The Albayzin 2010 Language Recognition Evaluation

The Albayzin 2010 Language Recognition Evaluation (LRE), carried out from June to October 2010, was the second effort made by the Spanish/Portuguese community for benchmarking language recognition technology. As the Albayzin 2008 LRE, it was coordinated by the Software Technology Working Group of the University of the Basque Country, with the support of the Spanish Thematic Network on Speech Technology. A speech database was created for system development and evaluation. Speech signals were recorded from TV broadcasts, including clean and noisy speech. The task consisted in deciding whether or not a target language was spoken in a test utterance, and in- volved 6 target languages: English, Portuguese and the four of- ficial languages in Spain (Basque, Catalan, Galician and Span- ish), other (Out-Of-Set) languages being also recorded to allow open-set verification tests. This paper presents the main fea- tures of the evaluation, analyses system performance on differ- ent conditions, including the confusion among languages, and gives hints for future evaluations.