Phonetic speech segmentation of audiobooks by using adapted LSTM-based acoustic models

Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F22%3A43966127" target="_blank" >RIV/49777513:23520/22:43966127 - isvavai.cz</a>
Výsledek na webu
<a href="https://link.springer.com/chapter/10.1007/978-3-031-22419-5_27" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-22419-5_27</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-22419-5_27" target="_blank" >10.1007/978-3-031-22419-5_27</a>

Jazyk výsledku
angličtina
Název v původním jazyce
Phonetic speech segmentation of audiobooks by using adapted LSTM-based acoustic models
Popis výsledku v původním jazyce
This paper describes experiments on phonetic speech segmentation of audiobooks by using LSTM neural networks. The segmentation procedure includes an iterative adaptation of an initial speaker-independent model. The experimental data involves 5 audiobooks recorded by various renowned Czech speakers. About 20 minutes long portions of each audiobook were precisely manually segmented by phonetic experts. We focused mainly on the optimal setting of the iterative segmentation procedure and explored the effect of the most relevant parameters on the resulting segmentation accuracy.
Název v anglickém jazyce
Phonetic speech segmentation of audiobooks by using adapted LSTM-based acoustic models
Popis výsledku anglicky
This paper describes experiments on phonetic speech segmentation of audiobooks by using LSTM neural networks. The segmentation procedure includes an iterative adaptation of an initial speaker-independent model. The experimental data involves 5 audiobooks recorded by various renowned Czech speakers. About 20 minutes long portions of each audiobook were precisely manually segmented by phonetic experts. We focused mainly on the optimal setting of the iterative segmentation procedure and explored the effect of the most relevant parameters on the resulting segmentation accuracy.

Projekt
<a href="/cs/project/GA22-27800S" target="_blank" >GA22-27800S: Využití vícemodálních Transformerů pro přirozenější hlasový dialog</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Podobné výsledky(10)