A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms
Effective noise reduction and speech enhancement algorithms have great potential to enhance lives of hearing aid users by restoring speech intelligibility. An open problem in today’s commercial hearing aids is how to take into account users’ preferences, indicating which acoustic sources should be s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/20/9535 |
| _version_ | 1797515400606384128 |
|---|---|
| author | Bart van Erp Albert Podusenko Tanya Ignatenko Bert de Vries |
| author_facet | Bart van Erp Albert Podusenko Tanya Ignatenko Bert de Vries |
| author_sort | Bart van Erp |
| collection | DOAJ |
| description | Effective noise reduction and speech enhancement algorithms have great potential to enhance lives of hearing aid users by restoring speech intelligibility. An open problem in today’s commercial hearing aids is how to take into account users’ preferences, indicating which acoustic sources should be suppressed or enhanced, since they are not only user-specific but also depend on many situational factors. In this paper, we develop a fully probabilistic approach to “situated soundscaping”, which aims at enabling users to make on-the-spot (“situated”) decisions about the enhancement or suppression of individual acoustic sources. The approach rests on a compact generative probabilistic model for acoustic signals. In this framework, all signal processing tasks (source modeling, source separation and soundscaping) are framed as automatable probabilistic inference tasks. These tasks can be efficiently executed using message passing-based inference on factor graphs. Since all signal processing tasks are automatable, the approach supports fast future model design cycles in an effort to reach commercializable performance levels. The presented results show promising performance in terms of SNR, PESQ and STOI improvements in a situated setting. |
| first_indexed | 2024-03-10T06:44:58Z |
| format | Article |
| id | doaj.art-0aba35f1109443db969c9df3427d4580 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T06:44:58Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0aba35f1109443db969c9df3427d45802023-11-22T17:20:13ZengMDPI AGApplied Sciences2076-34172021-10-011120953510.3390/app11209535A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping AlgorithmsBart van Erp0Albert Podusenko1Tanya Ignatenko2Bert de Vries3Department of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The NetherlandsDepartment of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The NetherlandsGN Hearing, 5612 AB Eindhoven, The NetherlandsDepartment of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The NetherlandsEffective noise reduction and speech enhancement algorithms have great potential to enhance lives of hearing aid users by restoring speech intelligibility. An open problem in today’s commercial hearing aids is how to take into account users’ preferences, indicating which acoustic sources should be suppressed or enhanced, since they are not only user-specific but also depend on many situational factors. In this paper, we develop a fully probabilistic approach to “situated soundscaping”, which aims at enabling users to make on-the-spot (“situated”) decisions about the enhancement or suppression of individual acoustic sources. The approach rests on a compact generative probabilistic model for acoustic signals. In this framework, all signal processing tasks (source modeling, source separation and soundscaping) are framed as automatable probabilistic inference tasks. These tasks can be efficiently executed using message passing-based inference on factor graphs. Since all signal processing tasks are automatable, the approach supports fast future model design cycles in an effort to reach commercializable performance levels. The presented results show promising performance in terms of SNR, PESQ and STOI improvements in a situated setting.https://www.mdpi.com/2076-3417/11/20/9535Bayesian machine learningfactor graphsnoise reductionsituated soundscapingspeech enhancementvariational message passing |
| spellingShingle | Bart van Erp Albert Podusenko Tanya Ignatenko Bert de Vries A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms Applied Sciences Bayesian machine learning factor graphs noise reduction situated soundscaping speech enhancement variational message passing |
| title | A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms |
| title_full | A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms |
| title_fullStr | A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms |
| title_full_unstemmed | A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms |
| title_short | A Bayesian Modeling Approach to Situated Design of Personalized Soundscaping Algorithms |
| title_sort | bayesian modeling approach to situated design of personalized soundscaping algorithms |
| topic | Bayesian machine learning factor graphs noise reduction situated soundscaping speech enhancement variational message passing |
| url | https://www.mdpi.com/2076-3417/11/20/9535 |
| work_keys_str_mv | AT bartvanerp abayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT albertpodusenko abayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT tanyaignatenko abayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT bertdevries abayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT bartvanerp bayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT albertpodusenko bayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT tanyaignatenko bayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms AT bertdevries bayesianmodelingapproachtosituateddesignofpersonalizedsoundscapingalgorithms |