Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim

A sound retrieval method enables users to easily obtain their preferred sound. When we communicate, we exchange the expressive and related messages. This project reviews about identification of expressive speech video segment using acoustic features. Specifically, the segmented expressive speech ret...

Full description

Saved in:
Bibliographic Details
Main Author: Alim, Nur Amanini Syahirah
Format: Thesis
Language:English
Published: 2017
Subjects:
Online Access:https://ir.uitm.edu.my/id/eprint/98097/1/98097.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-uitm-ir.98097
record_format uketd_dc
spelling my-uitm-ir.980972024-08-21T23:27:46Z Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim 2017 Alim, Nur Amanini Syahirah Electronic Computers. Computer Science A sound retrieval method enables users to easily obtain their preferred sound. When we communicate, we exchange the expressive and related messages. This project reviews about identification of expressive speech video segment using acoustic features. Specifically, the segmented expressive speech retrieves the expressive speech and non-expressive speech from the video. From the sermon video that we have choose, the expression of motivator looks like similar from the beginning until the end. The audience cannot focus on what the motivator is talk about because there is no interesting part based on the motivator’s expression. This project applies manual video segmentation to differentiate expressive speech and non-expressive speech. Then, this project extracted the audio features from segmented expressive and non-expressive speech such as pitch and intensity by using Pratt tools. Then, we used Random Forest Classifier technique in Spyder (IDE) using Python language to get the accuracy which is 43% and used the prediction method to classify the expressive speech and non-expressive speech as the intended results. The training audio features was trained to get the performance accuracy. The correctness of the project has been showed from the evaluation. The project compared the predicted and manually segmented data to get the percentage of matches using pitch, the percentage of match is 80% while using the intensity is 75%. The correctness of the results has been verified to improve the identification of expressive speech video segment automatically. 2017 Thesis https://ir.uitm.edu.my/id/eprint/98097/ https://ir.uitm.edu.my/id/eprint/98097/1/98097.pdf text en public degree Universiti Teknologi MARA (UiTM) Faculty of Computer and Mathematical Sciences Mohamed Hanum, Haslizatul Fairuz
institution Universiti Teknologi MARA
collection UiTM Institutional Repository
language English
advisor Mohamed Hanum, Haslizatul Fairuz
topic Electronic Computers
Computer Science
spellingShingle Electronic Computers
Computer Science
Alim, Nur Amanini Syahirah
Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim
description A sound retrieval method enables users to easily obtain their preferred sound. When we communicate, we exchange the expressive and related messages. This project reviews about identification of expressive speech video segment using acoustic features. Specifically, the segmented expressive speech retrieves the expressive speech and non-expressive speech from the video. From the sermon video that we have choose, the expression of motivator looks like similar from the beginning until the end. The audience cannot focus on what the motivator is talk about because there is no interesting part based on the motivator’s expression. This project applies manual video segmentation to differentiate expressive speech and non-expressive speech. Then, this project extracted the audio features from segmented expressive and non-expressive speech such as pitch and intensity by using Pratt tools. Then, we used Random Forest Classifier technique in Spyder (IDE) using Python language to get the accuracy which is 43% and used the prediction method to classify the expressive speech and non-expressive speech as the intended results. The training audio features was trained to get the performance accuracy. The correctness of the project has been showed from the evaluation. The project compared the predicted and manually segmented data to get the percentage of matches using pitch, the percentage of match is 80% while using the intensity is 75%. The correctness of the results has been verified to improve the identification of expressive speech video segment automatically.
format Thesis
qualification_level Bachelor degree
author Alim, Nur Amanini Syahirah
author_facet Alim, Nur Amanini Syahirah
author_sort Alim, Nur Amanini Syahirah
title Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim
title_short Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim
title_full Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim
title_fullStr Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim
title_full_unstemmed Identification of expressive speech video segment using acoustic features / Nur Amanini Syahirah Alim
title_sort identification of expressive speech video segment using acoustic features / nur amanini syahirah alim
granting_institution Universiti Teknologi MARA (UiTM)
granting_department Faculty of Computer and Mathematical Sciences
publishDate 2017
url https://ir.uitm.edu.my/id/eprint/98097/1/98097.pdf
_version_ 1811768888382193664