Finding schwa: Comparing the results of an automatic aligner with human judgments when identifying schwa in a corpus of spoken French

Abstract

This paper compares the results of an automatic aligner with human judgments when identifying schwa in a natural language corpus of spoken French. All word-final, postconsonantal possible schwa insertion sites in the standardized text portion of investigations conducted in both Qu'ebec and France were both hand coded for schwa and time aligned at the word and phone level by the Penn Phonetics Lab Forced Aligner, modified for use with French. The results of the two methods of coding were statistically compared to determine their level of agreement. Preliminary results show a strong correlation between the two methods. Possible effects due to dialect or phonetic context were investigated using a two-way, between subjects analysis of variance. A mixed design analysis of variance was also conducted. Initial results have found no significant effect due to dialect, but a possible effect due to context. This suggests that the results of automatic alignment are comparable with human judgments in both dialects of French, but results may differ for individual speakers in specific contexts. The advantages of using an automatic aligner that can aid in the collection of larger volumes of natural language data than is possible when working manually is discussed.