Lyric document embeddings for music tagging

• URL: http://arxiv.org/abs/2112.11436v1
• Date: Mon, 29 Nov 2021 11:02:24 GMT
• Title: Lyric document embeddings for music tagging
• Authors: Matt McVicar, Bruno Di Giorgi, Baris Dundar, Matthias Mauch
• Abstract summary: We present an empirical study on embedding the lyrics of a song into a fixed-dimensional feature for the purpose of music tagging. Five methods of computing token-level and four methods of computing document-level representations are trained on an industrial-scale dataset of tens of millions of songs. We find that averaging word embeddings outperform more complex architectures in many downstream metrics.
• Score: 0.38233569758620045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an empirical study on embedding the lyrics of a song into a fixed-dimensional feature for the purpose of music tagging. Five methods of computing token-level and four methods of computing document-level representations are trained on an industrial-scale dataset of tens of millions of songs. We compare simple averaging of pretrained embeddings to modern recurrent and attention-based neural architectures. Evaluating on a wide range of tagging tasks such as genre classification, explicit content identification and era detection, we find that averaging word embeddings outperform more complex architectures in many downstream metrics.

Related papers

• Optical Music Recognition in Manuscripts from the Ricordi Archive [6.274767633959002]
  Ricordi archive, a prestigious collection of significant musical manuscripts from renowned opera composers such as Donizetti, Verdi and Puccini, has been digitized. We have automatically extracted samples that represent various musical elements depicted on the manuscripts, including notes, staves, clefs, erasures, and composer's annotations. We trained multiple neural network-based classifiers to differentiate between the identified music elements.
  arXiv  Detail & Related papers  (2024-08-14T09:29:11Z)
• Towards Explainable and Interpretable Musical Difficulty Estimation: A Parameter-efficient Approach [49.2787113554916]
  Estimating music piece difficulty is important for organizing educational music collections. Our work employs explainable descriptors for difficulty estimation in symbolic music representations. Our approach, evaluated in piano repertoire categorized in 9 classes, achieved 41.4% accuracy independently, with a mean squared error (MSE) of 1.7.
  arXiv  Detail & Related papers  (2024-08-01T11:23:42Z)
• Detecting Synthetic Lyrics with Few-Shot Inference [5.448536338411993]
  We have curated the first dataset of high-quality synthetic lyrics. Our best few-shot detector, based on LLM2Vec, surpasses stylistic and statistical methods. This study emphasizes the need for further research on creative content detection.
  arXiv  Detail & Related papers  (2024-06-21T15:19:21Z)
• Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings [36.090928638883454]
  Music-to-text synaesthesia aims to generate descriptive texts from music recordings with the same sentiment for further understanding. We build a computational model to generate sentences that can describe the content of the music recording. To tackle the highly non-discriminative classical music, we design a group topology-preservation loss.
  arXiv  Detail & Related papers  (2022-10-02T06:06:55Z)
• LeQua@CLEF2022: Learning to Quantify [76.22817970624875]
  LeQua 2022 is a new lab for the evaluation of methods for learning to quantify'' in textual datasets. The goal of this lab is to provide a setting for the comparative evaluation of methods for learning to quantify, both in the binary setting and in the single-label multiclass setting.
  arXiv  Detail & Related papers  (2021-11-22T14:54:20Z)
• Multi-task Learning with Metadata for Music Mood Classification [0.0]
  Mood recognition is an important problem in music informatics and has key applications in music discovery and recommendation. We propose a multi-task learning approach in which a shared model is simultaneously trained for mood and metadata prediction tasks. Applying our technique on the existing state-of-the-art convolutional neural networks for mood classification improves their performances consistently.
  arXiv  Detail & Related papers  (2021-10-10T11:36:34Z)
• Complex Network-Based Approach for Feature Extraction and Classification of Musical Genres [0.0]
  This work presents a feature extraction method for the automatic classification of musical genres. The proposed method initially converts the musics into sequences of musical notes and then maps the sequences as complex networks. Topological measurements are extracted to characterize the network topology, which composes a feature vector that applies to the classification of musical genres.
  arXiv  Detail & Related papers  (2021-10-09T22:23:33Z)
• Larger-Context Tagging: When and Why Does It Work? [55.407651696813396]
  We focus on investigating when and why the larger-context training, as a general strategy, can work. We set up a testbed based on four tagging tasks and thirteen datasets.
  arXiv  Detail & Related papers  (2021-04-09T15:35:30Z)
• Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks [61.23408995934415]
  We propose a novel framework for minimally supervised categorization by learning from the text-rich network. Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning. Our experiments show that given only three seed documents per category, our framework can achieve an accuracy of about 92%.
  arXiv  Detail & Related papers  (2021-02-23T04:14:34Z)
• dMelodies: A Music Dataset for Disentanglement Learning [70.90415511736089]
  We present a new symbolic music dataset that will help researchers demonstrate the efficacy of their algorithms on diverse domains. This will also provide a means for evaluating algorithms specifically designed for music. The dataset is large enough (approx. 1.3 million data points) to train and test deep networks for disentanglement learning.
  arXiv  Detail & Related papers  (2020-07-29T19:20:07Z)
• Deep Learning Based Text Classification: A Comprehensive Review [75.8403533775179]
  We provide a review of more than 150 deep learning based models for text classification developed in recent years. We also provide a summary of more than 40 popular datasets widely used for text classification.
  arXiv  Detail & Related papers  (2020-04-06T02:00:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.