Acoustic Classification of Focus: On the Web and in the Lab
Howell, Jonathan; Rooth, Mats; Wagner, Michael
We present a new methodological approach which combines both naturally-occurring speech “harvested” on the web and speech data elicited in the laboratory. This proof-of-concept study examines the phenomenon of focus sensitivity, in which the interpretation of particular grammatical constructions (e.g. the English comparative) is sensitive to the location of prosodic prominence. Machine learning algorithms (support vector machines and linear discriminant analysis) and human perception experiments are used to cross-validate the web-harvested and lab-elicited speech. Results confirm the theoretical predictions for location of prominence in comparative clauses and the advantages using both web-harvested and lab-elicited speech. The most robust acoustic classifiers include paradigmatic (i.e. un-normalized), non-intonational acoustic measures (duration and relative formant frequencies from single segments). These acoustic cues are also significant predictors of human listeners’ classification, offering new evidence in the decades-old debate surrounding the role of syntagmatic (i.e. utterance-normalized) and intonational acoustic cues of semantic focus.
This research was supported by the following grants: NSF 1035151 RAPID: Harvesting Speech Datasets for Linguistic Research on the Web (Digging into Data Challenge), SSHRC Digging into Data Challenge Grant 869-2009-0004, the SSHRC CRC program and SSHRC 410-2011-1062 Relative prosodic boundary strength and its role in encoding syntactic structure.
Linguistics; Phonetics; Phonology; Semantics; Prosody