Abstract Automatic Speech Recognition (ASR) has become increasingly popular since it
significantly simplifies human-computer interaction, providing a more intuitive way of …

Leta 2011 je bil dokončan prvi sklop referenčnega govornega korpusa Gos. Zajetih je bilo
120 ur posnetkov govora oz. 1 mio. besed. S tem obsegom se korpus Gos uvršča na …

This paper describes selected concepts and solutions that were used to build an interface
for smart audiovisual data archive (ISADA). Automatic speech recognition (ASR) cloud …

Prispevek obravnava vprašanja, povezana z morebitno nadgradnjo referenčnega
govornega korpusa slovenščine Gos, s poudarkom na nekaterih težavnejših vprašanjih …

This paper presents a new Slovenian spoken language resource built from TEDx Talks. The
speech database contains 242 talks in total duration of 54 hours. The annotation and …

This paper introduces a new version of the Gos reference corpus of spoken Slovenian,
which was recently extended to more than double the original size (300 hours, 2.4 million …

Automatic segmentation and classification of audio streams is a challenging problem, with
many applications, such as indexing multimedia digital libraries, information retrieving, and …

V članku bomo predstavili novi slovenski govorni vir, nastal na osnovi posnetkov predavanj
TEDx. Govorna baza vsebuje posnetke 242 predavanj, v skupni dolžini 54 ur …

Automatic segmentation and classification of audio streams is a challenging problem, with
many applications, such as indexing multimedia digital libraries, information retrieving, and …

Iz govornih korpusov lahko izluščimo informacije o jeziku, ki jih iz pisnih korpusov ne
moremo dobiti. Pisni vir ne more v celoti ustrezno zastopati govorjene rabe. Iz samo 1 …