Kc. Hustad et al., DECTALK AND MACINTALK SPEECH SYNTHESIZERS - INTELLIGIBILITY DIFFERENCES FOR 3 LISTENER GROUPS, Journal of speech language and hearing research, 41(4), 1998, pp. 744-752
This study examined word level intelligibility differences between DEC
Talk and MacinTalk speech synthesizers using the Modified Rhyme Test i
n an open format transcription task. Three groups of listeners partici
pated: inexperienced, speech-language pathologists, and speech synthes
is experts. Results for between-subjects ANOVA showed that he expert g
roup correctly identified a significantly higher number of words than
each of the other listener groups. For the within-subjects factor of v
oice, simple effects ANOVA and post hoc contrasts within each group sh
owed that listeners had higher intelligibility scores for the DECTalk
male voice, Perfect Paul, than for the MacinTalk male voice, Bruce. No
other pairwise gender/age-matched differences were found between the
two synthesizers.