Language-independent, multi-modal, and data-efficient approaches for speech synthesis and translation

期間：2021年4月 – 2024年3月
助成種目：日本学術振興会 科学研究費助成事業 基盤研究(C)
課題番号：21K11951
URL：https://kaken.nii.ac.jp/ja/grant/KAKENHI-PROJECT-21K11951

Language technology has improved due to advances in neural-network-based approaches; for example, speech synthesis has reached the quality of human speech. However, neural models require large quantities of data. Speech technologies bring social benefits of accessibility and communication – to ensure broad access to these benefits, we consider language-independent methods that can make use of less data. We propose 1) articulatory class based end-to-end speech synthesis; 2) multi-modal machine translation with text and speech; and 3) neural architecture search for data-efficient architectures.