# SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

arXiv: https://arxiv.org/abs/2506.12222 · HTML: https://mlsanity.com/paper/2506.12222/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 32)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [SSAST: Self-Supervised Audio Spectrogram Transformer](https://mlsanity.com/paper/2110.09784/) (2021)
- [Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language](https://mlsanity.com/paper/2212.07525/) (2022)
- [BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation](https://mlsanity.com/paper/2103.06695/) (2021)
- [MAE-AST: Masked Autoencoding Audio Spectrogram Transformer](https://mlsanity.com/paper/2203.16691/) (2022)
- [X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning](https://mlsanity.com/paper/2311.18799/) (2023)
- [ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst](https://mlsanity.com/paper/2305.16103/) (2023)
- [A-JEPA: Joint-Embedding Predictive Architecture Can Listen](https://mlsanity.com/paper/2311.15830/) (2023)
- [EAT: Self-Supervised Pre-Training with Efficient Audio Transformer](https://mlsanity.com/paper/2401.03497/) (2024)
- [Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation](https://mlsanity.com/paper/2204.12260/) (2022)
- [Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training](https://mlsanity.com/paper/2204.12768/) (2022)
- [Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics](https://mlsanity.com/paper/2307.16620/) (2023)
- [Can CLIP Help Sound Source Localization?](https://mlsanity.com/paper/2311.04066/) (2023)
- [ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification](https://mlsanity.com/paper/2211.13189/) (2022)
- [CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding](https://mlsanity.com/paper/2309.00454/) (2023)

## Built on by (most cited first, 16 of 16)

- [USAD: Universal Speech and Audio Representation via Distillation](https://mlsanity.com/paper/2506.18843/) (2025)
- [Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification](https://mlsanity.com/paper/2509.24901/) (2025)
- [MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning](https://mlsanity.com/paper/2606.25225/) (2026)
- [DroneAudioset: An Audio Dataset for Drone-based Search and Rescue](https://mlsanity.com/paper/2510.15383/) (2025)
- [ALARM: Audio-Language Alignment for Reasoning Models](https://mlsanity.com/paper/2603.09556/) (2026)
- [AudioMosaic: Contrastive Masked Audio Representation Learning](https://mlsanity.com/paper/2605.14231/) (2026)
- [USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding](https://mlsanity.com/paper/2606.06444/) (2026)
- [Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification](https://mlsanity.com/paper/2608.02397/) (2026)
- [Improving Audio Event Recognition with Consistency Regularization](https://mlsanity.com/paper/2509.10391/) (2025)
- [AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers](https://mlsanity.com/paper/2512.03637/) (2025)
- [BAT: Better Audio Transformer Guided by Convex Gated Probing](https://mlsanity.com/paper/2602.16305/) (2026)
- [Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection](https://mlsanity.com/paper/2603.13749/) (2026)
- [CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks](https://mlsanity.com/paper/2604.03314/) (2026)
- [Sparse Prototype Code Underlies Classification and Prediction Across Modalities](https://mlsanity.com/paper/2608.15632/) (2026)
- [Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners](https://mlsanity.com/paper/2608.19863/) (2026)
- [Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models](https://mlsanity.com/paper/2609.18041/) (2026)

## Abstract (arXiv)

Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL pre-training has sufficiently equipped them to handle real-world audio. However, a critical question remains: how well do these models actually perform in real-world conditions, where audio is typically polyphonic and complex, involving multiple overlapping sound sources? Current audio SSL methods are often benchmarked on datasets predominantly featuring monophonic audio, such as environmental sounds, and speech. As a result, the ability of SSL models to generalize to polyphonic audio, a common characteristic in natural scenarios, remains underexplored. This limitation raises concerns about the practical robustness of SSL models in more realistic audio settings. To address this gap, we introduce Self-Supervised Learning from Audio Mixtures (SSLAM), a novel direction in audio SSL research, designed to improve, designed to improve the model's ability to learn from polyphonic data while maintaining strong performance on monophonic data. We thoroughly evaluate SSLAM on standard audio SSL benchmark datasets which are predominantly monophonic and conduct a comprehensive comparative analysis against SOTA methods using a range of high-quality, publicly available polyphonic datasets. SSLAM not only improves model performance on polyphonic audio, but also maintains or exceeds performance on standard audio SSL benchmarks. Notably, it achieves up to a 3.9% improvement on the AudioSet-2M (AS-2M), reaching a mean average precision (mAP) of 50.2. For polyphonic datasets, SSLAM sets new SOTA in both linear evaluation and fine-tuning regimes with performance improvements of up to 9.1% (mAP).