fonollosa, 2018, ArXiv.

Analisis estadistico de orden superior de la voz

José A. R. Fonollosa, M. Asunción Moreno Bilbao, 1991 .

Combining length restrictions and n-best techniques in multiple-pass search strategies

José A. R. Fonollosa, Eloi Batlle, 1999, EUROSPEECH.

CUMULANT - based voicing decision in noise corrupted speech

José A. R. Fonollosa, Asunción Moreno, A. Moreno, 1992, ICSLP.

Double Layer Architectures for Automatic Speech Recognition Using HMM

José A. R. Fonollosa, Marta Casar, Marta Casar, 2007 .

N-gram-based Machine Translation

José B. Mariño, José A. R. Fonollosa, Rafael E. Banchs, 2006, CL.

A new algorithm for adaptive IIR filtering based on the log-area-ratio parameters

José A. R. Fonollosa, Enrique José Masgrau Gómez, 1990 .

Estimation of the modulation index of CPM signals using higher-order statistics

José A. R. Fonollosa, Javier Rodríguez Fonollosa, J. Fonollosa, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

On the adaptive lattice algorithms with data dependent parameters

José A. R. Fonollosa, Enrique José Masgrau Gómez, 1990 .

English-latvian SMT: the challenge of translating into a free word order language

José A. R. Fonollosa, Inguna Skadina, Maxim Khalilov, 2010, SLTU.

Blind channel estimation and data detection using hidden Markov models

José A. R. Fonollosa, Javier Rodríguez Fonollosa, Carles Antón-Haro, 1997, IEEE Trans. Signal Process..

Including zeros in the backward adaptive predictor of AVPC coders

José A. R. Fonollosa, Enrique Masgrau, Asunción Moreno, 1989, EUROSPEECH.

Low delay phone recognition

José B. Mariño, José A. R. Fonollosa, Eloi Botile, 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

Blind multiuser identification and detection in CDMA systems

José A. R. Fonollosa, Zoran Zvonar, Josep Vidal, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Overcoming HMM Time and Parameter Independence Assumptions for ASR

José A. R. Fonollosa, Marta Casar, Marta Casar, 2008 .

Conditional distribution variability measures for causality detection

José A. R. Fonollosa, 2016, Cause Effect Pairs in Machine Learning.

Probabilistic algorithms for blind adaptive multiuser detection

José A. R. Fonollosa, Zoran Zvonar, Carles Antón-Haro, 1998, IEEE Trans. Signal Process..

Blind multiuser deconvolution in fading and dispersive channels

José A. R. Fonollosa, Zoran Zvonar, Josep Vidal, 1995, Proceedings of 1995 IEEE International Symposium on Information Theory.

Vocoder design based on HOS

José A. R. Fonollosa, Josep Vidal, Asunción Moreno, 1993, EUROSPEECH.

Towards Improving English-Latvian Translation: A System Comparison and a New Rescoring Feature

José A. R. Fonollosa, Inguna Skadina, Maxim Khalilov, 2010, LREC.

A Catalan Broadcast Conversational Speech Database

José A. R. Fonollosa, Henrik Schulz, 2009 .

SpeechDat-Car Fixed Platform

José A. R. Fonollosa, Asunción Moreno, 2000, LREC.

The UPC text-to-speech system for Spanish and catalan

José A. R. Fonollosa, Antonio Bonafonte, Ignasi Esquerra, 1998, ICSLP.

Modelo estocástico de traducción basado en N-gramas de tuplas bilinges y combinación log-lineal de características

José B. Mariño, José A. R. Fonollosa, Rafael E. Banchs, 2005, Proces. del Leng. Natural.

Character-based Neural Machine Translation pdf

José A. R. Fonollosa, Marta R. Costa-jussà, M. Costa-jussà, 2016, ACL.

Parametric modeling of PDF using a convolution of one-sided exponentials: application to HMM

José A. R. Fonollosa, Antonio Bonafonte Cávez, José Vidal Manzano, 1994 .

Detailed Description of the Development of a MOOC in the Topic of Statistical Machine Translation

Marta R. Costa-jussà, José A. R. Fonollosa, Jordi Petit, 2014, MICAI.

Pitch determination of noisy speech using higher order statistics

José A. R. Fonollosa, Asunción Moreno, A. Moreno, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A comparison of several recent methods of fundamental frequency and voicing decision estimation

José A. R. Fonollosa, E. Mousset, William A. Ainsworth, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

FIR system identification using a linear combination of cumulants

José A. R. Fonollosa, J. Vidal, A. Moreno, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A baseline system for the transcription of catalan broadcast conversation

José A. R. Fonollosa, Henrik Schulz, David Rybach, 2009 .

Coupling Hierarchical Word Reordering and Decoding in Phrase-Based Statistical Machine Translation

José A. R. Fonollosa, Mark Dras, Maxim Khalilov, 2009, SSST@HLT-NAACL.

Pitch analysis of noisy speech

José A. R. Fonollosa, M. Asunción Moreno Bilbao, M. A. M. Bilbao, 1992 .

Rational characteristic functions and markov chains

José A. R. Fonollosa, Antonio Bonafonte Cávez, José Vidal Manzano, 1995 .

Continuous space language models for the IWSLT 2006 task

Marta R. Costa-jussà, José A. R. Fonollosa, Holger Schwenk, 2006, IWSLT.

Ngram-based versus Phrase-based Statistical Machine Translation

José A. R. Fonollosa, Marta R. Costa-jussà, J. Mariño, 2005, IWSLT.

Enhancing Sequence-to-Sequence Modelling for RDF triples to Natural Text

José A. R. Fonollosa, Oriol Domingo, David Bergés, 2020, WEBNLG.

The UPC RDF-to-Text System at WebNLG Challenge 2020

José A. R. Fonollosa, Oriol Domingo, David Bergés, 2020, WEBNLG.

Using Reordering in Statistical Machine Translation based on Recursive Alignment Block Classification

José A. R. Fonollosa, Marta R. Costa-jussà, E. Monte, 2008 .

Ngram-based SMT System for IWSLT 2006

José A. R. Fonollosa, Marta R. Costa-jussà, Patrik Lambert, 2006 .

Speech analysis using higher-order statistics

José A. R. Fonollosa, J. Vidal, E. Masgrau, 1993 .

Arabic-English translation improvement by target-side neural network language modeling

José A. R. Fonollosa, Maxim Khalilov, Maxim Khalilov, 2008 .

Adaptive blind system identification using weighted cumulant slices

José A. R. Fonollosa, Josep Vidal, J. Vidal, 1996 .

PONDERACIÓN DE LAS PROBABILIDADES DE OBSERVACIÓN DE LOS HMM PARA VERIFICACIÓN DE LOCUCIONES EN SISTEMAS DE RAH

José A. R. Fonollosa, Marta Casar, 2005 .

Hybrid machine translation: integration of linguistics and statistics : editorial

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2015 .

N-gram-based versus phrase-based statistical machine translation

José B. Mariño, Marta R. Costa-jussà, José A. R. Fonollosa, 2005, IWSLT.

Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022

José A. R. Fonollosa, M. Costa-jussà, Gerard I. Gállego, 2022, IWSLT.

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

José A. R. Fonollosa, M. Costa-jussà, Gerard I. Gállego, 2022, INTERSPEECH.

Subband splitting, adaptive scalar prediction and vector quantization for speech coding

José A. R. Fonollosa, Enrique José Masgrau Gómez, J. Acebal, 1988 .

Character-level Intra Attention Network for Natural Language Inference

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2017, RepEval@EMNLP.

Linguistic knowledge-based vocabularies for Neural Machine Translation

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2020, Natural Language Engineering.

Chinese-Catalan

Marta R. Costa-jussà, José A. R. Fonollosa, Carlos Escolano, 2019, ACM Trans. Asian Low Resour. Lang. Inf. Process..

Joint Source-Target Self Attention with Locality Constraints pdf

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2019, ArXiv.

Statistical Machine Reordering

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2006, EMNLP.

Analytic performance evaluation of cumulant-based FIR system identification methods

José A. R. Fonollosa, J. M. Mendel, J.A.R. Fonollosa, 1992, [1992] IEEE Sixth SP Workshop on Statistical Signal and Array Processing.

Adaptive system identification based on higher-order statistics

José A. R. Fonollosa, Josep Vidal, Enrique Masgrau, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

An Ngram-based reordering model

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2009, Comput. Speech Lang..

From bilingual to multilingual neural‐based machine translation by incremental training

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2020, J. Assoc. Inf. Sci. Technol..

Towards Interlingua Neural Machine Translation pdf

Marta R. Costa-jussà, José A. R. Fonollosa, Carlos Escolano, 2019, ArXiv.

(Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation pdf

Marta R. Costa-jussà, José A. R. Fonollosa, Carlos Escolano, 2018, ArXiv.

Chinese–Spanish neural machine translation enhanced with character and word bitmap fonts

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2017, Machine Translation.

Automatic Spanish Translation of SQuAD Dataset for Multi-lingual Question Answering pdf

José A. R. Fonollosa, Marta R. Costa-jussa, Casimiro Pio Carrino, 2019, LREC.

End-to-End Speech Translation with the Transformer

Marta R. Costa-jussà, José A. R. Fonollosa, Carlos Escolano, 2018, IberSPEECH.

Enabling Zero-Shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders

José A. R. Fonollosa, M. Costa-jussà, C. Segura, 2020, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders pdf

José A. R. Fonollosa, Carlos Escolano, Mikel Artetxe, 2020, EACL.

Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders pdf

José A. R. Fonollosa, Carlos Escolano, Mikel Artetxe, 2020, ArXiv.

Determining CPU and memory requirements for real-time speech recognition systems using the TMS320C3x/C4x

José A. R. Fonollosa, José Adrián Rodríguez Fonollosa, Eloi Batlle Mont, 1996 .

BUCEADOR, a multi-language search engine for digital libraries

Eva Navas, Marta R. Costa-jussà, José A. R. Fonollosa, 2012, LREC.

Efficient Speech Translation with Dynamic Latent Perceivers

José A. R. Fonollosa, Gerard I. Gállego, Ioannis Tsiamas, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task

Marta R. Costa-jussà, José A. R. Fonollosa, Carlos Escolano, 2018, WMT.

A differentiable BLEU loss. Analysis and first results

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2018, ICLR.

Neural Network Language Models for Translation with Limited Data

José A. R. Fonollosa, Salvador España Boquera, María José Castro Bleda, 2008, 2008 20th IEEE International Conference on Tools with Artificial Intelligence.

The TALP-UPC Ngram-Based Statistical Machine Translation System for ACL-WMT 2008

José B. Mariño, Marta R. Costa-jussà, José A. R. Fonollosa, 2008, WMT@ACL.

Using Reordering in Statistical Machine Translation based on Alignment Block Classification

Marta R. Costa-jussà, José A. R. Fonollosa, Enric Monte-Moreno, 2008, LREC.

TALP phrase-based system and TALP system combination for IWSLT 2006

José B. Mariño, Marta R. Costa-jussà, José A. R. Fonollosa, 2006, IWSLT.

Syntax-driven Iterative Expansion Language Models for Controllable Text Generation

José A. R. Fonollosa, M. Costa-jussà, Noe Casas, 2020, SPNLP.

From bilingual to multilingual neural‐based machine translation by incremental training

José A. R. Fonollosa, M. Costa-jussà, C. Escolano, 2019, J. Assoc. Inf. Sci. Technol..

Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information

José A. R. Fonollosa, Christine Basta, Marta R. Costa-jussà, 2020, WINLP.

The TALP-UPC phrase-based translation systems for WMT12: Morphology simplification and domain adaptation

José B. Mariño, José A. R. Fonollosa, Enric Monte-Moreno, 2012, WMT@NAACL-HLT.

Automatic and Human Evaluation Study of a Rule-based and a Statistical Catalan-Spanish Machine Translation Systems

José B. Mariño, Marta R. Costa-jussà, Mireia Farrús, 2010, LREC.

Linguistic-based Evaluation Criteria to identify Statistical Machine Translation Errors

José A. R. Fonollosa, José Bernardo Mariño Acebal, José A. R. Fonollosa, 2010, EAMT.

PHRASE AND NGRAM-BASED STATISTICAL MACHINE TRANSLATION SYSTEM COMBINATION

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2009, Appl. Artif. Intell..

Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23

José A. R. Fonollosa, M. Costa-jussà, Gerard I. Gállego, 2023, IWSLT.

BERT Masked Language Modeling for Co-reference Resolution

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2019, Proceedings of the First Workshop on Gender Bias in Natural Language Processing.

SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations

José A. R. Fonollosa, M. Costa-jussà, Ioannis Tsiamas, 2022, ArXiv.

Byte-based Neural Machine Translation

Marta R. Costa-jussà, José A. R. Fonollosa, Carlos Escolano, 2017, SWCN@EMNLP.

First experiments on an HMM based double layer framework for automatic continuous speech recognition

José A. R. Fonollosa, Mónica Caballero Galeote, Albino Nogueiras Rodríguez, 2006 .

Automatic Speech Recognition with Deep Neural Networks for Impaired Speech

José A. R. Fonollosa, José A. R. Fonollosa, Cristina España-Bonet, 2016, IberSPEECH.

Using Linear Interpolation and Weighted Reordering Hypotheses in the Moses System

Marta R. Costa-jussà, José A. R. Fonollosa, José A. R. Fonollosa, 2010, LREC.

The TALP-UPC Phrase-Based Translation System for EACL-WMT 2009

José B. Mariño, Marta R. Costa-jussà, José A. R. Fonollosa, 2009, WMT@EACL.