# Yet Another Generative Model For Room Impulse Response Estimation

arXiv: https://arxiv.org/abs/2311.02581 · HTML: https://mlsanity.com/paper/2311.02581/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2023.

## Built on by (most cited first, 4 of 4)

- [AV-RIR: Audio-Visual Room Impulse Response Estimation](https://mlsanity.com/paper/2312.00834/) (2023)
- [Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers](https://mlsanity.com/paper/2602.09233/) (2026)
- [Blind Spatial Impulse Response Generation from Separate Room- and Scene-Specific Information](https://mlsanity.com/paper/2409.14971/) (2024)
- [Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score](https://mlsanity.com/paper/2607.01527/) (2026)

## Abstract (arXiv)

Recent neural room impulse response (RIR) estimators typically comprise an encoder for reference audio analysis and a generator for RIR synthesis. Especially, it is the performance of the generator that directly influences the overall estimation quality. In this context, we explore an alternate generator architecture for improved performance. We first train an autoencoder with residual quantization to learn a discrete latent token space, where each token represents a small time-frequency patch of the RIR. Then, we cast the RIR estimation problem as a reference-conditioned autoregressive token generation task, employing transformer variants that operate across frequency, time, and quantization depth axes. This way, we address the standard blind estimation task and additional acoustic matching problem, which aims to find an RIR that matches the source signal to the target signal's reverberation characteristics. Experimental results show that our system is preferable to other baselines across various evaluation metrics.