Teaching machines to predict words in running speech
Current automatic speech recognition (ASR) technology hinges on rich acoustic representations of words and extensive training on large corpora of recorded speech to enable recognition of speech sounds in all their variance combined with probabilistic sequencing of whole words in a language model trained on large written text corpora. In contrast, building on the FlexSR recognition of phonological building-blocks, the EU-funded MorSR project will further enable systems to reject improbable words by exploiting linguistic information about word structure, such as the systematic, language-specific processes that alter the manifestations of particular speech sounds at the boundaries between words. This will improve both ASR performance and the adaptability of systems to languages where the availability of training data is reduced.
Funding SchemeERC-POC - Proof of Concept Grant
OX1 2JD Oxford
See on map