Digitalization of the intangible cultural heritage of the Pomaks of Xanthi

In this paper the language and the oral tradition of the Pomaks of Western Thrace is studied as a part of their intangible cultural heritage. Digital technologies can play an important role in the preservation and transmission of intangible cultural heritage. In Greece, audiovisual material from the Rhodope region dates back to the 1960s. In 1995 the "Thrace" project was launched, focusing on the collection of folk songs and extracts of speech from various villages of Thrace. The “CT-Audio Link” web project (2015-2016) included digitized recordings of Pomak songs, fairy tales, proverbs, wishes, curses and excerpts of spoken word. We present “Philotis”, a research project implemented at the Athena-Research and Innovation Center in Information, Communication and Knowledge Technologies / Xanthi’s Branch (2020-2023). “Philotis” focuses on the creation of the infrastructure, the methodology and the tools for the recording, analysis and documentation of living spoken languages, with emphasis on idiomatic language. The infrastructure is characterized by state-of-the-art multimodal technologies (text, image, audio), while the tools integrate into an advanced digital platform for language analysis and documentation using machine learning techniques. The development support framework utilizes modern technology and adapts to the specific needs and characteristics of the individual languages, offering methodology, good practices and digital services. Among the project outputs are a morphosyntactically annotated Pomak corpus that is openly available, a gold annotated corpus on the UD treebank repository, an Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) model, and multiword expressions (MWE) documentation. Innovative research projects make available cultural resources that could not be easily developed otherwise. Therefore, the use of new technologies for the preservation and dissemination of the intangible cultural heritage of the Pomaks offers fertile grounds for significant applications in the fields of sociological and linguistic research, folklore studies and education