Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 14, 2021Applied SciencesOpen Access

A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms

View Full Paper
Ask AI
Bookmark
Share

Authors

BEBart van ErpAPAlbert PodusenkoTITanya Ignatenko

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improvements in noise reduction for hearing aid users, highlighting personalized soundscaping's potential.

Key Points

  • This study aims to develop a Bayesian model for personalized soundscaping to enhance speech intelligibility for hearing aid users.
  • Developed a generative probabilistic model for acoustic signals.
  • Framed signal processing tasks as probabilistic inference tasks.
  • Utilized message passing-based inference on factor graphs.
  • Achieved improvements in signal-to-noise ratio (SNR), perceptual evaluation of speech quality (PESQ), and short-time objective intelligibility (STOI).
  • Results indicate enhancements in user-specific acoustic preferences in real situations.

Cite This Study

Erp et al. (2021) studied this question.

synapsesocial.com/papers/6a1f4142854268ffd72a95cbhttps://doi.org/10.3390/app11209535
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Towards Environmental Preference Based Speech Enhancement For Individualised Multi-Modal Hearing Aids2024
  2. 2Model-Informed Speech Enhancement Using Virtual Room Acoustics and Acoustic Descriptor Optimization2026
  3. 3A Speech-Segregation Algorithm for Spatial Hearing Aids to Operate With Multiple Sound Sources2026 · 1 citations
  4. 4Acoustic Scene-Aware Processing and Auditory Model-Based Compensation Strategies2026
  5. 5Real-Time Signal Processing for Distributed Acoustic Sensing and Acoustic Sensing Systems Under Non-Stationary Noise2026