Soundscapy
Listed under Others. It does not compute the metrics itself; its results come from MoSQITo.
Python library for soundscape assessment. Its optional audio module computes psychoacoustic metrics of binaural recordings, per channel, by calling MoSQITo: time-varying Zwicker loudness, DIN 45692 sharpness and Daniel & Weber roughness.
| Repository | https://github.com/MitchellAcoustics/Soundscapy |
|---|---|
| Documentation | https://soundscapy.readthedocs.io/en/latest/ |
| Language | Python |
| Kind | Library/Toolbox Functions to call from your own code: a Python package, a MATLAB toolbox, or a C, C++, C#, Rust or Julia library. |
| Group | other Tools that do not compute the metrics themselves: interfaces, front ends and wrappers that call one of the listed projects. |
| Licence | BSD-3-Clause |
| Package | PyPI soundscapy |
| Install | pip install "soundscapy[audio]" |
| Latest release | v0.8.5 (2026-05) |
| Last commit | 2026-05-14 active |
| GitHub stars | 59 |
| Maintainers | Andrew Mitchell |
| AI assistance | disclosed (Commit metadata only; the README does not mention AI. At least 31 commits from March to May 2026 carry co-author lines for Claude or Copilot, and eight commits are authored by copilot-swe-agent[bot].) |
| Paper | Mitchell, A., Aletta, F., & Kang, J. (2022). How to analyse and represent quantitative soundscape data. JASA Express Letters, 2, 037201. https://doi.org/10.1121/10.0009794 |
| How to cite | Cite the paper above. The repository has a CITATION.cff file. Name the version or commit you used. |
| Entry checked | 6 October 2026 |
What it implements
| Metric | Edition | Functions | Validation (as stated) | Notes |
|---|---|---|---|---|
| Zwicker loudness | ISO 532-1:2017 time-varying, per channel | Binaural.mosqito_metric, process_all_metrics | not stated | Computed by MoSQITo. Calls loudness_zwtv. |
| Sharpness | DIN 45692:2009 | Binaural.mosqito_metric, process_all_metrics | not stated | Computed by MoSQITo. Calls sharpness_din_from_loudness, sharpness_din_perseg or sharpness_din_tv; the weighting can be chosen. |
| Roughness (Daniel & Weber) | Daniel & Weber (1997) | Binaural.mosqito_metric, process_all_metrics | not stated | Computed by MoSQITo. Calls roughness_dw. |
How it was validated
As reported by the project; LISQM has not run the code. Two implementations that agree can still share the same error. Kinds of evidence.
The project does not say how any of these were validated.
Notes
- The psychoacoustic functions need the optional
audioextra (MoSQITo 1.2.1 or newer). Environmental acoustic metrics come from acoustic-toolbox and ecoacoustic indices from scikit-maad. - Issue #123, open since 2025-10-29, plans to integrate sottek-hearing-model for ECMA-418-2 metrics; its branch has no such code yet.
- The paper the README asks users to cite covers soundscape data analysis, not the psychoacoustic functions.
Before you rely on it
- The psychoacoustic values are computed by MoSQITo, so their editions and accuracy are those of the installed MoSQITo version.