Performance and Biases of the LENA and ACLEW Algorithms in Analyzing Language Environments in Down, Fragile X, Angelman Syndromes, and Populations at Elevated Likelihood for Autism.

First, both LENA and ACLEW's automatic counts are strongly predictive of human counts, as evidenced by highly significant effects (all p < 0.001) across all three counts (CTC, AWC, and CVC).

also in 132,142 other papers

For ACLEW, the diagnostic group did not significantly improve model fit for any measure (all p > 0.05, though AWC showed a marginal trend with p = 0.073), with additional variance explained ranging from 0.2% to 0.6%.

also in 626 other papers