# EnvId: A Metric Learning Approach for Forensic Few-Shot Identification of Unseen Environments

arXiv: https://arxiv.org/abs/2405.02119 · HTML: https://mlsanity.com/paper/2405.02119/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 3 May 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Utterance-level Aggregation For Speaker Recognition In The Wild](https://mlsanity.com/paper/1902.10107/) (2019)
- [A Theoretical Analysis of the Number of Shots in Few-Shot Learning](https://mlsanity.com/paper/1909.11722/) (2019)
- [MetaAudio: A Few-Shot Audio Classification Benchmark](https://mlsanity.com/paper/2204.02121/) (2022)
- [A Study of Few-Shot Audio Classification](https://mlsanity.com/paper/2012.01573/) (2020)
- [Contrastive Representation Learning for Acoustic Parameter Estimation](https://mlsanity.com/paper/2302.11205/) (2023)
- [Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification](https://mlsanity.com/paper/2309.16369/) (2023)
- [Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers](https://mlsanity.com/paper/2203.16499/) (2022)
- [Blind Acoustic Room Parameter Estimation Using Phase Features](https://mlsanity.com/paper/2303.07449/) (2023)
- [End-to-End Classification of Reverberant Rooms using DNNs](https://mlsanity.com/paper/1812.09324/) (2018)
- [Blind Reverberation Time Estimation in Dynamic Acoustic Conditions](https://mlsanity.com/paper/2202.11790/) (2022)
- [Environment Classification via Blind Roomprints Estimation](https://mlsanity.com/paper/2209.07196/) (2022)
- [Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets](https://mlsanity.com/paper/2307.05641/) (2023)

## Abstract (arXiv)

Audio recordings may provide important evidence in criminal investigations. One such case is the forensic association of a recorded audio to its recording location. For example, a voice message may be the only investigative cue to narrow down the candidate sites for a crime. Up to now, several works provide supervised classification tools for closed-set recording environment identification under relatively clean recording conditions. However, in forensic investigations, the candidate locations are case-specific. Thus, supervised learning techniques are not applicable without retraining a classifier on a sufficient amount of training samples for each case and respective candidate set. In addition, a forensic tool has to deal with audio material from uncontrolled sources with variable properties and quality. In this work, we therefore attempt a major step towards practical forensic application scenarios. We propose a representation learning framework called EnvId, short for environment identification. EnvId avoids case-specific retraining by modeling the task as a few-shot classification problem. We demonstrate that EnvId can handle forensically challenging material. It provides good quality predictions even under unseen signal degradations, out-of-distribution reverberation characteristics or recording position mismatches.