The ITU-R BS.1770 recommendation for measuring the perceived loudness of audio signals has seen widespread adoption in broadcasting. Due to its simplicity, this algorithm has now found applications across audio signal processing. Here we describe pyloudnorm, a Python package that enables the measurement of integrated loudness following the recommendation. While a number of implementations are available, ours provides an easy-to-install package, a simple interface, and the ability to adjust the algorithm parameters, a feature that others neglect. We outline the design of pyloudnorm and discuss a set of modifications based upon recent literature that improve the robustness of loudness measurements. We perform an evaluation comparing accuracy and runtime with six other implementations, demonstrating that pyloudnorm is both fully compliant and one of the fastest options.
(See document for exact affiliation information.)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
