Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network
The process of speaker recognition in a noisy and distant environment is a difficult task as it faces numerous challenges before clean speaker speech signal reaching the microphone. While developing a deep neural network for robust functioning in extreme conditions, the selection of a perfectly comp...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
IEEE
2022
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/37829/ |
| _version_ | 1848848711280492544 |
|---|---|
| author | Natarajan, Sureshkumar Al-Haddad, Syed Abdul Rahman Ahmad, Faisul Arif Hassan, Mohd Khair Raja Kamil Azrad, Syaril Yahya, Mohammed Nawfal Macleans, June Francis Salvekar, Pratiksha Prashant |
| author_facet | Natarajan, Sureshkumar Al-Haddad, Syed Abdul Rahman Ahmad, Faisul Arif Hassan, Mohd Khair Raja Kamil Azrad, Syaril Yahya, Mohammed Nawfal Macleans, June Francis Salvekar, Pratiksha Prashant |
| author_sort | Natarajan, Sureshkumar |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | The process of speaker recognition in a noisy and distant environment is a difficult task as it faces numerous challenges before clean speaker speech signal reaching the microphone. While developing a deep neural network for robust functioning in extreme conditions, the selection of a perfectly compatible optimizer, loss function, and dropout is necessary. This paper presents a comparative study of the optimization process in the neural network, how loss function effectively unites in seeking the optimizer. It emphasizes on the selection of the number of input nodes, hidden layers, and time consumed by each set of selections. This study elaborates the accuracy obtained at different combinations of parameters for robust deep neural network structure. This paper is classified under speaker and speech recognition process into improving accuracy. Experiment results shows that Adam optimizer with 150 epochs offers around 95% accuracy for speaker classification under the noisy condition at different SNR values. |
| first_indexed | 2025-11-15T09:38:50Z |
| format | Conference or Workshop Item |
| id | upm-37829 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T09:38:50Z |
| publishDate | 2022 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-378292023-11-13T05:28:15Z http://psasir.upm.edu.my/id/eprint/37829/ Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network Natarajan, Sureshkumar Al-Haddad, Syed Abdul Rahman Ahmad, Faisul Arif Hassan, Mohd Khair Raja Kamil Azrad, Syaril Yahya, Mohammed Nawfal Macleans, June Francis Salvekar, Pratiksha Prashant The process of speaker recognition in a noisy and distant environment is a difficult task as it faces numerous challenges before clean speaker speech signal reaching the microphone. While developing a deep neural network for robust functioning in extreme conditions, the selection of a perfectly compatible optimizer, loss function, and dropout is necessary. This paper presents a comparative study of the optimization process in the neural network, how loss function effectively unites in seeking the optimizer. It emphasizes on the selection of the number of input nodes, hidden layers, and time consumed by each set of selections. This study elaborates the accuracy obtained at different combinations of parameters for robust deep neural network structure. This paper is classified under speaker and speech recognition process into improving accuracy. Experiment results shows that Adam optimizer with 150 epochs offers around 95% accuracy for speaker classification under the noisy condition at different SNR values. IEEE 2022 Conference or Workshop Item PeerReviewed Natarajan, Sureshkumar and Al-Haddad, Syed Abdul Rahman and Ahmad, Faisul Arif and Hassan, Mohd Khair and Raja Kamil and Azrad, Syaril and Yahya, Mohammed Nawfal and Macleans, June Francis and Salvekar, Pratiksha Prashant (2022) Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network. In: 2022 International Conference on Future Trends in Smart Communities (ICFTSC), 1-2 Dec. 2022, Borneo Conventional Centre Kuching, Sarawak, Malaysia. (pp. 12-17). https://ieeexplore.ieee.org/document/10040065 10.1109/ICFTSC57269.2022.10040065 |
| spellingShingle | Natarajan, Sureshkumar Al-Haddad, Syed Abdul Rahman Ahmad, Faisul Arif Hassan, Mohd Khair Raja Kamil Azrad, Syaril Yahya, Mohammed Nawfal Macleans, June Francis Salvekar, Pratiksha Prashant Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| title | Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| title_full | Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| title_fullStr | Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| title_full_unstemmed | Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| title_short | Comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| title_sort | comparative analysis of different parameters used for optimization in the process of speaker and speech recognition using deep neural network |
| url | http://psasir.upm.edu.my/id/eprint/37829/ http://psasir.upm.edu.my/id/eprint/37829/ http://psasir.upm.edu.my/id/eprint/37829/ |