# Blind Acoustic Parameter Estimation Through Task-Agnostic Embeddings Using Latent Approximations

arXiv: https://arxiv.org/abs/2407.19989 · HTML: https://mlsanity.com/paper/2407.19989/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2024.

## Built on by (most cited first, 3 of 3)

- [Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers](https://mlsanity.com/paper/2602.09233/) (2026)
- [Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study](https://mlsanity.com/paper/2503.22713/) (2025)
- [Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score](https://mlsanity.com/paper/2607.01527/) (2026)

## Abstract (arXiv)

We present a method for blind acoustic parameter estimation from single-channel reverberant speech. The method is structured into three stages. In the first stage, a variational auto-encoder is trained to extract latent representations of acoustic impulse responses represented as mel-spectrograms. In the second stage, a separate speech encoder is trained to estimate low-dimensional representations from short segments of reverberant speech. Finally, the pre-trained speech encoder is combined with a small regression model and evaluated on two parameter regression tasks. Experimentally, the proposed method is shown to outperform a fully end-to-end trained baseline model.