Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

Song Describer Dataset Dataset | Papersgraph

Datasets/

TextsAudioMusic

Song Describer Dataset

Introduced in The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation2023

About this Dataset

The Song Describer Dataset (SDD) contains ~1.1k captions for 706 permissively licensed music recordings. It is designed for use in evaluation of models that address music-and-language (M&L) tasks such as music captioning, text-to-music generation and music-language retrieval.

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

Dataset Variants

Song Describer Dataset

Papers1

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

This work introduces the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models, and benchmark popular models on three key music- and-language tasks.

Tasks

EDIT

Cross-Modal Retrieval Text-to-Music Generation Music Generation Music Captioning

Similar Datasets