# Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score

arXiv: https://arxiv.org/abs/2607.01527 · HTML: https://mlsanity.com/paper/2607.01527/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 1 Jul 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [Building and Evaluation of a Real Room Impulse Response Dataset](https://mlsanity.com/paper/1811.06795/) (2018)
- [Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speech](https://mlsanity.com/paper/2107.07503/) (2021)
- [MeshRIR: A Dataset of Room Impulse Responses on Meshed Grid Points For Evaluating Sound Field Analysis and Synthesis Methods](https://mlsanity.com/paper/2106.10801/) (2021)
- [SoundCam: A Dataset for Finding Humans Using Room Acoustics](https://mlsanity.com/paper/2311.03517/) (2023)
- [Contrastive Representation Learning for Acoustic Parameter Estimation](https://mlsanity.com/paper/2302.11205/) (2023)
- [Yet Another Generative Model For Room Impulse Response Estimation](https://mlsanity.com/paper/2311.02581/) (2023)
- [Blind Acoustic Parameter Estimation Through Task-Agnostic Embeddings Using Latent Approximations](https://mlsanity.com/paper/2407.19989/) (2024)
- [Neural network for multi-exponential sound energy decay analysis](https://mlsanity.com/paper/2205.09644/) (2022)

## Abstract (arXiv)

Room embeddings derived from reverberant speech are often unreliable: speech content and recording degradation can alter the representation even when speaker, room, and source-receiver geometry remain unchanged, degrading downstream task performance. We propose a framework that learns room embeddings robust to speech-content variation and a representation-level uncertainty score from reverberant speech without downstream-task supervision. The embedding is anchored to a structured room impulse response (RIR) latent space and trained using a multi-view data structure with Kullback-Leibler (KL)-based alignment; a multi-positive contrastive term further refines robustness. A lightweight uncertainty head is calibrated using the dispersion of corruption-induced embeddings and optimized with a rank-based objective. Across waveform- and spectrogram-level corruptions, the score is consistent with representation dispersion and enables effective selective prediction while requiring only a single utterance at inference.