Holy smoke: vocalic precursors of phrase breaks in Milton's Paradise Lost

Non-traditional prosodic features for automated phrase break prediction

“…Finally, we test the correlation between preboundary lexical items bearing complex vowels and gold-standard phrase break annotations on different kinds of speech via the chi-squared statistic, to determine whether the perceived association is statistically significant or not. Our findings indicate that this correlation is extremely statistically significant: it is present in contemporary, formal, British English speech (Brierley and Atwell, 2009) and seventeenth century English verse (Brierley and Atwell, 2010a); and it holds for spontaneous as well as read speech, and for multiple speakers (Brierley and Atwell, 2010b). We hypothesise that while complex vowels seem to constitute phrase break signifiers in English, this may translate to a subset of the vowel system in other languages.…”

Exploring complex vowels as phrase break correlates in a corpus of English speech with proPOSEL, a prosody and POS English lexicon

“…There is consensus in the ASR community that pauses affect vowel durations in adjacent words. Based on intuitions from poetry and concurrent work [18], have redefined this causal relationship and interpreted complex vowels as phrase break signifiers. From significance tests on a sample of contemporary British English speech from the Aix-MARSEC Corpus, plus seventeenth century English verse (ibid.…”

“…The intuition that the presence of complex vowels in (content) words increases the likelihood of their being classified as breaks comes from poetry [18], where diphthongs and triphthongs seem to be associated with rhythmic junctures. This happens within lines and across lines as in Blake's The Tyger (circa 1794):…”

“…The SAMP-PA transcriptions from the syllables tier were not used in our study because we are interested in predictive features derived from speaker-independent and domain-independent citation forms in ProPOSEL which can be superimposed on any unseen English text -for example, seventeenth century English verse cf. [18].…”