Researcher position on Multilingual Spontaneous Speech Transcription
The candidate will participate in the NEL-GAITU project, whose aim is to promote multilingual language and speech technologies for Iberian languages. NEL-GAITU is part of a common and coordinated project between the different official languages of the Spanish state, called NEL (New Language Economy). The ultimate goal of NEL is the development of multilingual resources such as multilingual language models, as well as speech processing models and automatic translation systems that respond to the needs of society and are in line with current technology, in which multilingualism and the transfer between languages play a key role.
The specific objective of this position is to develop multilingual automatic transcription systems in a bilingual environment. The main challenge is to overcome some of the problems found in spontaneous speech in meetings at a bilingual environment where rapid change of language occurs (code-switching), change of speakers and least but not less, overlapping of speech.
The candidate will perform the following tasks, among others:
- Definition, training, validation and testing of Basque and Spanish bilingual voice models.
- Definition, training, validation and testing of speaker models for their application in speaker diarization
- Definition, training, validation and testing of language models for Basque and Spanish language detection
- Tuning and integration of the developed systems into applications demos.
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.
The candidate should preferably have a BSc degree in computer science, telecommunications engineering, or physics, and a MSc in language technologies and/or machine learning. We are looking for individuals who are passionate about speech processing and have a strong background in computer science and related fields. The applicants must demonstrate excellent communication skills in English. Knowledge of Basque will be highly valued.
Our ideal candidate has experience in machine learning, deep learning, statistical analysis and speech processing, as well as a strong proficiency in programming languages such as Python.
We welcome applicants from all backgrounds and are committed to creating an inclusive and supportive workplace.
2 and a half years
Gross salary is around 32.300 euros per year.
For questions and doubts please contact recruitment.hitz@ehu.eus. Please include the job ID when contacting us.
To submit your application please follow this link.
