Automatic Speech Recognition (ASR) is an active field of research due to its large number applications and the proliferation interfaces or computing devices that can support speech processing. However, bulk are based on well-resourced languages overshadow under-resourced ones. Yet, ASR represents undeniable means promote such languages, especially when designing human-to-human human-to-machine ...

This study focuses on the analysis of the Lombard effect in visual and audiovisual speech recognition. Previous studies have shown that the performance of an audio-only automatic speech recognizer decreases in noisy environments because of the Lombard reflex. A few studies have considered the visual changes due to the Lombard reflex, but the role of the Lombard reflex in automatic visual speech...

The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or which the phone inventories remain unknown. Past works explored multilingual training, transfer learning, as well zero-shot learning in order to build ASR systems these low-resource languages. While it h...