[PDF][PDF] Speech synthesis from articulatory movements recorded by real-time MRI

Y Otani, S Sawada, H Ohmura, K Katsurada - Proc. Interspeech, 2023 - isca-archive.org
Previous speech synthesis models from articulatory movements recorded using real-time
MRI (rtMRI) only predicted vocal tract shape parameters and required additional pitch …

Reconstructing speech from real-time articulatory MRI using neural vocoders

Y Yu, AH Shandiz, L Tóth - 2021 29th European Signal …, 2021 - ieeexplore.ieee.org
Several approaches exist for the recording of articulatory movements, such as
eletromagnetic and permanent magnetic articulagraphy, ultrasound tongue imaging and …

RtMRI からの調音-音響変換における転置畳み込みニューラルネットワークの利用

丹治涼, 大村英史, 澤田隼, 桂田浩一 - 電子情報通信学会論文誌 D, 2023 - search.ieice.org
本論文では rtMRI データから音響特徴量を生成するための深層学習モデルを提案する.
調音器官全体を高解像度で記録できる rtMRI は, 調音データから音響特徴量を生成するための元 …

[PDF][PDF] Towards speech-based brain-computer interfaces: finding most distinguishable word articulations with autoencoders

E Stolwijk - 2023 - studenttheses.uu.nl
People that suffer from locked-in syndrome are severely limited in their means of
communication. Recent advances in BCI technology have allowed communication by ty** …