Probably pleasant? A neural-probabilistic approach to automatic masker selection for urban soundscape augmentation

• Main Authors: Ooi, Kenenth, Watcharasupat, Karn N., Lam, Bhan, Ong, Zhen-Ting, Gan, Woon-Seng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2022
• Subjects: Engineering::Electrical and electronic engineering; Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Science::Physics::Acoustics; Social sciences::Psychology::Applied psychology; Soundscape; Neural Attention; Soundscape Augmentation; Deep Learning; Probabilistic Model
• Online Access: https://hdl.handle.net/10356/158000
• Institution: Nanyang Technological University

Soundscape augmentation, which involves the addition of sounds known as “maskers” to a given soundscape, is a human-centric urban noise mitigation measure aimed at improving the overall soundscape quality. However, the choice of maskers is often predicated on laborious processes and is inflexible to the time-varying nature of real-world soundscapes. Owing to the perceptual uniqueness of each soundscape and the inherent subjectiveness of human perception, we propose a probabilistic perceptual attribute predictor (PPAP) that predicts parameters of random distributions as outputs instead of a single deterministic value. Using the PPAP, we developed a novel automatic masker selection system (AMSS), which selects optimal masker candidates based on the predicted distribution of the ISO 12913-3 Pleasantness score for a given soundscape. Via a large-scale listening test with 300 participants, we collected 12600 subjective responses, each to a unique augmented soundscape, to train the PPAP models in a 5-fold cross-validation scheme. Using a convolutional recurrent neural network backbone and experimenting with several variants of the attention mechanism for the PPAP, we evaluated the proposed system on a blind test set with 48 unseen augmented soundscapes to assess the effectiveness of the probabilistic output scheme over traditional deterministic systems.