The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation

We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset consists of 1.1k human-written natural language descriptions of 706 music recordings, all publicly accessible and releas...

Full description

Saved in:
Bibliographic Details
Main Authors Manco, Ilaria, Weck, Benno, Doh, SeungHeon, Won, Minz, Zhang, Yixiao, Bogdanov, Dmitry, Wu, Yusong, Chen, Ke, Tovstogan, Philip, Benetos, Emmanouil, Quinton, Elio, Fazekas, György, Nam, Juhan
Format Journal Article
LanguageEnglish
Published 16.11.2023
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Sound
Online AccessGet full text

Cover

More Information
Summary:We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset consists of 1.1k human-written natural language descriptions of 706 music recordings, all publicly accessible and released under Creative Common licenses. To showcase the use of our dataset, we benchmark popular models on three key music-and-language tasks (music captioning, text-to-music generation and music-language retrieval). Our experiments highlight the importance of cross-dataset evaluation and offer insights into how researchers can use SDD to gain a broader understanding of model performance.
DOI:10.48550/arxiv.2311.10057