# Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders

arXiv: https://arxiv.org/abs/2609.27195 · HTML: https://mlsanity.com/paper/2609.27195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [HEAR: Holistic Evaluation of Audio Representations](https://mlsanity.com/paper/2203.03022/) (2022)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics](https://mlsanity.com/paper/2401.16812/) (2024)
- [Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio](https://mlsanity.com/paper/2501.11378/) (2025)
- [A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences](https://mlsanity.com/paper/2001.04460/) (2020)
- [Speech Robust Bench: A Robustness Benchmark For Speech Recognition](https://mlsanity.com/paper/2403.07937/) (2024)
- [Effective Context in Neural Speech Models](https://mlsanity.com/paper/2505.22487/) (2025)
- [Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models](https://mlsanity.com/paper/2605.02715/) (2026)
- [Self-Supervised Speech Quality Assessment (S3QA): Leveraging Speech Foundation Models for a Scalable Speech Quality Metric](https://mlsanity.com/paper/2506.01655/) (2025)
- [SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails](https://mlsanity.com/paper/2606.06837/) (2026)

## Abstract (arXiv)

Non-speech interference can change a speech representation without causing comparable task loss. We test eight frozen encoders on four tasks, adding non-speech sounds throughout recordings, during speech, or in pauses. Under whole-recording interference, embedding drift tracks task loss across seven sounds, with mean Spearman correlations of 0.81-0.88. Moving the same sound between speech and pauses changes this pattern. At quiet to moderate levels, pause interference produces larger drift, while speech interference usually causes greater loss on intent recognition, speaker verification and speech recognition. Emotion recognition shows a weaker placement effect. Pause interference also changes speech-frame representations beyond the injected region. Even below the estimated recording background, interference can change embeddings as much as repeated speech takes do. Drift helps rank the effects of different sounds, but larger drift does not consistently indicate greater task loss.