Speech-in-speech recognition in preschoolers

Objective The purpose of this study was to 1) characterise word recognition in a speech masker for preschoolers tested using closed-set, forced-choice procedures and 2) better understand the stimulus and listener factors affecting performance. Design Speech recognition thresholds (SRTs) in a two-talker masker were evaluated using a picture-pointing response with two sets of disyllabic target words. ChEgSS words were previously developed for children >= 5 years of age, and simple words were developed for preschoolers. Familiarisation ensured accurate identification of target words before testing. Study sample Participants were 3- and 4-year olds (n = 21) and young adults (n = 10) with normal hearing. Results Preschoolers and adults had significantly lower SRTs for the simple words than the ChEgSS words, and lower SRTs for early-acquired than later-acquired ChEgSS words. For both word sets, SRTs were approximately 11-dB higher for preschoolers than adults, and child age was associated with SRTs. Preschoolers' receptive vocabulary size predicted performance for ChEgSS words but not simple words. Conclusions Preschoolers were more susceptible to speech-in-speech masking than adults, with a similar child-adult difference for the ChEgSS and simple words. Effects of receptive vocabulary in preschoolers' recognition of ChEgSS words indicate that vocabulary size is an important consideration, even when using closed-set methods.