Cloud-Based Web Services for Endangered Language Analysis (Invited Paper)

Language endangerment is one of the most urgent problems facing humanities, with roughly one language disappearing every two weeks. Currently most of the linguistics tools used for endangered language documentation and analysis are desktop-based standalone software systems that do not expose libraries or services to be integrated by user applications, nor do they sufficiently support data sharing among different users for collaborative research efforts. To address this issue, we present a general architecture to design and develop an integrative computational platform for endangered language documentation and analysis (called PELDA) using RESTful web services and cloud computing techniques. The web services developed and deployed on the cloud platform can be easily integrated into any applications that support HTTP communications, while general users can access the linguistics tools and manage data files via web browsers. Then using Praat, an open source linguistics tool for acoustic analysis, as an example, we discuss the unique challenges and basic procedure to migrate linguistics tools to the cloud platform and demonstrate the feasibility of the proposed approach.