Commercial ASR transcribes deaf and hard-of-hearing speech with about a 77% word error rate, versus 18% for hearing speech.
Phonetically sensitive discriminants for improved speech recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.HC 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Feasibility of Using Automatic Speech Recognition with Voices of Deaf and Hard-of-Hearing Individuals
Commercial ASR transcribes deaf and hard-of-hearing speech with about a 77% word error rate, versus 18% for hearing speech.