Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-By-Humming Task

Domain:

natural language processing

Record type:

paperdataset
Creator:
AmaLamTitVov
Host:avatar
Query-by-Humming (QbH) is a task that involves finding the most relevant song based on a hummed or sung fragment. Despite recent successful commercial solutions, implementing QbH systems remains challenging due to the lack of high-quality datasets for training machine learning models. In this paper, we propose a deep learning data collection technique and introduce Covers and Hummings Aligned Dataset (CHAD), a novel dataset that contains 18 hours of short music fragments, paired with time-aligned hummed versions. To expand our dataset, we employ a semi-supervised model training pipeline that leverages the QbH task as a specialized case of cover song identification (CSI) task. Starting with a model trained on the initial dataset, we iteratively collect groups of fragments of cover versions of the same song and retrain the model on the extended data. Using this pipeline, we collect over 308 hours of additional music fragments, paired with time-aligned cover versions. The final model is successfully applied to the QbH task and achieves competitive results on benchmark datasets. Our study shows that the proposed dataset and training pipeline can effectively facilitate the implementation of QbH systems.

Visit

arxiv.org

Tags

SoundMachine LearningAudio and Speech Processing

Similar

Reconstructing Human Mobility Pattern: A Semi-Supervised Approach for Cross-Dataset Transfer LearningTransfer Learning with Semi-Supervised Dataset Annotation for Birdcall ClassificationFrom speech to primate vocalizations: self-supervised deep learning as a comparative approachSupervised Contrastive Deep Learning for Individual RecognitionSemi-Supervised Learning to Perceive Children's Affective States in a Tablet Tutorlwind18/SkySat-lightweight-semi-supervised-learning

Reconstructing Human Mobility Pattern: A Semi-Supervised Approach for Cross-Dataset Transfer Learning

Understanding human mobility patterns is crucial for urban planning, transportation management, and

Transfer Learning with Semi-Supervised Dataset Annotation for Birdcall Classification

We present working notes on transfer learning with semi-supervised dataset annotation for the BirdCL

From speech to primate vocalizations: self-supervised deep learning as a comparative approach

International audience The deep learning revolution partly embodied in transformers a

Supervised Contrastive Deep Learning for Individual Recognition

Supervised Contrastive Deep Learning for Individual Recognition

Poster presented at the Deep Learning Indaba 2022 by Yusuf Brima

Semi-Supervised Learning to Perceive Children's Affective States in a Tablet Tutor

Like good human tutors, intelligent tutoring systems should detect and respond to students' affectiv

lwind18/SkySat-lightweight-semi-supervised-learning

this code is used in the paper using SkySat image to detect individual demilunes in southern Niger