Optimization of automatic speech recognition under noisy environment using machine learning techniques
- Authors: Yamkela, Melane
- Date: 2024-04
- Subjects: Automatic speech recognition , Speech processing systems , Computational linguistics
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/29954 , vital:79216
- Description: Speech recognition technology is a fascinating field that enables machines to comprehend and interpret human speech. It allows users to interact with computers, smartphones, and other devices, using spoken commands rather than traditional input methods, like typing. Speech recognition systems analyse audio input, typically in the form of spoken words or phrases, and convert them into text or commands that computers can understand. The journey of speech recognition technology has been remarkable, evolving from simple command-based systems to advanced natural language processing algorithms capable of understanding context, accents, and even emotions. While speech recognition has made significant strides, challenges persist, particularly in accurately handling noisy environments and distinguishing between similarsounding words. This study aimed at developing an optimal automatic speech recognition system under a noisy environment, using machine learning techniques. In addition, the study aimed at evaluating the performance of the developed system. Speech recognition methodology involves several key steps to accurately transform verbal words into written commands or text, such as - Audio Input, Preprocessing, Feature Extraction, Acoustic Modeling, and Language Modeling. The model was developed using Google Collab and TensorFlow, an open-source machinelearning platform. This model used a transformer-hugging face, which is a pre-trained model. Transformers deploy convolutional neural networks that were trained with data collected by Facebook wac2 vec. For evaluation, the model made use of a confusion matrix, precision and accuracy metrics; the model was tested on real-time data and good results were achieved. Evaluation is continuing to observe the model's performance under different noisy backgrounds. This research adds to the corpus of knowledge, particularly in the field of speech recognition and for future work, the study will seek to use large live data and also investigate the error rate. , Thesis (MSci) -- Faculty of Science and Agriculture, 2024
- Full Text:
- Date Issued: 2024-04
- Authors: Yamkela, Melane
- Date: 2024-04
- Subjects: Automatic speech recognition , Speech processing systems , Computational linguistics
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/29954 , vital:79216
- Description: Speech recognition technology is a fascinating field that enables machines to comprehend and interpret human speech. It allows users to interact with computers, smartphones, and other devices, using spoken commands rather than traditional input methods, like typing. Speech recognition systems analyse audio input, typically in the form of spoken words or phrases, and convert them into text or commands that computers can understand. The journey of speech recognition technology has been remarkable, evolving from simple command-based systems to advanced natural language processing algorithms capable of understanding context, accents, and even emotions. While speech recognition has made significant strides, challenges persist, particularly in accurately handling noisy environments and distinguishing between similarsounding words. This study aimed at developing an optimal automatic speech recognition system under a noisy environment, using machine learning techniques. In addition, the study aimed at evaluating the performance of the developed system. Speech recognition methodology involves several key steps to accurately transform verbal words into written commands or text, such as - Audio Input, Preprocessing, Feature Extraction, Acoustic Modeling, and Language Modeling. The model was developed using Google Collab and TensorFlow, an open-source machinelearning platform. This model used a transformer-hugging face, which is a pre-trained model. Transformers deploy convolutional neural networks that were trained with data collected by Facebook wac2 vec. For evaluation, the model made use of a confusion matrix, precision and accuracy metrics; the model was tested on real-time data and good results were achieved. Evaluation is continuing to observe the model's performance under different noisy backgrounds. This research adds to the corpus of knowledge, particularly in the field of speech recognition and for future work, the study will seek to use large live data and also investigate the error rate. , Thesis (MSci) -- Faculty of Science and Agriculture, 2024
- Full Text:
- Date Issued: 2024-04
Assessment of antibiotic production by some marine actinomycetes belonging to the genera norcadia, saccharopolyspora and kibdellosporangium.
- Koba, Siziwe (https://orcid.org/0000-0002-6761-6403)
- Authors: Koba, Siziwe (https://orcid.org/0000-0002-6761-6403)
- Date: 2010
- Subjects: Actinobacteria , Bacteria , Actinomycetales
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/25811 , vital:64488
- Description: Antibacterial potency of the extracts of the three marine actinomycetes strains which were isolated in the Nahoon Beach and tentatively identified as the genera Norcadia, Kibdellosporingium and Saccharopolyspora were investigated in this study against a panel of referenced, environmental and clinical bacterial strains. The ethyl acetate extracts of these marine actinomycetes were screened for activity against 32 bacterial isolates. Out of the 32 organisms, 10 were susceptible to one or all the extracts used. Antibacterial activity was mainly observed against Gram-negative organisms with Minimum inhibitory concentration (MIC) values ranging from 0.078 mg/ml to >10mg/ml. The killing rates of the active extracts were also elucidated using standard procedures. The two extracts NO64 and NO53 showed rapid bactericidal activity against B. pumilus ATCC 14884 and Serratia marcens with a 3Log10 reduction in counts within 6 hours at 3.75 mg/ml and 5 mg/ml respectively. In conclusion, the ethyl acetate extract of these marine actinomycetes strains possess strong bactericidal and bacteriostatic activities against Gram negative organisms and can be therapeutically useful in the treatment of bacterial infections which are mainly caused by Gram negative bacteria. , Thesis (MA) -- Faculty of Science and Agriculture, 2010
- Full Text:
- Date Issued: 2010
- Authors: Koba, Siziwe (https://orcid.org/0000-0002-6761-6403)
- Date: 2010
- Subjects: Actinobacteria , Bacteria , Actinomycetales
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/25811 , vital:64488
- Description: Antibacterial potency of the extracts of the three marine actinomycetes strains which were isolated in the Nahoon Beach and tentatively identified as the genera Norcadia, Kibdellosporingium and Saccharopolyspora were investigated in this study against a panel of referenced, environmental and clinical bacterial strains. The ethyl acetate extracts of these marine actinomycetes were screened for activity against 32 bacterial isolates. Out of the 32 organisms, 10 were susceptible to one or all the extracts used. Antibacterial activity was mainly observed against Gram-negative organisms with Minimum inhibitory concentration (MIC) values ranging from 0.078 mg/ml to >10mg/ml. The killing rates of the active extracts were also elucidated using standard procedures. The two extracts NO64 and NO53 showed rapid bactericidal activity against B. pumilus ATCC 14884 and Serratia marcens with a 3Log10 reduction in counts within 6 hours at 3.75 mg/ml and 5 mg/ml respectively. In conclusion, the ethyl acetate extract of these marine actinomycetes strains possess strong bactericidal and bacteriostatic activities against Gram negative organisms and can be therapeutically useful in the treatment of bacterial infections which are mainly caused by Gram negative bacteria. , Thesis (MA) -- Faculty of Science and Agriculture, 2010
- Full Text:
- Date Issued: 2010
- «
- ‹
- 1
- ›
- »