HearLoc: Locating Unknown Sound Sources in 3D With a Small-Sized Microphone Array
Bibliographic record
Abstract
Indoor Sound Source Localization (ISSL) is under growing focus with the rapid development of smart IOT intelligence. The predominant approaches typically involve constructing large microphone (Mic) array systems or extracting multiple angles of arrival (AOAs). However, the performance of these solutions is often constrained by the physical size of the array. Besides, there has been limited focus on 3D localization with a single small-sized Mic array. In this paper, we propose HearLoc, an ISSL system that can directly locate 3D sources with a ten-<inline-formula><tex-math notation="LaTeX">$cm$</tex-math></inline-formula> Mic array. We demonstrate that the localization ability and dimensional capability can be significantly enhanced by incorporating the time differences of arrival (TDOAs) between the line-of-sight (LOS) and ECHO signals from nearby reflective surfaces. Our approach involves a localization method that selectively sums the correlation powers at useful TDOAs induced by each location. We also design a data processing pipeline with interpolation, normalization and pruning techniques to improve system accuracy and efficiency. To further enhance scalability, we design an iterative algorithm for the ISSL problem with multiple sources and an array location calibration scheme. Experiments demonstrate that the HearLoc can effectively locate sound sources, exhibiting <inline-formula><tex-math notation="LaTeX">$2\times$</tex-math></inline-formula>/<inline-formula><tex-math notation="LaTeX">$3.7\times$</tex-math></inline-formula> improvements in accuracy for 2D and 3D localization, respectively, and a <inline-formula><tex-math notation="LaTeX">$4\times$</tex-math></inline-formula> increase in efficiency compared to the existing AOA-based ISSL solutions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".