We present a large-vocabulary automatic speech-recognition system that is being developed for the Slovenian language. The concept of a single-pass token-passing algorithm for the fast speech decoding that can be used with the designed multi-level system structure is discussed. From the algorithmic point of view, the main component of the system is a finite-state pronunciation lexicon model. We developed a sequential minimization algorithm that very efficiently reduces the size (up to 60%) and algorithmic complexity of the lexicon model.
B.03 Paper at an international scientific conferenceCOBISS.SI-ID: 7264340
A novel method for robust and accurate detection of acoustic change points in continuous audio streams was presented. The proposed segmentation procedure aimed to estimate decision-thresholds directly from the currently processed audio data and thus reduces a need for additional threshold tuning from development data. It employed change-detection methods from two well-established audio segmentation approaches based on the Bayesian Information Criterion. Combining methods from both approaches enabled us to adaptively tune boundary-detection thresholds from the underlying processing data.
B.03 Paper at an international scientific conferenceCOBISS.SI-ID: 7258196
A novel 3D triangulation-based imaging method and device is proposed, which has the following the following advantages over known state-of-the-art methods: low energy consumption, enables uninterrupted usage of several devices in the same room, is robust to illumination changes and disturbancies.
F.32 International patentCOBISS.SI-ID: 7107412