The Center for Language and Speech Technologies and Applications (TALP) is a specific interdepartmental research center at the Technical University of Catalunya (UPC).

The technological scope of the TALP Center is the automatic processing of both written and spoken natural language. Its aim is to help overcome language barriers to improve access to information systems focusing on research and development in the area of human language processing. The center is comprised of two research groups: The Speech Processing Group at the Signal Theory and Communication Department and the Natural Language Processing Group at the Software Department. Both of them enjoy the status of a Consolidated Research Group, conferred by the Catalan Government.

The centre has been involved in research and development of spoken and written language processing technologies and applications with special attention to English, Spanish, Catalan, and Arabic. Our research activities include construction and use of multilingual lexical resources, knowledge acquisition and representation, information extraction, machine learning methods, machine translation, text summarization, question answering, dialog systems, speech technologies (recognition, representation, enhancement, etc), audio processing and classification, multimodal perceptual interfaces in smart room environments, speech synthesis, natural language interfaces, and core language technologies (such as morpho-syntactic and semantic analyzers, word sense disambiguation, named entity recognition).

Moreover, as an R&D center, the TALP is actively involved in basic and applied research project.     





7:00 - Doors open. Welcome. Networking. Beer.

7:15 - Convolutional Neural Networks for NLP.

7:45 - Q&A break.

8:00 - Introduction in Generative Adversarial Networks.

8:30 - Q&A break

8:45 - Networking.

Convolutional Neural Networks for NLP.

Convolutional Neural Networks have proven very effective in classification tasks. Initially created for computer vision for image recognition and classification, they were adopted also in natural language processing (NLP). We will make a short introduction in Convolutional Neural Networks and will explain how they apply to NLP problems.


Carlos Segura has a Telecommunications Engineering background and received his PhD from the UPC in 2011 in multimedia signal processing. He has been doing research in Deep Learning for the last 3 years applied to computer vision, speech processing and more lately in natural language processing and dialog systems. He currently works at Telefónica I+D as an associate researcher.

Silvia Necsulescu, passionate about algorithms and foreign languages, got a PhD in Natural Language Processing from UPF Barcelona addressing the automatic extraction of semantically related words. She works as an NLP Scientist on problems about automatic text classification.

Introduction to Generative Adversarial Networks.

Generative Adversarial Networks are a recent type of generative model framed within Deep Learning. They allow us to model very high dimensional distributions, making them very effective to generate novel samples for complex domains. They have been applied successfully in computer vision, where these systems generate images of high quality out of detailed descriptions. Other fields also are adopting this adversarial methodology for its proven effectiveness, like speech processing. In this talk GANs will be introduced, as well as their current applications in different domains. Moreover, there will be a coding example to see how we can construct a GAN to solve a toy example in TensorFlow.


Santiago Pascual, graduated in Telecommunications Engineering in 2016 at Telecom BCN@UPC. He has been working in Deep Learning research for more than two years, and more specifically in speech and language processing with these methodologies. Nonetheless, he also likes working in multimodal technologies, in an end2end fashion whenever it is possible. He is currently a PhD candidate at TALP@UPC, working in architectures for end2end speech processing with deep learning.

Hem afegit al Joomla la possibilitat de pujar els fitxers de la vostra web personal, per si voleu crear-ne una.

  Simplement heu d'entrar a la intranet, i pujar els fitxers amb el formulari que surt a baix a l'esquerra.
  Alla mateix podeu gestionar els fitxers que tingueu posats.
  Tot el que es pugi a traves d'aqui, sera visible a traves de<nomusuari>
  ( on <nomusuari> es el vostre usuari de la intranet.)

  Podeu pujar la vostra pagina en hmtl o en php.
  Podeu pujar-hi els fitxers adidcionals que necessiteu (imatges, css, pdfs, ect).
  Hi ha l'opcio de pujar diversos fitxers de cop (clicant el botonet "+" i afegint-los a la llista).

     - Feu que els enllaços dins de la vostra pagina siguin relatius,
       aixi tindreu menys problemes.

     - L'applet permet pujar fitxers, sobreescriure'ls amb una nova versio,
       o esborrar-los, pero no permet modificar-los. Per tant, guardeu una copia
       local de la vostra web, per si voleu fer-hi modificacions.

   Si teniu cap dubte o problema, digueu-nos-ho a la Maria o al Lluís


  • Online Patent Translation
  • Treeler - an open-source c++ library of structure prediction methods, focusing on NLP tasks like tagging and parsing.
  • Sibyl - QA engine for spoken documents.

  • Fescat - Festival parla català
  • AEDL - Acoustic event detection and localization in multimodal room

  • ALICE - Integration of several state-of-the-art technologies related to spoken language and natural language processing used in Intelligent Computer Assisted Language Learning (ICALL) systems

  • Asiya - An Open Toolkit for Automatic Machine Translation (Meta-)Evaluation

  • AVIVAVOZ - Voice translation technologies:  recognition, statistical machine translation based on corpus and synthesis.

  • Bidirectional machine translator between Spanish and Catalan: piece of program Àgora (March 2009) in Flash format

  • DIGUI - Flexible DIalogues Guiding the User Interaction for accesing web services

  • Freeling - Open source suite of Language Analyzers.

  • LCsum - Lexical Chain based summarizer

  • Machine Translation interface that combines several on-line MT systems to enable translation to/from any available language.

  • N-II - Statistical machine translator between Spanish and Catalan

  • Ogmios - Text-to-Speech system

  • Spanish and Catalan WordNets: knowledge bases following the EuroWordNet framework and structured in the same way as the American wordnet for English (Princeton WordNet) in terms of synsets (sets of synonymous words) with basic semantic relations between them.

  • Speech adaptation demostration in speech synthesis

Additional information