Deaf-Accented Speech

Speech produced by Deaf or Hard of Hearing people whose articulation, prosody, and voicing patterns differ from typical hearing speakers because the speaker has limited or no auditory feedback for their own voice. Deaf-accented speech is intelligible to familiar listeners but is often misrecognised by mainstream Automatic Speech Recognition systems, which are trained predominantly on hearing voices. Recognition accuracy varies widely across individuals and depends on factors such as age of hearing loss onset, degree of hearing loss, and use of hearing aids or cochlear implants. Robust native recognition of deaf-accented speech is a key accessibility requirement for voice assistants, smart-home devices, and dictation systems.