POMET for the meter estimation task

The availability of appropriate research corpora is a fundamental concern in music information retrieval (MIR) research. Design, development, and evaluation of a poetic corpus, POMET for the meter estimation task is addressed in this paper. Poems, which communicate through rhythm and apparent meaning, have a vital role in many literary traditions. Metrical rhythm generally involves periodic arrangements of sequences of stressed and unstressed syllables in each line of poems. The aesthetic and emotional perception of poetry can be studied well using poetic meter analysis. A corpus with eight meters is designed and recorded in a studio environment for Malayalam, one of the prominent languages in South India. A pilot evaluation is performed with musical texture features (MTF) and spectrograms using deep neural-network architectures. We hope that the corpus can be used as a benchmark dataset for poetic meter estimation, rhythmic analysis, and corpus-based prosody analysis