2016
|
Sanchez-Cortina, Isaias; Andrés-Ferrer, Jesús; Sanchis, Alberto; Juan, Alfons Speaker-adapted confidence measures for speech recognition of video lectures Journal Article Computer Speech & Language, 37 , pp. 11–23, 2016, ISBN: 0885-2308. Abstract | Links | BibTeX | Tags: Confidence measures, Log-linear models, Online video lectures, Speaker adaptation, Speech Recognition @article{SanchezCortina2016,
title = {Speaker-adapted confidence measures for speech recognition of video lectures},
author = {Isaias Sanchez-Cortina and Jesús Andrés-Ferrer and Alberto Sanchis and Alfons Juan},
url = {http://www.sciencedirect.com/science/article/pii/S0885230815000960
http://authors.elsevier.com/a/1SAsB39HpSHRc0},
isbn = {0885-2308},
year = {2016},
date = {2016-01-01},
journal = {Computer Speech & Language},
volume = {37},
pages = {11--23},
abstract = {Abstract Automatic Speech Recognition applications can benefit from a confidence measure (CM) to predict the reliability of the output. Previous works showed that a word-dependent naïve Bayes (NB) classifier outperforms the conventional word posterior probability as a CM. However, a discriminative formulation usually renders improved performance due to the available training techniques. Taking this into account, we propose a logistic regression (LR) classifier defined with simple input functions to approximate to the \\{NB\\} behaviour. Additionally, as a main contribution, we propose to adapt the \\{CM\\} to the speaker in cases in which it is possible to identify the speakers, such as online lecture repositories. The experiments have shown that speaker-adapted models outperform their non-adapted counterparts on two difficult tasks from English (videoLectures.net) and Spanish (poliMedia) educational lectures. They have also shown that the \\{NB\\} model is clearly superseded by the proposed \\{LR\\} classifier.},
keywords = {Confidence measures, Log-linear models, Online video lectures, Speaker adaptation, Speech Recognition},
pubstate = {published},
tppubtype = {article}
}
Abstract Automatic Speech Recognition applications can benefit from a confidence measure (CM) to predict the reliability of the output. Previous works showed that a word-dependent naïve Bayes (NB) classifier outperforms the conventional word posterior probability as a CM. However, a discriminative formulation usually renders improved performance due to the available training techniques. Taking this into account, we propose a logistic regression (LR) classifier defined with simple input functions to approximate to the \{NB\} behaviour. Additionally, as a main contribution, we propose to adapt the \{CM\} to the speaker in cases in which it is possible to identify the speakers, such as online lecture repositories. The experiments have shown that speaker-adapted models outperform their non-adapted counterparts on two difficult tasks from English (videoLectures.net) and Spanish (poliMedia) educational lectures. They have also shown that the \{NB\} model is clearly superseded by the proposed \{LR\} classifier. |
2012
|
Silvestre-Cerdà, Joan Albert; Andrés-Ferrer, Jesús; Civera, Jorge Explicit length modelling for statistical machine translation Journal Article Pattern Recognition, 45 (9), pp. 3183 - 3192, 2012, ISSN: 0031-3203. Abstract | Links | BibTeX | Tags: Length modelling, Log-linear models, Phrase-based models, Statistical machine translation @article{Silvestre-Cerdà2012a,
title = {Explicit length modelling for statistical machine translation},
author = {Joan Albert Silvestre-Cerdà and Jesús Andrés-Ferrer and Jorge Civera},
url = {http://hdl.handle.net/10251/34996},
issn = {0031-3203},
year = {2012},
date = {2012-01-01},
journal = {Pattern Recognition},
volume = {45},
number = {9},
pages = {3183 - 3192},
abstract = {Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative parametrisation for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs prove the benefits of explicit length modelling.},
keywords = {Length modelling, Log-linear models, Phrase-based models, Statistical machine translation},
pubstate = {published},
tppubtype = {article}
}
Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative parametrisation for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs prove the benefits of explicit length modelling. |
2011
|
Silvestre-Cerdà, Joan Albert; Andrés-Ferrer, Jesús ; Civera, Jorge Explicit Length Modelling for Statistical Machine Translation Incollection Vitrià, Jordi ; Sanches, JoãoMiguel ; Hernández, Mario (Ed.): Pattern Recognition and Image Analysis (IbPRIA 2011), 6669 , pp. 273-280, Springer Berlin Heidelberg, 2011, ISBN: 978-3-642-21256-7. Abstract | Links | BibTeX | Tags: Length modelling, Log-linear models, Phrase-based models, Statistical machine translation @incollection{Silvestre-Cerdà2011,
title = {Explicit Length Modelling for Statistical Machine Translation},
author = { Joan Albert Silvestre-Cerdà and Jesús Andrés-Ferrer and Jorge Civera},
editor = {Vitrià, Jordi and Sanches, JoãoMiguel and Hernández, Mario},
url = {http://hdl.handle.net/10251/35749
http://dx.doi.org/10.1007/978-3-642-21257-4_34},
isbn = {978-3-642-21256-7},
year = {2011},
date = {2011-01-01},
booktitle = {Pattern Recognition and Image Analysis (IbPRIA 2011)},
volume = {6669},
pages = {273-280},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes in Computer Science},
abstract = {Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, promising experimental results are reported on a reference SMT task.},
keywords = {Length modelling, Log-linear models, Phrase-based models, Statistical machine translation},
pubstate = {published},
tppubtype = {incollection}
}
Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, promising experimental results are reported on a reference SMT task. |