Rhythmicalizer. A digital tool to identify free verse prosody

At least 80% of modern and postmodern poems have neither rhyme nor metrical schemes like iamb or trochee. But does this mean that they are free of any rhythmical features? The US american research on free verse prosody claims the opposite: Modern poets like Whitman, the Imagists, the Beat Poets as well as contemporary Slam Poets developed a postmetrical idea of prosody, using rhythmical features of everyday language, prose, and musical styles like Jazz or Hip Hop. Our project will prove this theory by using digital pattern recognition techniques. For this purpose we examine, lyrikline, the biggest online portal for spoken poetry. Following the vastly improved prosody detection in current speech processing, we will use methods like phrase break prediction, prosodic phrasing, spoken document analysis or fluency/disfluency modelling to identify rhythmical features. First the philological subproject will define specific rhythmical patterns by aligning the textual line arrangement and the prosodic phrasing in the Poet’s voice. Than the digital subproject will develop an automatic pattern recognition based on machine learning techniques.

Our aim is to develop a method and a tool for prosody detection and formal corpus analysis, focused on modern free verse poetry. In traditional poetry, metrical patterns like Pentameter or Hexameter are used to identify poetic forms like the elegiac couplet or influences like those of Greek Poetry on German Writers of the 18th century. Our rhythmical patterns will help to identify poetic forms in free verse prosody and to detect influence like those of American free verse poetry on modern and postmodern German Writers. In the long run, our tool will be hosted on the German website lyrikline to be usable for university teaching and research.

Funding Period: 2017-2019

Funded by the Volkswagenstiftung in the programmee „Mixed Methods in the humanities“

See also: www.rhythmicalizer.net