# TS-RIR: Translated synthetic room impulse responses for speech augmentation

arXiv: https://arxiv.org/abs/2103.16804 · HTML: https://mlsanity.com/paper/2103.16804/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2021.

## Built on by (most cited first, 12 of 12)

- [Few-Shot Audio-Visual Learning of Environment Acoustics](https://mlsanity.com/paper/2206.04006/) (2022)
- [FAST-RIR: Fast neural diffuse room impulse response generator](https://mlsanity.com/paper/2110.04057/) (2021)
- [MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes](https://mlsanity.com/paper/2205.09248/) (2022)
- [Self-Supervised Visual Acoustic Matching](https://mlsanity.com/paper/2307.15064/) (2023)
- [Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes](https://mlsanity.com/paper/2302.02809/) (2023)
- [How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes](https://mlsanity.com/paper/2508.02905/) (2025)
- [MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients](https://mlsanity.com/paper/2507.09750/) (2025)
- [Bayesian inference and neural estimation of acoustic wave propagation](https://mlsanity.com/paper/2305.17749/) (2023)
- [MetaSpeech: Speech Effects Switch Along with Environment for Metaverse](https://mlsanity.com/paper/2210.13811/) (2022)
- [SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field](https://mlsanity.com/paper/2406.11006/) (2024)
- [Materialistic RIR: Material Conditioned Realistic RIR Generation](https://mlsanity.com/paper/2604.21119/) (2026)
- [PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation](https://mlsanity.com/paper/2607.23293/) (2026)

## Abstract (arXiv)

We present a method for improving the quality of synthetic room impulse responses for far-field speech recognition. We bridge the gap between the fidelity of synthetic room impulse responses (RIRs) and the real room impulse responses using our novel, TS-RIRGAN architecture. Given a synthetic RIR in the form of raw audio, we use TS-RIRGAN to translate it into a real RIR. We also perform real-world sub-band room equalization on the translated synthetic RIR. Our overall approach improves the quality of synthetic RIRs by compensating low-frequency wave effects, similar to those in real RIRs. We evaluate the performance of improved synthetic RIRs on a far-field speech dataset augmented by convolving the LibriSpeech clean speech dataset [1] with RIRs and adding background noise. We show that far-field speech augmented using our improved synthetic RIRs reduces the word error rate by up to 19.9% in Kaldi far-field automatic speech recognition benchmark [2].