Study on Acoustic Model Personalization in a Context of Collaborative Learning Constrained by Privacy Preservation
Study on Acoustic Model Personalization in a Context of Collaborative Learning Constrained by Privacy Preservation
Salima Mdhaffar,M. Tommasi,Y. Estève
2021 · DOI: 10.1007/978-3-030-87802-3_39
International Conference on Speech and Computer · 7 Citations
TLDR
Inspired by the federated learning paradigm, speakers that have access to a personalized database of their own speech, learn an acoustic model and collaborate with other speakers in a network to improve their model are considered.