Due to the profound differences between acoustic characteristics of neutral and whispered
speech, the performance of traditional automatic speech recognition (ASR) systems trained …

The acoustic-phonetic properties of speech sounds vary substantially across languages,
and across talkers within a single language. The central thesis of this dissertation is that …

Arabic automatic speech recognition is one of the difficult topics of current speech
recognition research field. Its difficulty lies on rarity of researches related to Arabic speech …

Nedavno postignuti uspesi dubinskih neuralnih mreža u različitim zadacima mašinskog
učenja su doprineli da vestačke neuralne mreze ponovo zauzmu bitnu ulogu u …

Abstract Automatic Speech Recognition (ASR) is widely used in many applications and
tools. Smartphones, video games, cars. etc., are a few example where people use ASR …

Avec la disponibilité grandissante des capteurs et des réseaux de capteurs à coûts réduits,
la reconnaissance d'activités humaines, grâce à des vêtements intelligents, fait l'objet de …

Generally, the user group of a language is remarkably diverse in terms of speaker-specific
characteristics such as dialect and speaking style. Hence, quality of spoken content varies …