TY - JOUR

T1 - Assessing the accuracy of existing forced alignment software on varieties of British English

AU - MacKenzie, Laurel

AU - Turton, Danielle

PY - 2020/1/29

Y1 - 2020/1/29

N2 - This paper presents an analysis of the performance and usability of automatic speech processing tools on six different varieties of English spoken in the British Isles. The tools used in the present study were developed for use with Mainstream American English, but we demonstrate that their forced alignment func- tionality nonetheless performs extremely well on a range of British varieties, encompassing both careful and casual speech. Where phone boundary placement is concerned, substantial errors in alignment occur infre- quently, and although small displacements between aligner-placed and human-placed phone boundaries are found regularly, these will rarely have a significant effect on measurements of interest for the researcher. We demonstrate that gross phone boundary placement errors, when they do arise, are particularly likely to be introduced in fast speech or with varieties that are radically different from Mainstream American English (e.g. Scots). We also observe occasional problems with phonetic transcription. Overall, we advise that, although forced alignment software is highly reliable and improving continuously, human confirmation is needed to correct errors which can displace entire stretches of speech. Nevertheless, sociolinguists can be assured that the output of these tools is generally highly accurate for a wide range of varieties.

AB - This paper presents an analysis of the performance and usability of automatic speech processing tools on six different varieties of English spoken in the British Isles. The tools used in the present study were developed for use with Mainstream American English, but we demonstrate that their forced alignment func- tionality nonetheless performs extremely well on a range of British varieties, encompassing both careful and casual speech. Where phone boundary placement is concerned, substantial errors in alignment occur infre- quently, and although small displacements between aligner-placed and human-placed phone boundaries are found regularly, these will rarely have a significant effect on measurements of interest for the researcher. We demonstrate that gross phone boundary placement errors, when they do arise, are particularly likely to be introduced in fast speech or with varieties that are radically different from Mainstream American English (e.g. Scots). We also observe occasional problems with phonetic transcription. Overall, we advise that, although forced alignment software is highly reliable and improving continuously, human confirmation is needed to correct errors which can displace entire stretches of speech. Nevertheless, sociolinguists can be assured that the output of these tools is generally highly accurate for a wide range of varieties.

KW - sociophonetics

U2 - 10.1515/lingvan-2018-0061

DO - 10.1515/lingvan-2018-0061

M3 - Journal article

VL - 6

JO - Linguistics Vanguard

JF - Linguistics Vanguard

SN - 2199-174X

IS - s1

M1 - 20180061

ER -