Modrzejewski, MateuszRokita, Przemysław2023-09-222023-09-222023Modrzejewski M., Rokita P., Text-to-music Models and Their Evaluation Methods. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 213-218, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.34.978-83-66741-92-8http://hdl.handle.net/11652/4810https://doi.org/10.34658/9788366741928.34Text-to-music models are a very recent approach to generative music, allowing to generate music based on an abstract, rich description input in natural language. In this paper, we propose guidelines for evaluation in text-to-music models, highlighting the need for musical insight and clear descriptions of perceptual quality upon investigating the metrics of currently developed approaches. We also present a critical analysis of the capabilities and evaluation methods of the pioneering text-to-music models.enDla wszystkich w zakresie dozwolonego użytkuFair use conditiongenerative musicmusic information retrievaltext-to-musicdeep learningdiffusion modelsmuzyka generatywnawyszukiwanie informacji muzycznychzamiana tekstu na muzykęgłębokie uczenie sięmodele dyfuzjiRozdział - monografiaLicencja PŁLUT License10.34658/9788366741928.34