Rafael E. Banchs, Josep M. Crego, Patrik Lambert, José B. Mariño
This article presents some experimental results on Chinese-Spanish machine translation. The implemented translation system is based on the statistical framework and, more specifically, it implements...
GEOVAQA: A VOICE ACTIVATED GEOGRAPHICAL QUESTION ANSWERING SYSTEM (2008)
Jordi Luque, Daniel Ferrés, Javier Hern, José B. Mariño, Horacio Rodríguez
In this paper we present GeoVAQA, a Restricted Domain Spoken Question Answering system in the scope of the Spanish geography. The system consists of a webbased application that allows speech input...
TALP Phrase-Based System and TALP System Combination for IWSLT 2006 (2008)
Josep M. Crego, Adrià De Gispert, Patrik Lambert, Maxim Khalilov, ...
This paper describes the TALP phrase-based statistical machine translation system, enriched with the statistical machine reordering technique. We also report the combination of this system and the...
Josep M. Crego, Patrik Lambert, Maxim Khalilov, José B. Mariño, ...
statistical machine translation enhanced with multiple
The TALP Ngram-based SMT System for IWSLT 2007 (2008)
Patrik Lambert, Josep M. Crego, Maxim Khalilov, José B. Mariño, Rafael E. Banchs, ...
BASURDE[LITE], A MACHINE-DRIVEN DIALOGUE SYSTEM FOR ACCESSING RAILWAY TIMETABLE INFORMATION (2008)
Roger Trias-sanz, José B. Mariño
We present Basurde[lite], a complete human-machine dialogue system for accessing railway information, based on machine-driven dialogues, a small vocabulary and grammar, and word and phrase spotting...
Taking Advantage of Spanish Speech Resources to Improve Catalan Acoustic HMMs (2008)
At TALP, we are working on speech recognition of official languages in Catalonia, i.e. Spanish and Catalan. These two languages share approximately 80 % of their allophones. The speech databases that...
Eurospeech 2001- Scandinavia Speech Emotion Recognition Using Hidden Markov Models (2008)
Albino Nogueiras, Asunción Moreno, Antonio Bonafonte, José B. Mariño
This paper introduces a first approach to emotion recognition using RAMSES, the UPC’s speech recognition system. The approach is based on standard speech recognition technology using hidden...
GEOVAQA: A VOICE ACTIVATED GEOGRAPHICAL QUESTION ANSWERING SYSTEM (2008)
Jordi Luque, Daniel Ferrés, Javier Hern, José B. Mariño, Horacio Rodríguez
In this paper we present GeoVAQA, a Restricted Domain Spoken Question Answering system in the scope of the Spanish geography. The system consists of a webbased application that allows speech input...
José B. Mariño, Jaume Padrell, Asunción Moreno, Climent Nadeu
Under the SpeechDat specifications, the Spanish member of SpeechDat consortium has recorded a Catalan database that includes one thousand speakers. This communication describes some experimental work...
Multidialectal Spanish Modeling for ASR (2008)
Mónica Caballero, José B. Mariño, Asunción Moreno
This paper describes the latest advances in our ongoing work in the area of Spanish multidialectal speech recognition. This work deals with the suitability of using a single multidialectal acoustic...
Fuzzy Reasoning in Confidence Evaluation of Speech Recognition (2007)
Gustavo Hernández-Ábrego, Gustavo Hernandez, José B. Mariño
Confidence measures represent a systematic way to express reliability of speech recognition results. A common approach to confidence measuring is to take profit of the information that several...
A Second Opinion Approach For Speech Recognition Verification (2007)
Gustavo Hernández Ábrego, José B. Mariño
In order to improve the reliability of speech recognition results, a verifying system, that takes profit of the information given from an alternative recognition step is proposed. The alternative...
Crego, Josep Maria, Mariño, José B.
This paper presents a reordering framework for statistical machine translation (SMT) where source-side reorderings are integrated into SMT decoding, allowing for a highly constrained reordered search...
Gispert, Adrià De, Mariño, José B.
Ngram-based Statistical Machine Translation relies on a standard Ngram language model of tuples to estimate the translation process. In training, this translation model requires a segmentation of...
Maja Popović, Hermann Ney, Adrià De Gispert, José B. Mariño, Deepa Gupta, Marcello Federico, ...
Evaluation of machine translation output is an important but difficult task. Over the last years, a variety of automatic evaluation measures have been studied, some of them like Word Error Rate...
Statistical machine translation without parallel corpus: bridging through Spanish (2006)
Adrià De Gispert, José B. Mariño
This paper presents a full experiment on large-vocabulary Catalan-English statistical machine translation without an English-Catalan parallel corpus, in the context of the debates of the European...
Maja Popovic, Hermann Ney, Adrià De Gispert, José B. Mariño, Deepa Gupta, Marcello Federico, ...
Evaluation of machine translation output is an important but difficult task. Over the last years, a variety of automatic evaluation measures have been studied, some of them like Word Error Rate...
Proceedings of the Workshop on Statistical Machine Translation, pages 142--145, (2006)
New York City, Patrik Lambert, José B. Mariño, Josep M. Crego, Maxim Khalilov, ...
This paper reports translation results for the "Exploiting Parallel Texts for Statistical Machine Translation" (HLT-NAACL Workshop on Parallel Texts 2006). We have studied different...
Proceedings of the Workshop on Statistical Machine Translation, pages 162--165, (2006)
New York City, Josep M. Crego, José B. Mariño, Adrià De Gispert, Maxim Khalilov, ...
This work presents translation results for the three data sets made available in the shared task "Exploiting Parallel Texts for Statistical Machine Translation" of the HLT-NAACL 2006...
Integration of postag-based source reordering into smt decoding by an extended search graph (2006)
Josep M. Crego, José B. Mariño
This paper presents a reordering framework for statistical machine translation (SMT) where source-side reorderings are integrated into SMT decoding, allowing for a highly constrained reordered search...
Ngram-based smt system enhanced with reordering patterns (2006)
Josep M. Crego, José B. Mariño, Adrià De Gispert, Maxim Khalilov, ...
This work presents translation results for the three data sets made available in the shared task “Exploiting Parallel Texts for Statistical Machine Translation ” of the HLT-NAACL 2006 Workshop on...
Ngram-based versus Phrasebased Statistical Machine Translation (2005)
Josep M. Crego, José B. Mariño
This work summarizes a comparison between two approaches to Statistical Machine Translation (SMT), namely Ngram-based and Phrase-based SMT. In both approaches, the translation process is based on...
Adrià De Gispert, José B. Mariño, Josep M. Crego
This paper introduces a rule-based classification of single-word and compound verbs into a statistical machine translation approach. By substituting verb forms by the lemma of their head verb, the...
An ngrambased statistical machine translation decoder (2005)
Josep M. Crego, José B. Mariño, Adrià De Gispert
In this paper we describe MARIE, an Ngram-based statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying...
Gispert, “Reordered search and tuple unfolding for ngram-based smt (2005)
Josep M. Crego, José B. Mariño, Adrià Degispert
In Statistical Machine Translation, the use of reordering for certain language pairs can produce a significant improvement on translation accuracy. However, the search problem is shown to be NP-hard...
Statistical machine translation of euparl data by using bilingual n-grams (2005)
Rafael E. Banchs, Josep M. Crego, Adrià Gispert, Patrik Lambert, José B. Mariño
This work discusses translation results for the four Euparl data sets which were made available for the shared task “Exploiting Parallel Texts for Statistical Machine Translation”. All results...
Finitestate-based and phrase-based statistical machine translation (2004)
Josep M. Crego, José B. Mariño, Adrià De Gispert
This paper shows the common framework that underlies the translation systems based on phrases or driven by finite state transducers, and summarizes a first comparison between them. In both approaches...
Frequency and time filtering of filter-bank energies for robust HMM speech recognition (2001)
Climent Nadeu, José B. Mariño, Javier Hern, Albino Nogueiras
In speech recognition, a discriminative quefrency weighting can be achieved by somewhat decorrelating the frequency sequence of log mel-scaled filter-bank energies with a computationally inexpensive...
Frequency And Time Filtering Of Filter-Bank Energies For Hmm Speech Recognition (2001)
Climent Nadeu, José B. Mariño, Jos� B. Mari��o, Javier Hernando, Albino Nogueiras
In speech recognition, a discriminative quefrency weighting can be achieved by somewhat decorrelating the frequency sequence of log mel-scaled filter-bank energies with a computationally inexpensive...
Frequency and time filtering of filter-bank energies for robust HMM speech recognition (2001)
Climent Nadeu, José B. Mariño, Javier Hern, Albino Nogueiras
In speech recognition, a discriminative quefrency weighting can be achieved by somewhat decorrelating the frequency sequence of log mel-scaled filter-bank energies with a computationally inexpensive...
Using X-Gram For Efficient Speech Recognition (1998)
Antonio Bonafonte, José B. Mariño, Jos� B. Mari��o
X-grams are a generalization of the n-grams, where the number of previous conditioning words is different for each case and decided from the training data. X-grams reduce perplexity with respect to...
The Demiphone Versus The Triphone In A Decision-Tree State-Tying Framework (1998)
José B. Mariño, Pau Pachès-Leal, Jos� B. Mari��o, Albino Nogueiras
The performances of the demiphone (a context dependent subword unit that models independently the left and the right parts of a phoneme) and the triphone are compared. Continuous density hidden...
Sethos: the UPC speech understanding system (1996)
Antonio Bonafonte, José B. Mariño, Albino Nogueiras
ABSTRACT. In EuroSpeech’95, we presented the first version of Sethos, the speech understanding system which has been developed at the UPC. In this paper some improvements are incorporated at...
Language Modeling Using X-Grams (1996)
Antonio Bonafonte, José B. Mariño, Jos� B. Mari��o
In this paper, an extension of n-grams is proposed. In this extension, the memory of the model (n) is not fixed a priori. Instead, first, large memories are accepted and afterwards, merging criteria...
Sethos: The Upc Speech Understanding System (1996)
Antonio Bonafonte, José B. Mariño, Jos� B. Mari��o, Albino Nogueiras
. In EuroSpeech'95, we presented the first version of Sethos, the speech understanding system which has been developed at the UPC. In this paper some improvements are incorporated at different...