Evaluation of sound-event classification for robot hearing
Over the years, there have been numerous ways of carrying out the process of sound event classification. Some of these known methods consists of the use of the spectrogram, a time-frequency spectral analysis that depicts the magnitude spectrum of the signal within a 2D time-frequency plane. Thoug...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77561 |
| _version_ | 1826111760784949248 |
|---|---|
| author | Ng, Max Rui Min |
| author2 | Jiang Xudong |
| author_facet | Jiang Xudong Ng, Max Rui Min |
| author_sort | Ng, Max Rui Min |
| collection | NTU |
| description | Over the years, there have been numerous ways of carrying out the process of sound
event classification. Some of these known methods consists of the use of the
spectrogram, a time-frequency spectral analysis that depicts the magnitude spectrum
of the signal within a 2D time-frequency plane. Though useful, there could have been
further improvements that could have been made. For example, what if the phase
spectrum was included as well? Would it have been able to provide more
distinguishable features to the sound for effective sound classification? Therefore, in
this Final Year Project, an evaluation will be carried out for a process called
“Regularized 2D complex-log-Fourier transform”, which was originally proposed by
Jiang Xudong and Ren Jianfeng. In the “Regularized 2D complex-log-Fourier
transform”, both magnitude and phase spectrums of the signal will be utilized for the
sound event classification. In addition, the Principal Component Analysis, PCA, will
be used to facilitate in the removal of unnecessary features in the samples which might
pose an issue during the classification process. Finally, the method chosen for the
sound classification is to calculate “Mahalanobis Distance” between the test samples
and the reference data of the training samples. |
| first_indexed | 2024-10-01T02:56:06Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/77561 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:56:06Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/775612023-07-07T17:00:29Z Evaluation of sound-event classification for robot hearing Ng, Max Rui Min Jiang Xudong School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Over the years, there have been numerous ways of carrying out the process of sound event classification. Some of these known methods consists of the use of the spectrogram, a time-frequency spectral analysis that depicts the magnitude spectrum of the signal within a 2D time-frequency plane. Though useful, there could have been further improvements that could have been made. For example, what if the phase spectrum was included as well? Would it have been able to provide more distinguishable features to the sound for effective sound classification? Therefore, in this Final Year Project, an evaluation will be carried out for a process called “Regularized 2D complex-log-Fourier transform”, which was originally proposed by Jiang Xudong and Ren Jianfeng. In the “Regularized 2D complex-log-Fourier transform”, both magnitude and phase spectrums of the signal will be utilized for the sound event classification. In addition, the Principal Component Analysis, PCA, will be used to facilitate in the removal of unnecessary features in the samples which might pose an issue during the classification process. Finally, the method chosen for the sound classification is to calculate “Mahalanobis Distance” between the test samples and the reference data of the training samples. Bachelor of Engineering (Electrical and Electronic Engineering) 2019-05-31T06:08:10Z 2019-05-31T06:08:10Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77561 en Nanyang Technological University 38 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Ng, Max Rui Min Evaluation of sound-event classification for robot hearing |
| title | Evaluation of sound-event classification for robot hearing |
| title_full | Evaluation of sound-event classification for robot hearing |
| title_fullStr | Evaluation of sound-event classification for robot hearing |
| title_full_unstemmed | Evaluation of sound-event classification for robot hearing |
| title_short | Evaluation of sound-event classification for robot hearing |
| title_sort | evaluation of sound event classification for robot hearing |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing |
| url | http://hdl.handle.net/10356/77561 |
| work_keys_str_mv | AT ngmaxruimin evaluationofsoundeventclassificationforrobothearing |