Efficiency of Spectral Subtraction Algorithms for an Urban Audio Acquisition System Using IoT Devices
Bibliographic record
Abstract
Ambient audio acquisition systems gather information about the noise levels in a specific area. Such systems chart the environment based on averaged sound parameters as they change over time. This can improve human life by detecting nuisance noise as well as sound levels hazardous to human health and by allowing citizens, business owners and urban planners to visualize the noise pollution in their city. An efficient way to monitor the noise is through cost-effective, small-size Internet of Thing (IoT) devices that monitor, record and report the noise level. However, the prevalence of wind and electrical interference and artefacts in urban environments affects the fidelity of audio acquisitions. Filtering out these unwanted contributions allows the analysis of relevant sounds. In this paper, three spectral subtraction algorithms are compared and applied to urban sound clips to reduce unwanted noise from audio recordings. The effectiveness of the Boll, Berouti, and Kamath algorithms for reducing noise in various sounds found in urban environments was assessed. Then, an IoT device was used to collect real data from an outdoor environment, using a spectral subtraction algorithm. According to experimental results, the Kamath algorithm increases the signal-to-noise ratio by 20 dB and improves the resemblance to the true audio signal.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".