Machine learning / deep learning approach to soundscape analysis
Visual understanding of the soundscape environment is an enabling factor for a wide range of applications in studying how humans perceive sounds. Audiovisual scene decomposition allows further understanding of soundscape. This project will be focusing on the decomposition of urban soundscapes such a...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/158057 |
| _version_ | 1811695601428987904 |
|---|---|
| author | Koh, Cheng Yong |
| author2 | Gan Woon Seng |
| author_facet | Gan Woon Seng Koh, Cheng Yong |
| author_sort | Koh, Cheng Yong |
| collection | NTU |
| description | Visual understanding of the soundscape environment is an enabling factor for a wide range of applications in studying how humans perceive sounds. Audiovisual scene decomposition allows further understanding of soundscape. This project will be focusing on the decomposition of urban soundscapes such as parks, plazas, streets, etc. As water sounds are a prominent sound source in urban landscapes, this project will add a new waterbody class to the segmentation model which do not currently exist in most multiclass urban semantic segmentation model. This project proposes the use of the DeepLabV3+ model, with a ResNet50 backbone, trained on an improved Cityscapes dataset to perform semantic segmentation for urban scene decomposition. The training dataset will include additional waterbody images on top of the original Cityscapes images. |
| first_indexed | 2024-10-01T07:26:04Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/158057 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:26:04Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1580572023-07-07T19:21:44Z Machine learning / deep learning approach to soundscape analysis Koh, Cheng Yong Gan Woon Seng School of Electrical and Electronic Engineering EWSGAN@ntu.edu.sg Engineering::Electrical and electronic engineering Visual understanding of the soundscape environment is an enabling factor for a wide range of applications in studying how humans perceive sounds. Audiovisual scene decomposition allows further understanding of soundscape. This project will be focusing on the decomposition of urban soundscapes such as parks, plazas, streets, etc. As water sounds are a prominent sound source in urban landscapes, this project will add a new waterbody class to the segmentation model which do not currently exist in most multiclass urban semantic segmentation model. This project proposes the use of the DeepLabV3+ model, with a ResNet50 backbone, trained on an improved Cityscapes dataset to perform semantic segmentation for urban scene decomposition. The training dataset will include additional waterbody images on top of the original Cityscapes images. Bachelor of Engineering (Information Engineering and Media) 2022-05-26T05:49:40Z 2022-05-26T05:49:40Z 2022 Final Year Project (FYP) Koh, C. Y. (2022). Machine learning / deep learning approach to soundscape analysis. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158057 https://hdl.handle.net/10356/158057 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Koh, Cheng Yong Machine learning / deep learning approach to soundscape analysis |
| title | Machine learning / deep learning approach to soundscape analysis |
| title_full | Machine learning / deep learning approach to soundscape analysis |
| title_fullStr | Machine learning / deep learning approach to soundscape analysis |
| title_full_unstemmed | Machine learning / deep learning approach to soundscape analysis |
| title_short | Machine learning / deep learning approach to soundscape analysis |
| title_sort | machine learning deep learning approach to soundscape analysis |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/158057 |
| work_keys_str_mv | AT kohchengyong machinelearningdeeplearningapproachtosoundscapeanalysis |