# Shared Representation Learning for Reference-Guided Targeted Sound Detection

arXiv: https://arxiv.org/abs/2603.17025 · HTML: https://mlsanity.com/paper/2603.17025/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Audio Retrieval with Natural Language Queries](https://mlsanity.com/paper/2105.02192/) (2021)
- [Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization](https://mlsanity.com/paper/1912.04761/) (2019)
- [Weakly Labelled AudioSet Tagging with Attention Neural Networks](https://mlsanity.com/paper/1903.00765/) (2019)
- [Adapting a ConvNeXt model to audio classification on AudioSet](https://mlsanity.com/paper/2306.00830/) (2023)
- [Towards duration robust weakly supervised sound event detection](https://mlsanity.com/paper/2101.07687/) (2021)
- [Improving Target Sound Extraction with Timestamp Information](https://mlsanity.com/paper/2204.00821/) (2022)
- [FlowTSE: Target Speaker Extraction with Flow Matching](https://mlsanity.com/paper/2505.14465/) (2025)
- [Detect what you want: Target Sound Detection](https://mlsanity.com/paper/2112.10153/) (2021)
- [Multi-Branch Learning for Weakly-Labeled Sound Event Detection](https://mlsanity.com/paper/2002.09661/) (2020)
- [A Mixed supervised Learning Framework for Target Sound Detection](https://mlsanity.com/paper/2204.02088/) (2022)
- [RaDur: A Reference-aware and Duration-robust Network for Target Sound Detection](https://mlsanity.com/paper/2204.02143/) (2022)
- [Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments](https://mlsanity.com/paper/2502.16611/) (2025)
- [Aud-Sur: An Audio Analyzer Assistant for Audio Surveillance Applications](https://mlsanity.com/paper/2503.23827/) (2025)

## Abstract (arXiv)

Human listeners exhibit the remarkable ability to segregate a desired sound from complex acoustic scenes through selective auditory attention, motivating the study of Targeted Sound Detection (TSD). The task requires detecting and localizing a target sound in a mixture when a reference audio of that sound is provided. Prior approaches, rely on generating a sound-discriminative conditional embedding vector for the reference and pairing it with a mixture encoder, jointly optimized with a multi-task learning approach. In this work, we propose a unified encoder architecture that processes both the reference and mixture audio within a shared representation space, promoting stronger alignment while reducing architectural complexity. This design choice not only simplifies the overall framework but also enhances generalization to unseen classes. Following the multi-task training paradigm, our method achieves substantial improvements over prior approaches, surpassing existing methods and establishing a new state-of-the-art benchmark for targeted sound detection, with a segment-level F1 score of 83.15% and an overall accuracy of 95.17% on the URBAN-SED dataset.