Hierarchical conditional end-to-end asr with ctc and multi-granular subword units

Y Higuchi, K Karube, T Ogawa… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn
representations suitable for recognizing a word-level sequence. However, the huge …

Disordered speech recognition considering low resources and abnormal articulation

Y Lin, J Dang, L Wang, S Li, C Ding - Speech Communication, 2023 - Elsevier
The success of automatic speech recognition (ASR) benefits a great number of healthy
people, but not people with disorders. The speech disordered may truly need support from …

PhISANet: Phonetically Informed Speech Animation Network

S Medina, SL Taylor, C Stoll, G Edwards… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Realistic animation is crucial for immersive and seamless human-avatar interactions as
digital avatars become more prevalent. This work presents PhISANet, an encoder-decoder …

Reconnaissance automatique de la parole d'enfants apprenant· e· s lecteur· ice· s en salle de classe: modélisation acoustique de phonèmes

L Gelin - 2022 - theses.hal.science
À travers ces travaux de thèse, nous cherchons à perfectionner les transcriptions
phonétiques de lectures orales d'enfants apprenant· e· s lecteur· rice· s réalisées en …