Algorithmic composition methods must prove themselves within real-world musical contexts to moreudfirmly solidify their adoption in musical practice. The present project is an automatic composing program trainedudon a corpus of songs from musical theater to create novel material, directly generating a scored lead sheet of vocaludmelody and chords. The program can also produce output based upon phonetic analysis of user-provided lyrics. Theudchance to undertake the research arose from a television documentary funded by Sky Arts that considered the questionudof whether current-generation, computationally creative methods could devise a new work of musical theater (theudresearch described here provides but one strand within that project). Allied with the documentary, the resultantudmusical had a two-week West End run in London and was itself broadcast in full. Evaluation of the project includedudboth design feedback from a musical theater composer team, and critical feedback from audiences and media coverage.udThe research challenges of the real-world context are discussed, with respect to the compromises necessary to get suchuda project to the stage.
展开▼