{"id":18439435,"url":"https://github.com/idiap/kaldi-ivector","last_synced_at":"2025-04-07T21:32:27.133Z","repository":{"id":144962259,"uuid":"49192023","full_name":"idiap/kaldi-ivector","owner":"idiap","description":"Extension to Kaldi implementing the standard i-vector hyperparameter estimation and i-vector extraction procedure","archived":false,"fork":false,"pushed_at":"2018-02-23T06:46:53.000Z","size":59,"stargazers_count":89,"open_issues_count":3,"forks_count":24,"subscribers_count":12,"default_branch":"master","last_synced_at":"2025-03-23T01:01:42.871Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","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,"roadmap":null,"authors":null}},"created_at":"2016-01-07T08:33:37.000Z","updated_at":"2024-11-04T22:00:47.000Z","dependencies_parsed_at":"2024-01-13T22:25:10.719Z","dependency_job_id":"68124b7b-5e29-40e1-acaa-0bac1206954f","html_url":"https://github.com/idiap/kaldi-ivector","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fkaldi-ivector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fkaldi-ivector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fkaldi-ivector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fkaldi-ivector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/idiap","download_url":"https://codeload.github.com/idiap/kaldi-ivector/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247732682,"owners_count":20986901,"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":[],"created_at":"2024-11-06T06:24:45.607Z","updated_at":"2025-04-07T21:32:22.120Z","avatar_url":"https://github.com/idiap.png","language":"C++","funding_links":[],"categories":["Software"],"sub_categories":["Speaker embedding"],"readme":"# UPDATED: 20/02/2018\nThis is the README to the Idiap's implementation of the i-vector\nsystem for Kaldi. It contains information about the package, implementation\ndetails, installation and compilation.\n\n## General information\n\nThis implementation of the i-vector system is based on the\nstandard i-vector extraction procedure. It contains code to estimate\nthe T-matrix with the conventional EM algorithm for estimation of\nEigenvoice matrices, estimate i-vectors given the T-matrix, features\nand corresponding posteriors. \n\n## Data structures\n\nThe classes for T-matrix and sufficient statistics are modifications\nto the classes already present in Kaldi. Some irrelevant members are\nremoved.\n\nThe i-vector is still a kaldi::Vector and is compatible with the \nLDA and PLDA backends already available in Kaldi.\n\n## Compilation\n\nTo compile the package simply follow the 2 steps\n\n1. export the path to kaldi souce in the environment variable $KALDI_DIR\n\n```\nexport KALDI_DIR=/home/username/kaldi-trunk/\n```\n\n2. Run make in the src/ directory\n\n```\ncd src/\nmake\n```\n\nNow, the binaries should have been created in the src/ivectorbin/\nfolder.\n\n## Kaldi recipe\n\nThe recipe equivalent to the kaldi recipe to train and\ntest a speaker recognition system for NIST SRE 2008 dataset\nis available in the scripts folder. The file scripts/run.sh\nis the main recipe that calls other scripts from within. \n\n## References\n\nThe implementation is based on the i-vector systems in \n\n[1] Glembek, Ondřej, et al. \"Simplification and optimization of i-vector extraction.\" Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. IEEE, 2011.\n\n[2] Madikeri, Srikanth. \"A hybrid factor analysis and probabilistic pca-based system for dictionary learning and encoding for robust speaker recognition.\" Odyssey Workshop. 2012.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fkaldi-ivector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fidiap%2Fkaldi-ivector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fkaldi-ivector/lists"}