# Semi-Supervised Music Tagging Transformer

arXiv: https://arxiv.org/abs/2111.13457 · HTML: https://mlsanity.com/paper/2111.13457/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2021.

## Built on by (most cited first, 25 of 25)

- [MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response](https://mlsanity.com/paper/2309.08730/) (2023)
- [Supervised and Unsupervised Learning of Audio Representations for Music Understanding](https://mlsanity.com/paper/2210.03799/) (2022)
- [Contrastive Audio-Language Learning for Music](https://mlsanity.com/paper/2208.12208/) (2022)
- [Video Background Music Generation: Dataset, Method and Evaluation](https://mlsanity.com/paper/2211.11248/) (2022)
- [MuseChat: A Conversational Music Recommendation System for Videos](https://mlsanity.com/paper/2310.06282/) (2023)
- [Language-Guided Music Recommendation for Video via Prompt Analogies](https://mlsanity.com/paper/2306.09327/) (2023)
- [VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos](https://mlsanity.com/paper/2409.07450/) (2024)
- [Multitrack Music Transcription with a Time-Frequency Perceiver](https://mlsanity.com/paper/2306.10785/) (2023)
- [The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling](https://mlsanity.com/paper/2209.14458/) (2022)
- [Jointist: Joint Learning for Multi-instrument Transcription and Its Applications](https://mlsanity.com/paper/2206.10805/) (2022)
- [Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representation](https://mlsanity.com/paper/2207.04471/) (2022)
- [Joint Music and Language Attention Models for Zero-shot Music Tagging](https://mlsanity.com/paper/2310.10159/) (2023)
- [Semi-supervised music emotion recognition using noisy student training and harmonic pitch class profiles](https://mlsanity.com/paper/2112.00702/) (2021)
- [Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training](https://mlsanity.com/paper/2302.00286/) (2023)
- [WikiMuTe: A web-sourced dataset of semantic descriptions for music audio](https://mlsanity.com/paper/2312.09207/) (2023)
- [Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning](https://mlsanity.com/paper/2409.11498/) (2024)
- [Scaling Up Music Information Retrieval Training with Semi-Supervised Learning](https://mlsanity.com/paper/2310.01353/) (2023)
- [MDSC: Towards Evaluating the Style Consistency Between Music and Dance](https://mlsanity.com/paper/2309.01340/) (2023)
- [Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training](https://mlsanity.com/paper/2401.15323/) (2024)
- [Towards Training Music Taggers on Synthetic Data](https://mlsanity.com/paper/2407.02156/) (2024)
- [CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining](https://mlsanity.com/paper/2503.23128/) (2025)
- [Spectrograms Are Sequences of Patches](https://mlsanity.com/paper/2210.15988/) (2022)
- [Self-supervised Auxiliary Loss for Metric Learning in Music Similarity-based Retrieval and Auto-tagging](https://mlsanity.com/paper/2304.07449/) (2023)
- [Constructing Composite Features for Interpretable Music-Tagging](https://mlsanity.com/paper/2603.28644/) (2026)
- [Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation](https://mlsanity.com/paper/2606.24307/) (2026)

## Abstract (arXiv)

We present Music Tagging Transformer that is trained with a semi-supervised approach. The proposed model captures local acoustic characteristics in shallow convolutional layers, then temporally summarizes the sequence of the extracted features using stacked self-attention layers. Through a careful model assessment, we first show that the proposed architecture outperforms the previous state-of-the-art music tagging models that are based on convolutional neural networks under a supervised scheme. The Music Tagging Transformer is further improved by noisy student training, a semi-supervised approach that leverages both labeled and unlabeled data combined with data augmentation. To our best knowledge, this is the first attempt to utilize the entire audio of the million song dataset.