Speech technologies and Russian pronunciation variation in the context of VoiceInteraction
DOI:
https://doi.org/10.26334/2183-9077/rapln10ano2023a8Keywords:
automatic speech recognition, phonetics, Russian language, filled pauses, varietiesAbstract
This article aims to describe the work conducted at VoiceInteraction, a company specialized in speech processing solutions, with a particular focus on automatic transcription using a Hybrid Automatic Speech Recognizer (ASR). The primary objective revolved around studying the phonetic characteristics of the Russian language, encompassing four main tasks: describing the phonetic-phonological inventory, validating news transcriptions, validating a previously created lexicon, and integrating filled pauses into the ASR. This work contributed to the Artificial Intelligence and Advanced Data Analysis for Authority Agencies (AIDA) project, funded by the European Commission under the Horizon 2020 program, by transcribing the data in the Russian language.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Anna Havras, Carlos Mendes, Gueorgui Hristovsky, Sérgio Paulo, Helena Moniz

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors retain copyright and concede to the journal the right of first publication. The articles are simultaneously licensed under the Creative Commons Attribution License, which allows sharing of the work with an acknowledgement of authorship and initial publication in this journal.
The authors have permission to make the version of the text published in RAPL available in institutional repositories or other platforms for the distribution of academic papers (e.g., ResearchGate).