RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information
In this article, we introduce an extended, freely available resource for the Romanian
language, named RoLEX. The dataset was developed mainly for speech processing …
language, named RoLEX. The dataset was developed mainly for speech processing …
[PDF][PDF] Investigation of Romanian speech recognition improvement by incorporating Italian speech data
CL Gasan, V PĂIȘ - LINGUISTIC RESOURCES AND …, 2023 - conferences.info.uaic.ro
This study investigates the potential for augmenting Romanian automatic speech
recognition (ASR) systems by incorporating Italian speech data, leveraging the phonetic …
recognition (ASR) systems by incorporating Italian speech data, leveraging the phonetic …
Establishing a baseline of Romanian speech-to-text models
D Ungureanu, M Badeanu, GC Marica… - 2021 International …, 2021 - ieeexplore.ieee.org
With the increasing usage of Natural Language Processing to facilitate the interactions
between humans and machines, automatic speech recognition systems have become …
between humans and machines, automatic speech recognition systems have become …
An analysis on the effects of speaker embedding choice in non auto-regressive TTS
A Stan, J O'Mahony - arXiv preprint arXiv:2307.09898, 2023 - arxiv.org
In this paper we introduce a first attempt on understanding how a non-autoregressive
factorised multi-speaker speech synthesis architecture exploits the information present in …
factorised multi-speaker speech synthesis architecture exploits the information present in …
[PDF][PDF] Machine Learning based Solutions for Text Processing and Speech Synthesis
N Maria - 2024 - ebooks.unitbv.ro
Machine Learning based Solutions for Text Processing and Speech Synthesis Page 1 Maria
NUȚU Machine Learning based Solutions for Text Processing and Speech Synthesis 2024 …
NUȚU Machine Learning based Solutions for Text Processing and Speech Synthesis 2024 …