Skip to main content

INTERACCION ACTIVA PARA TRANSCRIPCION DE HABLA Y TRADUCCION

TIN2012-31723

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Nacional de Proyectos de Investigación Fundamental
Subprogram Subprograma de Proyectos de Investigación Fundamental no Orientada
Call Proyectos I+D
Call year 2012
State Plan 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Management unit Secretaría de Estado de Investigación, Desarrollo e Innovación
Beneficiary centre UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 18
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Multimodal output combination for transcribing historical handwritten documents

  • GRANELL, EMILIO|||0000-0001-5782-7568
  • Martínez-Hinarejos, Carlos-D.|||0000-0002-6139-2891
Transcription of digitalised historical documents is an interesting task in the document analysis area. This transcription can be achieved by using Handwritten Text Recognition (HTR) on digitalised pages or by using Automatic Speech Recognition (ASR) on the dictation of contents. Moreover, another option is using both systems in a multimodal combination to obtain a draft transcription, given that combining the outputs of different recognition systems will generally improve the recognition accuracy. In this work, we present a new combination method based on Confusion Network. We check its effectiveness for transcribing a Spanish historical book. Results on both unimodal combination with different optical (for HTR) and acoustic (for ASR) models, and multimodal combination, show a relative reduction of Word and Character Error Rate of 14.3% and 16.6%, respectively, over the HTR baseline., Work partially supported by European Union -7th FP, under grant 600707 (tranScriptorium), and by the Spanish MEC under projects STraDA (TIN2012-37475-C02-01), Active2Trans (TIN2012-31723), and SmartWays (RTC-2014-1466-4).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Using automatic speech transcriptions in lecture recommendation systems

  • Pérez González de Martos, Alejandro Manuel
  • Rihtar, M.
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Juan, Alfons|||0000-0002-9984-4072
  • Civera Saiz, Jorge|||0000-0002-0963-0143
One problem created by the success of video lecture repositories is the difficulty faced by individual users when choosing the most suitable video for their learning needs from among the vast numbers available on a given site. Recommender systems have become extremely common in recent years and are used in many areas. In the particular case of video lectures, automatic speech transcriptions can be used to zoom in on user interests at a semantic level, thereby improving the quality of the recommendations made. In this paper, we describe a video lecture recommender system that uses automatic speech transcriptions, alongside other relevant text resources, to generate semantic lecture and user models. In addition, we present a real-life implementation of this system for the VideoLectures.NET repository., The research leading to these results has received funding from the PASCAL2 Network of Excellence under the PASCAL Harvest Project La Vie, the EU 7th Framework Programme (FP7/2007-2013) under grant agreement no. 287755 (transLectures), the ICT Policy Support Programme (ICT PSP/2007-2013) as part of the Competitiveness and Innovation Framework Programme (CIP) under grant agreement no. 621030 (EMMA), the Spanish MINECO Active2Trans (TIN2012-31723) research project, and by the Spanish Government with the FPU scholarship AP2010-4349.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Interactive Machine Translation using Hierarchical Translation Model

  • González-Rubio, Jesús
  • Ortiz-Martínez, Daniel
  • Benedí Ruiz, José Miguel
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] Current automatic machine translation systems are not able to generate error-free translations and human intervention is often required to correct their output. Alternatively, an interactive framework that integrates the human knowledge into the translation process has been presented in previous works. Here, we describe a new interactive machine translation approach that is able to work with phrase-based and hierarchical translation models, and integrates error-correction all in a unified statistical framework. In our experiments, our approach outperforms previous interactive translation systems, and achieves estimated effort reductions of as much as 48% relative over a traditional post-edition system., Work supported by the European Union 7 th Framework Program (FP7/2007-2013) under the CasMaCat project (grans agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Translating without In-domain Corpus: Machine TranslationPost-Editing with Online Learning Techniques

  • Lagarda Arroyo, Antonio Luís
  • Ortiz Martínez, Daniel
  • Alabau, V.
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] Globalization has dramatically increased the need of translating information from one language to another. Frequently, such translation needs should be satisfied under very tight time constraints. Machine translation (MT) techniques can constitute a solution to this overly complex problem. However, the documents to be translated in real scenarios are often limited to a specific domain, such as a particular type of medical or legal text. This situation seriously hinders the applicability of MT, since it is usually expensive to build a reliable translation system, no matter what technology is used, due to the linguistic resources that are required to build them, such as dictionaries, translation memories or parallel texts. In order to solve this problem, we propose the application of automatic post-editing in an online learning framework. Our proposed technique allows the human expert to translate in a specific domain by using a base translation system designed to work in a general domain whose output is corrected (or adapted to the specific domain) by means of an automatic post-editing module. This automatic post-editing module learns to make its corrections from user feedback in real time by means of online learning techniques. We have validated our system using different translation technologies to implement the base translation system, as well as several texts involving different domains and languages. In most cases, our results show significant improvements in terms of BLEU (up to 16 points) with respect to the baseline systems. The proposed technique works effectively when the n-grams of the document to be translated presents a certain rate of repetition, situation which is common according to the document-internal repetition property., Work partially supported by the European Union 7th Framework Programme (FP7/2007-2013) under the CasMaCat Project (Grant Agreement No. 287576), by Spanish MICINN under Grant TIN2012-31723, and by the Generalitat Valenciana under Grant ALMPR ALMAMATER (PROMETEUII/2014/030) and under Grant IMASI (ISIC/2012/004).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Improving on-line handwritten recognition in interactive machine translation

  • Alabau Gonzalvo, Vicente
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] On-line handwriting text recognition (HTR) could be used as a more natural way of interaction in many interactive applications. However, current HTR technology is far from developing error-free systems and, consequently, its use in many applications is limited. Despite this, there are many scenarios, as in the correction of the errors of fully-automatic systems using HTR in a post-editing step, in which the information from the specific task allows to constrain the search and therefore to improve the HTR accuracy. For example, in machine translation (MT), the on-line HTR system can also be used to correct translation errors. The HTR can take advantage of information from the translation problem such as the source sentence that is translated, the portion of the translated sentence that has been supervised by the human, or the translation error to be amended. Empirical experimentation suggests that this is a valuable information to improve the robustness of the on-line HTR system achieving remarkable results., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under Grant agreement no. 287576 (CasMaCat), from the EC (FEDER/FSE), and from the Spanish MEC/MICINN under the Active2Trans (TIN2012-31723) project. It is also supported by the Generalitat Valenciana under Grant ALMPR (Prometeo/2009/01) and GV/2010/067.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Evaluación de la revisión de transcripciones y traducciones automáticas de vídeos poliMedia

  • Valor Miró, Juan Daniel
  • Turró Ribalta, Carlos|||0000-0002-3840-9405
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[ES] Los vídeos docentes son una herramienta de gran aceptación en el mundo universitario, que se integran en metodologías activas y innovadoras, dando pie a plataformas como poliMedia, plataforma de la Universitat Politècnica de València (UPV) que permite la creación, publicación y difusión de este tipo de contenido multimedia. En el marco del proyecto europeo transLectures, la UPV ha generado automáticamente transcripciones y traducciones en español, catalán e inglés para todos los vídeos incluidos en el repositorio poliMedia. Las transcripciones y traducciones automáticas generadas tienen una alta calidad. Sin embargo, estas transcripciones y traducciones poseen errores inherentes al proceso automático de subtitulado utilizado, por lo que en ocasiones puede ser necesaria una revisión manual posterior para garantizar la ausencia de errores. El objetivo de este trabajo es evaluar este proceso de revisión manual para poder compararlo en términos de coste temporal con un proceso de obtención completamente manual. Así pues, en el marco de las ayudas de la UPV de Docencia en Red 2013-2014, pusimos en marcha una campaña de evaluación del proceso de revisión de transcripciones y traducciones automáticas por parte del profesorado, cuyos resultados indican inequívocamente la eficacia de estas técnicas y el importante ahorro de tiempo que suponen., The research leading to these results has received funding from the European Union FP7/2007- 2013 under grant agreement no 287755 (transLectures) and ICT PSP/2007-2013 under grant agreement no 621030 (EMMA), and the Spanish MINECO Active2Trans (TIN2012-31723) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Efficiency and usability study of innovative computer-aided transcription strategies for video lecture repositories

  • Valor Miró, Juan Daniel
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Turró Ribalta, Carlos|||0000-0002-3840-9405
  • Juan, Alfons|||0000-0002-9984-4072
[EN] Video lectures are widely used in education to support and complement face-to-face lectures. However, the utility of these audiovisual assets could be further improved by adding subtitles that can be exploited to incorporate added-value functionalities such as searchability, accessibility, translatability, note-taking, and discovery of content-related videos, among others. Today, automatic subtitles are prone to error, and need to be reviewed and post-edited in order to ensure that what students see on-screen are of an acceptable quality. This work investigates different user interface design strategies for this post-editing task to discover the best way to incorporate automatic transcription technologies into large educational video repositories. Our three-phase study involved lecturers from the Universitat Polite`cnica de Vale`ncia (UPV) with videos available on the poliMedia video lecture repository, which is currently over 10,000 video objects. Simply by conventional post-editing automatic transcriptions users almost reduced to half the time that would require to generate the transcription from scratch. As expected, this study revealed that the time spent by lecturers reviewing automatic transcriptions correlated directly with the accuracy of said transcriptions. However, it is also shown that the average time required to perform each individual editing operation could be precisely derived and could be applied in the definition of a user model. In addition, the second phase of this study presents a transcription review strategy based on confidence measures (CM) and compares it to the conventional post-editing strategy. Finally, a third strategy resulting from the combination of that based on CM with massive adaptation techniques for automatic speech recognition (ASR), achieved to improve the transcription review efficiency in comparison with the two aforementioned strategies. 2015 Elsevier B.V. All rights reserved., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under Grant agreement no. 287755 (transLectures) and ICT Policy Support Programme (ICT PSP/2007-2013) as part of the Competitiveness and Innovation Framework Programme (CIP) under Grant agreement no. 621030 (EMMA), and the Spanish MINECO Active2Trans (TIN2012-31723) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Handwriting recognition in historical documents using very large vocabularies

  • Frinken, Volkmar
  • Fischer, Andreas
  • Martínez-Hinarejos, Carlos-D.|||0000-0002-6139-2891
Language models are used in automatic transcription system to resolve ambiguities. This is done by limiting the vocabulary of words that can be recognized as well as estimating the n-gram probability of the words in the given text. In the context of historical documents, a non-unified spelling and the limited amount of written text pose a substantial problem for the selection of the recognizable vocabulary as well as the computation of the word probabilities. In this paper we propose for the transcription of historical Spanish text to keep the corpus for the n-gram limited to a sample of the target text, but expand the vocabulary with words gathered from external resources. We analyze the performance of such a transcription system with different sizes of external vocabularies and demonstrate the applicability and the significant increase in recognition accuracy of using up to 300 thousand external words., This work has been supported by the European project FP7-PEOPLE-2008-IAPP: 230653 the European Research Council’s Advanced Grant ERC-2010-AdG 20100407, the Spanish R&D projects TIN2009-14633-C03-03, RYC-2009-05031, TIN2011-24631, TIN2012-37475-C02-02, MITTRAL (TIN2009-14633-C03-01), Active2Trans (TIN2012-31723) as well as the Swiss National Science Foundation fellowship project PBBEP2_141453.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Efficient Generation of High-Quality Multilingual Subtitles for Video Lecture Repositories

  • Valor Miró, Juan Daniel
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Turró Ribalta, Carlos|||0000-0002-3840-9405
  • Juan, Alfons|||0000-0002-9984-4072
Video lectures are a valuable educational tool in higher education to support or replace face-to-face lectures in active learning strategies. In 2007 the Universitat Politècnica de València (UPV) implemented its video lecture capture system, resulting in a high quality educational video repository, called poliMedia, with more than 10.000 mini lectures created by 1.373 lecturers. Also, in the framework of the European project transLectures, UPV has automatically generated transcriptions and translations in Spanish, Catalan and English for all videos included in the poliMedia video repository. transLectures’s objective responds to the widely-recognised need for subtitles to be provided with video lectures, as an essential service for non-native speakers and hearing impaired persons, and to allow advanced repository functionalities. Although high-quality automatic transcriptions and translations were generated in transLectures, they were not error-free. For this reason, lecturers need to manually review video subtitles to guarantee the absence of errors. The aim of this study is to evaluate the efficiency of the manual review process from automatic subtitles in comparison with the conventional generation of video subtitles from scratch. The reported results clearly indicate the convenience of providing automatic subtitles as a first step in the generation of video subtitles and the significant savings in time of up to almost 75 % involved in reviewing subtitles., The research leading to these results has received funding fromthe European Union FP7/2007-2013 under grant agreement no 287755 (transLectures) and ICT PSP/2007-2013 under grant agreement no 621030 (EMMA), and the Spanish MINECO Active2Trans (TIN2012-31723) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

The TransLectures-UPV Toolkit

  • Del Agua Teba, Miguel Angel
  • Serrano Martinez Santos, Nicolas
  • Andrés Ferrer, Jesús
  • Giménez Pastor, Adrián
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
Over the past few years, online multimedia educational repositories have increased in number and popularity. The main aim of the transLectures project is to develop cost-effective solutions for producing accurate transcriptions and translations for large video lecture repositories, such as VideoLectures.NET or the Universitat Politècnica de València s repository, poliMedia. In this paper, we present the transLectures-UPV toolkit (TLK), which has been specifically designed to meet the requirements of the transLectures project, but can also be used as a conventional ASR toolkit. The main features of the current release include HMM training and decoding with speaker adaptation techniques (fCMLLR). TLK has been tested on the VideoLectures.NET and poliMedia repositories, yielding very competitive results. TLK has been released under the permissive open source Apache License v2.0 and can be directly downloaded from the transLectures website., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755 (transLectures) and ICT Policy Support Programme (ICT PSP/2007-2013) as part of the Competitiveness and InnovationFramework Programme (CIP) under grant agreement no 621030 (EMMA), andthe Spanish MINECO Active2Trans (TIN2012-31723) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Cost-sensitive active learning for computer-assisted translation

  • González Rubio, Jesús
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] Machine translation technology is not perfect. To be successfully embedded in real-world applications, it must compensate for its imperfections by interacting intelligently with the user within a computer-assisted translation framework. The interactive¿predictive paradigm, where both a statistical translation model and a human expert collaborate to generate the translation, has been shown to be an effective computer-assisted translation approach. However, the exhaustive supervision of all translations and the use of non-incremental translation models penalizes the productivity of conventional interactive¿predictive systems. We propose a cost-sensitive active learning framework for computer-assisted translation whose goal is to make the translation process as painless as possible. In contrast to conventional active learning scenarios, the proposed active learning framework is designed to minimize not only how many translations the user must supervise but also how difficult each translation is to supervise. To do that, we address the two potential drawbacks of the interactive-predictive translation paradigm. On the one hand, user effort is focused to those translations whose user supervision is considered more ¿informative¿, thus, maximizing the utility of each user interaction. On the other hand, we use a dynamic machine translation model that is continually updated with user feedback after deployment. We empirically validated each of the technical components in simulation and quantify the user effort saved. We conclude that both selective translation supervision and translation model updating lead to important user-effort reductions, and consequently to improved translation productivity., Work supported by the European Union Seventh Framework Program (FP7/2007-2013) under the CasMaCat Project (Grants agreement No. 287576), by the Generalitat Valenciana under Grant ALMPR (Prometeo/2009/014), and by the Spanish Government under Grant TIN2012-31723. The authors thank Daniel Ortiz-Martinez for providing us with the log-linear SMT model with incremental features and the corresponding online learning algorithms. The authors also thank the anonymous reviewers for their criticisms and suggestions.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Speaker-adapted confidence measures for speech recognition of video lectures

  • Sanchez-Cortina, Isaias
  • Andrés Ferrer, Jesús
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
[EN] 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 native 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., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755. Also supported by the Spanish MINECO (iTrans2 TIN2009-14511 and Active2Trans TIN2012-31723) research projects and the FPI Scholarship BES-2010-033005.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Improving the minimum description length inference of phrase-based translation models

  • Gonzalez Rubio, Jesus
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
We study the application of minimum description length (MDL) inference to estimate pattern recognition models for machine translation. MDL is a theoretically-sound approach whose empirical results are however below those of the state-of-the-art pipeline of training heuristics. We identify potential limitations of current MDL procedures and provide a practical approach to overcome them. Empirical results support the soundness of the proposed approach., Work supported by the EU 7th Framework Programme (FP7/2007–2013) under the CasMaCat project (grant agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Statistical text-to-speech synthesis of Spanish subtitles

  • Piqueras Gozalbes, Santiago Romualdo
  • Del Agua Teba, Miguel Angel
  • Giménez Pastor, Adrián
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish sys- tem and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755 (transLectures) and ICT Policy Support Programme (ICT PSP/2007-2013) as part of the Competitiveness and Innovation Framework Programme (CIP) under grant agreement no 621030 (EMMA), and the Spanish MINECO Active2Trans (TIN2012-31723) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Comparison of Data Selection Techniques for the Translation of Video Lectures

  • Wuebker, Joern
  • Ney, Hermann
  • Martínez-Villaronga, Adrià
  • Servan, Christophe
  • Dymetman, Marc
  • Mirkin, Shashar
  • Giménez Pastor, Adrián
  • Juan, Alfons|||0000-0002-9984-4072
[EN] For the task of online translation of scientific video lectures, using huge models is not possible. In order to get smaller and efficient models, we perform data selection. In this paper, we perform a qualitative and quantitative comparison of several data selection techniques, based on cross-entropy and infrequent n-gram criteria. In terms of BLEU, a combination of translation and language model cross-entropy achieves the most stable results. As another important criterion for measuring translation quality in our application, we identify the number of out-ofvocabulary words. Here, infrequent n-gram recovery shows superior performance. Finally, we combine the two selection techniques in order to benefit from both their strengths., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755 (transLectures), and the Spanish MINECO Active2Trans (TIN2012-31723) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

The New THOT Toolkit for Fully-Automatic and Interactive Statistical Machine Translation

  • Ortiz-Martínez, Daniel
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] We present the new THOT toolkit for fullyautomatic and interactive statistical machine translation (SMT). Initial public versions of THOT date back to 2005 and did only include estimation of phrase-based models. By contrast, the new version offers several new features that had not been previously incorporated. The key innovations provided by the toolkit are computeraided translation, including post-editing and interactive SMT, incremental learning and robust generation of alignments at phrase level. In addition to this, the toolkit also provides standard SMT features such as fully-automatic translation, scalable and parallel algorithms for model training, client-server implementation of the translation functionality, etc. The toolkit can be compiled in Unix-like and Windows platforms and it is released under the GNU Lesser General Public License (LGPL)., Work supported by the European Union 7 th Framework Program (FP7/2007-2013) under the CasMaCat project (grant agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Unsegmented Dialogue Act Annotation and Decoding with N-Gram Transducers

  • Martínez-Hinarejos, Carlos-D.|||0000-0002-6139-2891
  • Benedí Ruiz, José Miguel
  • Tamarit Ballester, Vicent
Most studies on dialogue corpora, as well as most dialogue systems, employ dialogue acts as the basic units for interpreting discourse structure, user input and system actions. The definition of the discourse structure and the dialogue strategy consequently require the tagging of dialogue corpora in terms of di- alogue acts. The tagging problem presents two basic variants: a batch variant (annotation of whole dialogues, in order to define dialogue strategy or study discourse structure) and an online variant (decoding of the dialogue act sequence of a given turn, in order to interpret user intentions). In the two variants is unusual having the segmentation of each turn into the dialogue meaningful units (segments) to which a dialogue act is assigned. In this paper we present the use of the N-Gram Transducer technique for tagging dialogues, without needing to provide a prior segmentation, in these two different variants (dialogue annotation and turn decoding). Experiments were performed in two corpora of different nature and results show that N-Gram Transducer models are suitable for these tasks and provide good performance., This work was supported in part by the Spanish MEC/MICINN under STraDA (TIN2012-37475-C02-01) and Active2Trans (TIN2012-31723) projects, and in part by the Generalitat Valenciana under project AMIIS (ISIC/2012/004). The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Bowen Zhou.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Language model adaptation for lecture transcription by document retrieval

  • Martínez-Villaronga, Adrià
  • Del Agua Teba, Miguel Angel
  • Andrés Ferrer, Jesús
  • Juan, Alfons
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
With the spread of MOOCs and video lecture repositories it is more important than ever to have accurate methods for automatically transcribing video lectures. In this work, we propose a simple yet effective language model adaptation technique based on document retrieval from the web. This technique is combined with slide adaptation, and compared against a strong baseline language model and a stronger slide-adapted baseline. These adaptation techniques are compared within two different acoustic models: a standard HMM model and the CD-DNN-HMM model. The proposed method obtains improvements on WER of up to 14% relative with respect to a competitive baseline as well as outperforming slide adaptation., The research leading to these results has received fund-ing from the European Union Seventh Framework Programme (FP7/2007-2013)under grant agreement no 287755 (transLectures) and ICT Policy Support Pro-gramme (ICT PSP/2007-2013) as part of the Competitiveness and Innovation Framework Programme (CIP) under grant agreement no 621030 (EMMA), the Spanish MINECO Active2Trans (TIN2012-31723) research project and the Spanish Government with the FPU scholarships FPU13/06241 and AP2010-4349.