BUILDING A LVCSR SYSTEM FOR ROMANIAN: METHODS AND CHALLENGES

Autor: Paula Georgiana ZĂLHAN

Publikováno v: Journal of Public Administration, Finance and Law, Vol 5, Iss 10, Pp 181-191 (2016)

The aim of this paper is to present a brief survey in the field of Automatic Speech Recognition (ASR) and major advances made in the last decades of research in order to highlight the fundamental progress that has been made so far. After years of dev

Externí odkaz: https://doaj.org/article/bb7fff23dbe14fe0aaf5270f477504d0

Speech Recognition Lab

Autor: Cornaggia-Urrigshardt, Alessia, Gökgöz, Fahrettin, Kurth, Frank, Schmitz, Hans-Christian, Wilkinghoff, Kevin

Publikováno v: Procedia Computer Science. 205:218-228

Automatic speech recognition (ASR) in the military domain can enable voice user interfaces of command & control information systems (C2IS) and, thus, improve the usability of C2IS. It can also serve intelligence (COMINT) by supporting the monitoring

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ba85a49130c476c047516515a019b4e
https://doi.org/10.1016/j.procs.2022.09.023

Categorization of Unorganized Text Corpora for better Domain-Specific Language Modeling

Autor: Jan Stas, Daniel Zlacky, Daniel Hladek, Jozef Juhar

Publikováno v: Advances in Electrical and Electronic Engineering, Vol 11, Iss 5, Pp 398-403 (2013)

This paper describes the process of categorization of unorganized text data gathered from the Internet to the in-domain and out-of-domain data for better domain-specific language modeling and speech recognition. An algorithm for text categorization a

Externí odkaz: https://doaj.org/article/a7464cfb348f4aeeb6363a23cb58d932

Automatic Speech Recognition System Continually Improving Based on Subtitled Speech Data

Autor: Kocour, Martin

V dnešnej dobe systémy rozpoznávania reči s veľkým slovníkom dosahujú pomerne vysoké presnosti. Za ich výsledkami však často stoja desiatky ba až stovky hodín manuálne oanotovaných trénovacích dát. Takéto dáta sú často bežne n

Externí odkaz: http://www.nusl.cz/ntk/nusl-399164

ASR performance prediction on unseen broadcast programs using convolutional neurol networks

Autor: Elloumi, Zied, Besacier, Laurent, Galibert, Olivier, Kahn, Juliette, Lecouteux, Benjamin

Publikováno v: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2018, Calgary, Alberta, Canada

International audience; In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a stat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1b4c0eead8637142717c815adfc032b1
https://hal.science/hal-01709779