Service description
Web-services provided by the Laboratory of Languge Technology at TTÜ are part of the infrastructure of the Center of Estonian Language Resources (CELR) and the pan-european CLARIN ERIC network. The services include: * Brauser of audio achives - enables brausing and search in automatically transcribed audio files * Web-based speech recognition - automatic transcription of speech recordings in Estonian * Dictation - real-time automatic speech recognition * Corpora - web-baser search engine enables queries in different speech corpora * Autosegmentation - word and phoneme level automatic segmentation/annotation of speech signals * Android apps - applications of Estonian speech recognition for Android smart phones * Software - different software modules for building an automatic speech recognition application for Estonian The services are provided in order to demonstrate the possibilities of the speech recognition technology for Estonian and contribute to the development of real applications. Software and language resources used in our web-services have been developed within the projects funded by the National Language Technology Programs 2006-2010 and 2011-2017.