Small-scale model for classification of single acoustic events
AI plays an essential role in enabling the awareness of intelligent machines and has recently attracted considerable attention. One such application of AI is audio classification. The most popular types of audio classifications are speech recognition and music classification. Both enjoyed great succ...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/157540 |
| _version_ | 1811684721374003200 |
|---|---|
| author | Ng, Matthew Tiong Ming |
| author2 | Gan Woon Seng |
| author_facet | Gan Woon Seng Ng, Matthew Tiong Ming |
| author_sort | Ng, Matthew Tiong Ming |
| collection | NTU |
| description | AI plays an essential role in enabling the awareness of intelligent machines and has recently attracted considerable attention. One such application of AI is audio classification. The most popular types of audio classifications are speech recognition and music classification. Both enjoyed great success and still have several widely used and reliable real-life applications such as Apple’s virtual assistant Siri for the former, and Shazam for the latter.
UST, on the other hand, is not as well-developed and popular when compared to the audio classification types mentioned earlier. UST can benefit AI-powered smart devices such as iPhones and robots by allowing them to better understand their environment better through the classification of sound scenes and recommend actions to users accordingly [1]. For example, this shows the potential of UST as it can improve the context understanding of AI models and may solve such issues.
UST is a trained machine model that can differentiate and classify different types of acoustic events. Acoustic events of daily urban life such as wedding parties, vehicle noise, keyboard typing, etc. can give relevant cues about the human presence and activity in a scenario. With such acoustic information, UST can make connections and allow analysts to find actionable insights from the generated audio descriptions.
Using DCASE 2019 Task 5 as a benchmark, the project looks into improving the baseline model both in terms of performance and reducing the model size. |
| first_indexed | 2024-10-01T04:33:08Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/157540 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:33:08Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1575402023-07-07T19:17:33Z Small-scale model for classification of single acoustic events Ng, Matthew Tiong Ming Gan Woon Seng School of Electrical and Electronic Engineering EWSGAN@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence AI plays an essential role in enabling the awareness of intelligent machines and has recently attracted considerable attention. One such application of AI is audio classification. The most popular types of audio classifications are speech recognition and music classification. Both enjoyed great success and still have several widely used and reliable real-life applications such as Apple’s virtual assistant Siri for the former, and Shazam for the latter. UST, on the other hand, is not as well-developed and popular when compared to the audio classification types mentioned earlier. UST can benefit AI-powered smart devices such as iPhones and robots by allowing them to better understand their environment better through the classification of sound scenes and recommend actions to users accordingly [1]. For example, this shows the potential of UST as it can improve the context understanding of AI models and may solve such issues. UST is a trained machine model that can differentiate and classify different types of acoustic events. Acoustic events of daily urban life such as wedding parties, vehicle noise, keyboard typing, etc. can give relevant cues about the human presence and activity in a scenario. With such acoustic information, UST can make connections and allow analysts to find actionable insights from the generated audio descriptions. Using DCASE 2019 Task 5 as a benchmark, the project looks into improving the baseline model both in terms of performance and reducing the model size. Bachelor of Engineering (Electrical and Electronic Engineering) 2022-05-21T11:18:10Z 2022-05-21T11:18:10Z 2022 Final Year Project (FYP) Ng, M. T. M. (2022). Small-scale model for classification of single acoustic events. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157540 https://hdl.handle.net/10356/157540 en A3082-211 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Ng, Matthew Tiong Ming Small-scale model for classification of single acoustic events |
| title | Small-scale model for classification of single acoustic events |
| title_full | Small-scale model for classification of single acoustic events |
| title_fullStr | Small-scale model for classification of single acoustic events |
| title_full_unstemmed | Small-scale model for classification of single acoustic events |
| title_short | Small-scale model for classification of single acoustic events |
| title_sort | small scale model for classification of single acoustic events |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/157540 |
| work_keys_str_mv | AT ngmatthewtiongming smallscalemodelforclassificationofsingleacousticevents |