Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1606.06258

Uncalibrated 3D Room Reconstruction from Sound

Marco Crocco·Andrea Trucco·Alessio Del Bue
View original source ↗Read source document ↗Export metadata ↓

Abstract

This paper presents a method to reconstruct the 3D structure of generic convex rooms from sound signals. Differently from most of the previous approaches, the method is fully uncalibrated in the sense that no knowledge about the microphones and sources position is needed. Moreover, we demonstrate that it is possible to bypass the well known echo labeling problem, allowing to reconstruct the room shape in a reasonable computation time without the need of additional hypotheses on the echoes order of arrival. Finally, the method is intrinsically robust to outliers and missing data in the echoes detection, allowing to work also in low SNR conditions. The proposed pipeline formalises the problem in different steps such as time of arrival estimation, microphones and sources localization and walls estimation. After providing a solution to these different problems we present a global optimization approach that links together all the problems in a single optimization function. The accuracy and robustness of the method is assessed on a wide set of simulated setups and in a challenging real scenario. Moreover we make freely available for a challenging dataset for 3D room reconstruction with accurate ground truth in a real scenario.

Explore related subjects

cs.SD

Keep this discovery

BibTeXRIS

Marco Crocco, Andrea Trucco, Alessio Del Bue. 2016-06-20. Uncalibrated 3D Room Reconstruction from Sound. https://arxiv.org/abs/1606.06258

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗