[ad_1]
Client speech recognition programs don’t work as effectively for many individuals with speech variations, resembling stuttering, relative to the remainder of the overall inhabitants. Nevertheless, what isn’t clear is the diploma to which these programs don’t work, how they are often improved, or how a lot folks need to use them. On this paper, we first handle these questions utilizing outcomes from a 61-person survey from individuals who stutter and discover members need to use speech recognition however are often lower off, misunderstood, or speech predictions don’t signify intent. In a second examine, the place 91 individuals who stutter recorded voice assistant instructions and dictation, we quantify how dysfluencies impede efficiency in a consumer-grade speech recognition system. By way of three technical investigations, we reveal what number of frequent errors might be prevented, leading to a system that cuts utterances off 79.1% much less typically and improves phrase error fee from 25.4% to 9.9%.
Support authors and subscribe to content
This is premium stuff. Subscribe to read the entire article.
