{"id":19810582,"url":"https://github.com/fazledyn/gender-classification-from-audio-clips","last_synced_at":"2025-09-18T05:32:01.212Z","repository":{"id":193125251,"uuid":"604243037","full_name":"fazledyn/gender-classification-from-audio-clips","owner":"fazledyn","description":"In this project, we built a machine learning model that can identify the gender of a person from their voice recording.","archived":false,"fork":false,"pushed_at":"2023-03-31T10:19:21.000Z","size":670,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-11-12T09:26:39.088Z","etag":null,"topics":["deep-learning","gender-classification","machine-learning","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fazledyn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-02-20T16:29:24.000Z","updated_at":"2024-10-20T03:32:55.000Z","dependencies_parsed_at":"2023-09-06T22:52:27.146Z","dependency_job_id":null,"html_url":"https://github.com/fazledyn/gender-classification-from-audio-clips","commit_stats":null,"previous_names":["fazledyn/gender-classification-from-audio-clips"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fazledyn%2Fgender-classification-from-audio-clips","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fazledyn%2Fgender-classification-from-audio-clips/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fazledyn%2Fgender-classification-from-audio-clips/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fazledyn%2Fgender-classification-from-audio-clips/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fazledyn","download_url":"https://codeload.github.com/fazledyn/gender-classification-from-audio-clips/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233451337,"owners_count":18678210,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","gender-classification","machine-learning","tensorflow"],"created_at":"2024-11-12T09:22:30.521Z","updated_at":"2025-09-18T05:31:55.850Z","avatar_url":"https://github.com/fazledyn.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"![Project Cover Image](/docs/cover.svg)\n\n# Overview\nIn this project, we aim to build a machine learning model that can identify the gender of a person from their voice recording. In the process, we use two intermediary data representation format of the audio clips- **Mel Spectrogram** (Mel) and **Mel-Frequency Cepstral Coefficients** (MFCC).\n\n\n# Datasets\n**[MCV]** Common Voice by Mozilla.org (https://www.kaggle.com/datasets/mozillaorg/common-voice)\n\n**[DLS]** Bengali Common Voice Speech Dataset (https://www.kaggle.com/competitions/dlsprint)\n\n\n# Proposed Solution\n## Mel-Frequency Cepstral Coefficients (MFCC)\n![Project Cover Image](/docs/mfcc.png)\n## Mel Spectrogram\n![Project Cover Image](/docs/mel.png)\n\n\n# Notebook Details\n## Training\nThe `training` folder contains four notebooks. Each of the notebooks are named as: `[Data-Type]_[Dataset]_[Model]`. These notebooks are used to train individual models on the train datasets.\n\n```      \n└── training\n    ├── mel_dls_resnet50_train.ipynb \n    ├── mel_mcv_resnet50.ipynb       \n    ├── mfcc_dls_train_resnet50.ipynb\n    └── mfcc_mcv_resnet50.ipynb\n```\n\n## Evaluation\nThe `evaluation` folder contains four notebooks. Each of the notebooks are named as: `[Data-Type]_[Datase#1]_on_[Dataset#2]`. The models trained on `Dataset#1` are used to evaluate `Dataset#2`.\n\n```\n└── evaluation\n    ├── mel_dls_on_mcv.ipynb\n    ├── mel_mcv_on_dls.ipynb\n    ├── mfcc_dls_on_mcv.ipynb        \n    └── mfcc_mcv_on_dls.ipynb\n```\n\nIn the report mentioned in the [presentation](#presentation-report), the comparison between models are shown.\n\n\n# Model Details\n- Architecture: ResNet50\n- Learning Rate: 0.0001\n- Adam Optimizer\n\n\n# Presentation Report\nhttps://docs.google.com/presentation/d/14BWOq6YSmO3GqZHEvCou43Z5A4dlOmKq4pjqUqgZALU/\n\n\n# References\n[1]  **Speaker Gender Recognition Based on Deep Neural Networks and ResNet50** (https://doi.org/10.1155/2022/4444388)\n\n[2]  **A Machine Learning Approach to Automating Bengali Voice Based Gender Classification** (https://ieeexplore.ieee.org/document/9117385)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffazledyn%2Fgender-classification-from-audio-clips","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffazledyn%2Fgender-classification-from-audio-clips","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffazledyn%2Fgender-classification-from-audio-clips/lists"}