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.

TALP's work includes Text, Speech and Audio Technology topics

  • audio analysis and enhancement,
  • construction and use of multilingual lexical resources,
  • development of speech databases,
  • information extraction,
  • information retrieval,
  • machine learning methods,
  • machine translation,
  • multilingual robust speech recognition,
  • multilingual text-to-speech conversion,
  • natural language interfaces,
  • natural language processing tools,
  • speaker and emotions recognition.  

TALP_UPC enjoys a strong presence in the international forums, with frequent collaboration in conference committees, PhD thesis panels, journal editors, etc. Furthermore, our center has a long experience participating in European projects(Acquilex, Acquilex II, EuroWN, SAM-A, SpeechDat, SpeechDat II, SpeechDatCar, SPEECON, SALA, LC-STAR, NAMIC, FAME, MEANING, LC-STAR II, Orientel, SALA II, LILA, BIOSEC, HOPS, CHIL, TC-STAR, FAUST, MOLTO, Metanet4u, XLIKE. CAMOMILE, FlaraNet i ALLIES) and one DARPA project (Arabic WordNet).

Moreover, as an R&D center, the TALP is actively involved in basic and applied research project. TALP is one of the 20 UPC Centers which are included in the UPC Technology Center (CIT UPC) is a non-profit entity, attached to the UPC but with its own legal personality. It is dedicated to applying university research capabilities to innovation in business . The mission of the CIT is to promote greater business competitiveness by creating, developing and implementing in companies differential technological knowledge that is generated in the UPC’s research and development centres. Furthermore, since 2016, TALP is candidate to get the TECNIO certificate. TECNIO Certificate is granted to the most qualified agents involved in technology transfer processes, increasing the visibility of the TECNIO Centers. As TECNIO candidate we have elaborated a detailed marketing and action plan, with a deep analysis of the industrial sectors where our technologies can provide competitive advantage.

TALP is part of the Catalan Cluster of Language Industries (CLUSTERLINGUA) is an association of companies based in Catalonia that provides services related to multiculturalism and multilingualism.The objectives of the association are to promote and contribute to the competitiveness of Catalonia’s language industry by encouraging partner innovation and improving conditions in the whole sector, in order to favorably meet its globalization needs.The activities of companies in the Cluster include translation services, subtitling, dubbing and indexing, as well as content internationalization and globalization.

The TALP center is part of RTTH, a Thematic Network in Speech Technologies. It is a common forum where researchers in Speech Technology can combine efforts and share experiences. It is currently composed of 17 Spanish research groups. Its objectives are to foster research in Speech Technologies, attract investments for companies' research towards Speech Technologies, and advance in the creation of collaboration and integration links of the Network members. RTTH is funded by the Spanish Government.

The TALP center is a permanent member of the organizing committee of the International Conference on Language Resources and Evaluation (LREC). It has a biannual periodicity and the scope is worldwide. It is a reference congress on linguistic resources.


Scroll to Top