{"id":18439472,"url":"https://github.com/idiap/cnn_qbe_std","last_synced_at":"2025-08-10T03:39:31.504Z","repository":{"id":144961730,"uuid":"147165027","full_name":"idiap/CNN_QbE_STD","owner":"idiap","description":"Implementation of the work presented in \"CNN based Query by Example Spoken Term Detection\"","archived":false,"fork":false,"pushed_at":"2018-09-03T07:05:52.000Z","size":1113,"stargazers_count":32,"open_issues_count":4,"forks_count":8,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-07T21:41:14.920Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/idiap.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-09-03T07:05:38.000Z","updated_at":"2024-08-11T08:44:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"d7704b86-f028-4f29-908b-73abf108f768","html_url":"https://github.com/idiap/CNN_QbE_STD","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/idiap/CNN_QbE_STD","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2FCNN_QbE_STD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2FCNN_QbE_STD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2FCNN_QbE_STD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2FCNN_QbE_STD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/idiap","download_url":"https://codeload.github.com/idiap/CNN_QbE_STD/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2FCNN_QbE_STD/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269672684,"owners_count":24457116,"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","status":"online","status_checked_at":"2025-08-10T02:00:08.965Z","response_time":71,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2024-11-06T06:24:54.742Z","updated_at":"2025-08-10T03:39:31.475Z","avatar_url":"https://github.com/idiap.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Description\nImplementation of the work presented in **\"CNN based Query by Example Spoken Term Detection\"**.\n\nWe have included some example groundtruth files for training as well as development set.\n\nThe posteriors features are extracted using the setup presented in the following paper:\n**\"High-performance query-by-example spoken term detection on the SWS 2013 evaluation\"**.\n\nThe input feature files for training/evaluation are in pytorch readable format which are \nsaved as python dictionaries. The keys are the names of the files in *'groundtruth files'*\nand values are the features in matrix format.\n\n## Training\n\n```\npython query_detection_dtw_cnn.py -optim adam -learning_rate 0.0001 -input_size 152 -batch_size 50 -layers 9 -depth 30 -dropout 0.2 -loss_threshold 0.1 -n_valid 50 -max_batch_dev 250 -max_batch_train 1000\n```\n\n## Evaluation\n\n```\npython query_detection_dtw_cnn_evaluation.py -input_size 152 -depth 30 -load_model -modelpath cnn_qbe_std_model.pt -outdir outpath -query_list dev_queries_sample_list.txt -search_list search_utterances_sample_list.txt\n```\n\n## Reference\n```\n@inproceedings{ram2018cnn,\n  title={CNN based Query by Example Spoken Term Detection},\n  author={Ram, Dhananjay and Miculicich, Lesly and Bourlard, Herv{\\'e}},\n  booktitle={Nineteenth Annual Conference of the International Speech Communication Association (INTERSPEECH)},\n  year={2018}\n}\n```\n\n## Contact:\n\ndhananjay.ram@idiap.ch\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fcnn_qbe_std","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fidiap%2Fcnn_qbe_std","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fcnn_qbe_std/lists"}