Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics

Abstract

Song translation requires both translation of lyrics and alignment of music notes so that the resulting verse can be sung to the accompanying melody, which is a challenging problem that has attracted some interests in different aspects of the translation process. In this paper, we propose Lyrics-Melody Translation with Adaptive Grouping (LTAG), a holistic solution to automatic song translation by jointly modeling lyrics translation and lyrics-melody alignment. It is a novel encoder-decoder framework that can simultaneously translate the source lyrics and determine the number of aligned notes at each decoding step through an adaptive note grouping module. To address data scarcity, we commissioned a small amount of training data annotated specifically for this task and used large amounts of augmented data through back-translation. Experiments conducted on an English-Chinese song translation data set show the effectiveness of our model in both automatic and human evaluations. 1

Perceived Carrer Barriers and Suicidal Ideation among Adolescent School Dropouts

“…Hence, systematic analysis of singable lyric translation has primarily relied on individual case studies [6], [7], [10], [11]. Moreover, while automatic lyric translation has gained popularity, the development of neural lyric translation models has been largely dependent on semi-supervised methods [12], [13] or privately sourced datasets [14].…”