Automatic Speech Recognition (ASR) for Communications with Seniors and Non-Hearing Users at Public Spaces: Speech-To-Text Technology for Live Subtitling and Accessibility

Considered the increasing ageing and multilingualism of population in public space across Italy and Europe, the application of AI Technologies in multilingual communications and for the purposes of accessibility has become an important challenge in the production of translation and interpreting services. In particular, the widespread usage of Automatic Speech Recognition (ASR) and Automatic Speech Translation (AST) technology represents a significant, recent development in the attempt of satisfying the increasing demand for interinstitutional, multilingual communications at inter- governmental level. The application of ASR technology, combined with Neural Machine Translation (NMT), may allow for the breaking down of communication barriers between single speakers or among more individuals at European public conferences or public spaces. ASR technology can also facilitate the communication with older people and non- hearing users. Thanks to Speech to Text technology, it is possible to guarantee content accessibility for non- hearing audience via subtitles. Hence the need for analyzing and evaluating ASR output emerges: a quantitative approach will be adopted with the objective of assessing its accuracy. A small corpus of F.A.O.’s English- language speeches and conferences on the impact of Climate Change on the Agricultural Production is taken into consideration, which is then analyzed by applying a statistical approach based on NER model. Only three typologies of SR errors will be identified and evaluated and all errors will be statistically quantified by using an adapted version of the NER model on the basis of two different variables: Native and Non- Native Speakers. Subtitles have been compared to a gold standard corpus. The study is intended to demonstrate that ASR technology can be a valuable instrument to cope with the issues of communications with seniors and non- hearing persons in public European institutions and spaces where aging and multilingualism are posing new challenges.