Skip to Main Content
Table 2. 
CDS F-score minus ADS F-score (in percentages) by algorithm, type of match, and whether human (H) or automatic (A) utterance boundaries were considered.
AlgoH: fullH: UMH: WMA: fullA: UMA: WMMedian
base-utt 2.9 1.4 1.5 3.3 1.8 1.9 1.85 
base-syll 1.3 −0.2 1.2 −0.2 −0.3 −0.1 
phonotactic-unsupervised −1.6 −2.5 −2.5 −1.3 −2.3 −2.4 −2.35 
phonotactic-gold 2.6 2.8 3.1 2.8 2.8 2.8 
TP-relative 0.7 0.9 0.4 0.7 0.8 
TP-average −1.6 −2.9 −2.8 −1.5 −2.9 −3.1 −2.85 
lexical-incremental 7.9 −0.6 1.6 7.1 1.2 2.3 1.95 
lexical-unigram 3.8 2.9 3.6 2.8 2.3 2.4 2.85 
lexical-multigram 3.4 1.9 0.2 3.1 −0.8 0.4 1.15 
Median 0.7 0.9 3.1 0.4 0.7 1.15 
AlgoH: fullH: UMH: WMA: fullA: UMA: WMMedian
base-utt 2.9 1.4 1.5 3.3 1.8 1.9 1.85 
base-syll 1.3 −0.2 1.2 −0.2 −0.3 −0.1 
phonotactic-unsupervised −1.6 −2.5 −2.5 −1.3 −2.3 −2.4 −2.35 
phonotactic-gold 2.6 2.8 3.1 2.8 2.8 2.8 
TP-relative 0.7 0.9 0.4 0.7 0.8 
TP-average −1.6 −2.9 −2.8 −1.5 −2.9 −3.1 −2.85 
lexical-incremental 7.9 −0.6 1.6 7.1 1.2 2.3 1.95 
lexical-unigram 3.8 2.9 3.6 2.8 2.3 2.4 2.85 
lexical-multigram 3.4 1.9 0.2 3.1 −0.8 0.4 1.15 
Median 0.7 0.9 3.1 0.4 0.7 1.15 

Note. Full means the full child-directed speech (CDS) corpus was used; UM = utterance match: CDS corpus shortened to have as many utterances as the adult-directed speech (ADS) corpus; WM = word match: idem for words.

Close Modal

or Create an Account

Close Modal
Close Modal