Toward Universal Text-To-Music Retrieval
Authors:
- 4 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
This paper introduces effective design choices for text-to-music retrieval systems. An ideal text-based retrieval system would support various input queries such as pre-defined tags, unseen tags, and sentence-level descriptions. In reality, most previous works mainly focused on a single query type (tag or sentence) which may not generalize to another input type. Hence, we review recent text-based music retrieval systems using our proposed benchmark in two main aspects: input text representation and training objectives. Our findings enable a universal text-to-music retrieval system that achieves comparable retrieval performances in both tag- and sentence-level inputs. Furthermore, the proposed multimodal representation generalizes to 9 different downstream music classification tasks. We present the code and demo online. 1Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Learning Music Audio Representations Via Weak Language Supervision2022
- Semantic Tagging of Singing Voices in Popular Music RecordingsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Multi-Task Music Representation Learning from Multi-Label Embeddings2019
- Learning Deep Structure-Preserving Image-Text Embeddings2016
- Studying emotion induced by music through a crowdsourcing gameInformation Processing & Management, 2016
- Glove: Global Vectors for Word Representation2014
- Semantic Annotation and Retrieval of Music and Sound EffectsIEEE Transactions on Audio, Speech, and Language Processing, 2008
- Lyrics-Based Audio Retrieval and Multimodal Navigation in Music CollectionsLecture Notes in Computer Science, 2007