{ "info": { "author": "Kazuhiro Kobayashi", "author_email": "root.4mac@gmail.com", "bugtrack_url": null, "classifiers": [ "License :: OSI Approved :: MIT License", "Topic :: Multimedia :: Sound/Audio :: Speech" ], "description": "[![Python Version](https://img.shields.io/badge/Python-3.5%2C%203.6%2C%203.7-green.svg)](https://img.shields.io/badge/Python-3.5%2C%203.6%2C%203.7-green.svg)\n[![Build Status](https://www.travis-ci.org/k2kobayashi/sprocket.svg?branch=travis)](https://www.travis-ci.org/k2kobayashi/sprocket)\n[![Coverage Status](https://coveralls.io/repos/github/k2kobayashi/sprocket/badge.svg?branch=master)](https://coveralls.io/github/k2kobayashi/sprocket?branch=master)\n[![PyPI version](https://badge.fury.io/py/sprocket-vc.svg)](https://badge.fury.io/py/sprocket-vc)\n[![MIT License](http://img.shields.io/badge/license-MIT-blue.svg?style=flat)](LICENSE)\n\nsprocket\n======\n\n\nVoice conversion software - Voice conversion (VC) is a technique to convert a speaker identity of a source speaker into that of a target speaker. This software enables the users to develop a traditional VC system based on a Gaussian mixture model (GMM) and a vocoder-free VC system based on a differential GMM (DIFFGMM) using a parallel dataset of the source and target speakers.\n\n## Paper and slide\n- K. Kobayashi, T. Toda, \"sprocket: Open-Source Voice Conversion Software,\" Proc. Odyssey, pp. 203-210, June 2018.\n[[paper]](https://nuss.nagoya-u.ac.jp/s/h8YKnq6qxjjxtU3)\n\n- T. Toda, \"Hands on Voice Conversion,\" Speech Processing Courses in Crete (SPCC), July 2018.\n[[slide]](https://www.slideshare.net/NU_I_TODALAB/hands-on-voice-conversion)\n\n## Conversion samples\n- Voice Conversion Challenge 2018 [[zip]](https://nuss.nagoya-u.ac.jp/index.php/s/Cs0YbTCw85p3QDK)\n\n\n## Purpose\n### Reproduce the typical VC systems\n\nThis software was developed to make it possible for the users to easily build the VC systems by only preparing a parallel dataset of the desired source and target speakers and executing example scripts.\nThe following VC methods were implemented as the typical VC methods.\n\n#### Traditional VC method based on GMM\n- T. Toda, A.W. Black, K. Tokuda, \"Voice conversion based on maximum likelihood estimation of spectral parameter trajectory,\" IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 8, pp. 2222-2235, Nov. 2007.\n\n#### Vocoder-free VC method based on DIFFGMM\n- K. Kobayashi, T. Toda, S. Nakamura, \"F0 transformation techniques for statistical voice conversion with direct waveform modification with spectral differential,\" Proc. IEEE SLT, pp. 693-700, Dec. 2016.\n\n### Supply Python3 VC library\nTo make it possible to easily develop VC-based applications using Python (Python3), the VC library is also supplied, including several interfaces, such as acoustic feature analysis/synthesis, acoustic feature modeling, acoustic feature conversion, and waveform modification.\nFor the details of the VC library, please see sprocket documents in (coming soon).\n\n## Installation & Run\n\nPlease use NOT Python2 BUT Python3.\n\n### Current stable version\n\nVer. 0.18.1\n\n### Install sprocket\n\n```\npip install numpy==1.15.4 cython # for dependency\npip install sprocket-vc\n```\n\n### Run example\n\nSee [VC example](docs/vc_example.md)\n\n## REPORTING BUGS\n\nFor any questions or issues please visit:\n\n```\nhttps://github.com/k2kobayashi/sprocket/issues\n```\n\n## COPYRIGHT\n\nCopyright (c) 2017 Kazuhiro KOBAYASHI\n\nReleased under the MIT license\n\n[https://opensource.org/licenses/mit-license.php](https://opensource.org/licenses/mit-license.php)\n\n## ACKNOWLEDGEMENTS\nThank you [@r9y9](https://github.com/r9y9) and [@tats-u](https://github.com/tats-u) for lots of contributions and encouragement helps before release.\n\n## Who we are\n- Kazuhiro Kobayashi [@k2kobayashi](https://github.com/k2kobayashi) [maintainer, design and development]\n\n- [Tomoki Toda](https://sites.google.com/site/tomokitoda/) [advisor]\n\nChangelog\n=========\n\n0.18.3 (2019/04/24)\n------------------\n\n- Implement several functions for GMM-based VC and minor bugfix\n- #133\n- #132\n- #130\n- #127\n\n0.18 (2017/10/01)\n------------------\n\n - Release first ver.\n - Baseline system for [Voice Conversion Challenge 2018](http://www.vc-challenge.org/)\n\n\n", "description_content_type": "", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/k2kobayashi/sprocket", "keywords": "", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "sprocket-vc", "package_url": "https://pypi.org/project/sprocket-vc/", "platform": "", "project_url": "https://pypi.org/project/sprocket-vc/", "project_urls": { "Homepage": "https://github.com/k2kobayashi/sprocket" }, "release_url": "https://pypi.org/project/sprocket-vc/0.18.3/", "requires_dist": [ "scipy", "pysptk (>=0.1.7)", "scikit-learn", "scikit-image", "pyworld", "h5py", "dtw", "fastdtw", "pyyaml", "dtw-c", "docopt", "nose ; extra == 'develop'" ], "requires_python": ">=3.5", "summary": "Voice conversion software", "version": "0.18.3" }, "last_serial": 5180359, "releases": { "0.18.1": [ { "comment_text": "", "digests": { "md5": "05183ec3c5a202aff5708ab24edeb471", "sha256": "84edb512b6f618444f6e62876dafbee03e28eb75c321d1a34df673f468225dbc" }, "downloads": -1, "filename": "sprocket_vc-0.18.1-py3-none-any.whl", "has_sig": false, "md5_digest": "05183ec3c5a202aff5708ab24edeb471", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.5", "size": 26910, "upload_time": "2018-12-06T08:28:01", "url": "https://files.pythonhosted.org/packages/d2/89/c7a1bc3c02ebe98229476c557d7c72ebb41e5d58f2effd47a29849796d64/sprocket_vc-0.18.1-py3-none-any.whl" } ], "0.18.2": [ { "comment_text": "", "digests": { "md5": "4879a248972e6902b3aa810811b6f413", "sha256": "8173be10c42901fc63d49bee30c3d0c2fef53fb2917134d28ae5b088fad279dd" }, "downloads": -1, "filename": "sprocket_vc-0.18.2-py3-none-any.whl", "has_sig": false, "md5_digest": "4879a248972e6902b3aa810811b6f413", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.5", "size": 28692, "upload_time": "2018-12-25T04:52:00", "url": "https://files.pythonhosted.org/packages/91/ea/49b7fa0d66b7f96401e6e76d510413e9a8f6b33feea80a73312822413c57/sprocket_vc-0.18.2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "46410c3796c9c873cdf149c89722e171", "sha256": "010eb7a288eeaf478cb6677aafab1406ae418e36585e45386d5a7bcda50a3bc0" }, "downloads": -1, "filename": "sprocket-vc-0.18.2.tar.gz", "has_sig": false, "md5_digest": "46410c3796c9c873cdf149c89722e171", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 23216, "upload_time": "2018-12-25T04:52:02", "url": "https://files.pythonhosted.org/packages/e7/ec/47b75ab303589f33ff084e405eb9fb3a014d5354c78ab9cac1ae6983817d/sprocket-vc-0.18.2.tar.gz" } ], "0.18.3": [ { "comment_text": "", "digests": { "md5": "e86d3c1df58f30a108ac38bc5379359a", "sha256": "3f5023d1861528790dfe401538434a461589e664f04f3d5f68c0dcbdb9e6ec27" }, "downloads": -1, "filename": "sprocket_vc-0.18.3-py3-none-any.whl", "has_sig": false, "md5_digest": "e86d3c1df58f30a108ac38bc5379359a", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.5", "size": 30912, "upload_time": "2019-04-24T04:48:52", "url": "https://files.pythonhosted.org/packages/b6/cc/30a41b9a1e40328421701308e3eae0ba7373e1b87447147e992449cace5e/sprocket_vc-0.18.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "136dcfcfe688a6e0bc1c26faf893c2ba", "sha256": "35bfdbc62a63cc9a148512fa92926de8ed9f25f69d0937ba1214e1a68f3995ae" }, "downloads": -1, "filename": "sprocket-vc-0.18.3.tar.gz", "has_sig": false, "md5_digest": "136dcfcfe688a6e0bc1c26faf893c2ba", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 24063, "upload_time": "2019-04-24T04:48:54", "url": "https://files.pythonhosted.org/packages/5d/a6/f74b39b9e4ed89eaf0c60bc3148e8fd88ba5fb484a704714b7dd230872d8/sprocket-vc-0.18.3.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "e86d3c1df58f30a108ac38bc5379359a", "sha256": "3f5023d1861528790dfe401538434a461589e664f04f3d5f68c0dcbdb9e6ec27" }, "downloads": -1, "filename": "sprocket_vc-0.18.3-py3-none-any.whl", "has_sig": false, "md5_digest": "e86d3c1df58f30a108ac38bc5379359a", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.5", "size": 30912, "upload_time": "2019-04-24T04:48:52", "url": "https://files.pythonhosted.org/packages/b6/cc/30a41b9a1e40328421701308e3eae0ba7373e1b87447147e992449cace5e/sprocket_vc-0.18.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "136dcfcfe688a6e0bc1c26faf893c2ba", "sha256": "35bfdbc62a63cc9a148512fa92926de8ed9f25f69d0937ba1214e1a68f3995ae" }, "downloads": -1, "filename": "sprocket-vc-0.18.3.tar.gz", "has_sig": false, "md5_digest": "136dcfcfe688a6e0bc1c26faf893c2ba", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 24063, "upload_time": "2019-04-24T04:48:54", "url": "https://files.pythonhosted.org/packages/5d/a6/f74b39b9e4ed89eaf0c60bc3148e8fd88ba5fb484a704714b7dd230872d8/sprocket-vc-0.18.3.tar.gz" } ] }