The candidate will participate in the IKER-GAITU project whose objective is the development of language technologies, resources and tools for Basque. The results of the project will place Basque language in a position to allow the use of AI applications also in that language.

The specific objective of this position is to develop a bilingual Automatic Speech Recognizer for Basque and Spanish in the context of spontaneous speech. The main challenge is to overcome some of the problems found in spontaneous speech at a bilingual environment: rapid change of language (code-switching). The candidate will have to train and evaluate different strategies which can be followed to cope with bilingual code-switching. He or she will also have to prepare the suitable databases. Finally, the candidate will apply the developed systems to the specific task of transcribing speech from learners of Basque.

The candidate will perform the following tasks, among others:

• Definition, training, validation and testing of Basque and Spanish bilingual ASR models.
• Definition, training, validation and testing of language models for Basque and Spanish language detection
• Definition and preparation of databases
• Tuning and integration of the developed systems into a language level assessment task

The candidate will work with the research group Aholab, located in the Faculty of Engineering of Bilbao. The candidate will have the
possibility of attending national and international conferences.