A Review of AlfaNum Speech Technologies for Serbian , Croatian and Macedonian

This paper gives a brief review of the development of systems for automatic speech recognition and text-to-speech synthesis in Serbian, Croatian and Macedonian language, at the Faculty of Engineering, University of Novi Sad, Serbia. The systems developed within this project enable two-way communication between humans and machines. These systems are predecessors to many commercial services such as voice portals and interactive voice response systems. Some original features of these systems, related to certain particularities of south-Slavic languages, will be illustrated as well. Available APIs and interfaces designed for using these software components in custom applications will also be described. Pregled govornih tehnologij za srbščino, hrvaščino in makedonščino skupine AlfaNum Članek poda kratek pregled razvoja sistemov samodejnega razpoznavanja govora in samodejnega tvorjenja govora iz besedil za srbski, hrvaški in makedonski jezik na Fakulteti za inženiring Univerze v Novem Sadu. Sistemi, ki so bili razvit pri tem projektu, omogočajo dvosmerno komunikacijo med človekom in računalnikom. Tovrstni sistemi so predhodniki mnogih komercialnih storitev, kot so glasovni portali in interaktivni govorni odzivniki. Ponazorjene bodo tudi nekatere izvirne značilnosti sistemov, ki so povezane s posebnostmi južnoslovanskih jezikov. Ob tem bodo opisani tudi razpoložljivi programski vmesniki (API) in vmesniki, ki smo jih razvili za uporabo programskih komponent pri uporabniških aplikacijah.