[PDF][PDF] Speech synthesis from intracranial stereotactic Electroencephalography using a neural vocoder.

FV Arthur, TG Csapó - Infocommunications Journal, 2024‏ - infocommunications.hu
Speech is one of the most important human biosig-nals. However, only some speech
production characteristics are fully understood, which are required for a successful …

[HTML][HTML] A Smart Control System for the Oil Industry Using Text-to-Speech Synthesis Based on IIoT

AR Mandeel, AA Aggar, MS Al-Radhi, TG Csapó - Electronics, 2023‏ - mdpi.com
Oil refineries have high operating expenses and are often exposed to increased asset
integrity risks and functional failure. Real-time monitoring of their operations has always …

Modeling Irregular Voice in End-to-End Speech Synthesis via Speaker Adaptation

AR Mandeel, MS Al-Radhi… - … Conference on Speech …, 2023‏ - ieeexplore.ieee.org
End-to-end text-to-speech (TTS) synthesizers may not create a speech similar to the target
speaker when the adaptation data is limited or/and chosen randomly. Creaky voice might …

Effects of Training Strategies and the Amount of Speech Data on the Quality of Speech Synthesis

L Vladař, J Matoušek - International Conference on Text, Speech, and …, 2024‏ - Springer
During the development of a speech synthesizer, we often face a lack of training data. This
paper describes how the amount of data used to train a speech synthesizer affects the …

Enhancing End-to-End Speech Synthesis by Modeling Interrogative Sentences with Speaker Adaptation

AR Mandeel, MS Al-Radhi… - … Conference on Speech …, 2023‏ - ieeexplore.ieee.org
Despite end-to-end text-to-speech (TTS) synthesizers producing human-like speech, they
might still need more intuitive user control over prosody. Modeling interrogative sentence …

[PDF][PDF] Is Dynamic Time War** of speech signals suitable for articulatory signal comparison using ultrasound tongue images?

TG Csapó - 2023‏ - smartlab.tmit.bme.hu
In speech technology, the examination of speaker dependency is vital–that is, whether
methods developed for one speaker can be adapted to another speaker or not. In the case …

[PDF][PDF] Leveraging Knowledge Distillation to Train a Compact Tacotron2 Student Model

T Prabhakara‏ - researchgate.net
Achieving natural and intelligible Text-to-Speech (TTS) synthesis requires training
objectives that align well with the model's output space and are amenable to stable, end-to …