* [[Extensions]] [#nd224010]
 Some of HTS users have implemented substantial extensions to HTS. On this page we provide short descriptions and links to further information.  Many thanks to the authors of these extensions.
 If you provide some free extension to HTS for download and would like to see it listed on this page, please contact [[us>Contact]].
 ** AndroidMaryTTS [#nc1fb250]
 > An open-source, offline HMM-Based text-to-speech synthesis system based on MaryTTS. Please visit [[this page>https://github.com/AndroidMaryTTS]].
 > Fariz Aghayev, Rashad Amirjanov
 ** MRHSMM patch and demo [#s92103b2]
 > This is the patch for MRHSMM (Multiple Regression HSMM) and its demo scripts. English emotional speech can be synthesized and the strength can be controlled by HRHSMM.
 Please, visit [[this page>https://www.inf.ed.ac.uk/research/isdd/admin/package?view=1&id=183]].
 > Oliver Watts
 ** SALB framework [#k9c24259]
 > The framework provides a front-end to hts_engine API through SAPI5. A free German HTS voice is included. Please, visit [[this page>http://m-toman.github.io/SALB/]].
 > Markus Toman, Michael Pucher, Dietmar Schabus, Junichi Yamagishi, Cassia Valentini-Botinhao
 ** HTS_PDFparser [#zbb907c1]
 > This is a parser for [[hts_engine API>http://hts-engine.sourceforge.net/]] model pdf file. Please, visit [[this page>https://github.com/naxingyu/HTS_PDFparser/]].
 > [[Xingyu Na>http://commlab.bit.edu.cn/staff/xna/]]
 ** StreamGenerator [#u460f5ca]
 > This is an HMM-based Single Stream Parameter Generator. Please, visit [[this page>https://github.com/naxingyu/StreamGenerator/]].
 > [[Xingyu Na>http://commlab.bit.edu.cn/staff/xna/]]
 ** HTS-based reactive speech synthesis engine pHTS/MAGE [#he1530b1]
 > This is the customized version of the HMM-based speech synthesis engine, [[hts_engine API>http://hts-engine.sourceforge.net/]]. Please, visit [[this page>http://mage.numediart.org/]].
 > [[Maria Astrinaki>http://tcts.fpms.ac.be/~astrinaki/]], Geoffrey Wilfart, [[Alexis Moinet>http://www.tcts.fpms.ac.be/~moinet/]], [[Nicolas d'Alessandro>http://www.nicolasdalessandro.net/]] and [[Thierry Dutoit>http://tcts.fpms.ac.be/~dutoit/]]
 ** Demo scripts with MGE option [#u9e61c9e]
 > [[This scripts>https://github.com/naxingyu/MGEtraining]] support MGE training for [[HTS-demo_CMU-ARCTIC-SLT_STRAIGHT (ver.2.2):http://hts.sp.nitech.ac.jp/archives/2.2/HTS-demo_CMU-ARCTIC-SLT_STRAIGHT.tar.bz2]].
 > [[Xingyu Na>http://www.idiap.ch/~xna/]]
 ** EM VTLN adaptation [#bdbee5e8]
 This allows VTLN adaptation within the context of HTS. This code will include the possibility to perform VTLN adaptation as a global warping of the spectrum using base classes and also as multiple warping parameters for different phoneme classes using regression trees (similar to CMLLR adaptation). Please visit [[this page>http://www.idiap.ch/scientific-research/resources/hts-vtln]].
 > [[Lakshmi Saheer>http://publications.idiap.ch/index.php/authors/show/773]]
 ** DFKI MARY [#sa03ffda]
 > [[DFKI MARY speech synthesis system:http://mary.opendfki.de/]] provides voice import tools for creating your own HMM-based voices for MARY.  It uses versions of the speaker dependent and adaptive demo scripts provided by HTS adapted to the MARY platform.  For details, please see [[tutorial:http://mary.opendfki.de/wiki/HMMVoiceCreation]].
 > [[Marc Schroeder:http://www.dfki.de/~schroed/]]
 ** Multi-process supporting patch for HTS-demo_CMU-ARCTIC-SLT [#ke48fc2d]
 > This patch uses JM command of HHEd in HTS-2.1 to provide an option for clustering in parallel. In a training environment with multi-core CPUs, the clustering time of HHEd could be generally reduced. The patch is applied to [[HTS-demo_CMU-ARCTIC-SLT (ver.2.1):http://hts.sp.nitech.ac.jp/archives/2.1/HTS-demo_CMU-ARCTIC-SLT.tar.bz2]] only.  Please visit [[this page:http://yaoxuchen.googlepages.com/scriptpatchhts]].
 > [[Xuchen Yao:http://yaoxuchen.googlepages.com/xuchen_en]] and Feng Ding
 ** Open-Source LVCSR Engine Julius [#ua7a8722]
 > The open-source LVCSR engine [[Julius:http://julius.sourceforge.jp/en_index.php?q=index-en.html]] now supports '''multi-stream HMMs with stream-depdendent parameter tying structure''' and '''multi-space probability distribution HMMs (MSD-HMMs)''' built by HTS.  You can use acoustic models trained by HTS directly.  Please check [[announce:http://julius.sourceforge.jp/forum/viewtopic.php?f=2&t=62]] and [[update:http://julius.sourceforge.jp/forum/viewtopic.php?f=9&t=60#p181]] pages on the Julius user forum for details.
 > [[Akinobu Lee:http://www.sp.nitech.ac.jp/~ri/index.html.en]]
 ** Prototype definition modification for HTK compatibility [#z8abcc39]
 > Due to the different format of the prototypes used by HTS and HTK, the demo for testing for a successful installation provided on the HTK website will not work with the HTS extension added.
 With the modification made in [[this>http://www.wushido.com/hmm/downloads.php]], HTKDemo will run correctly with the HTS extension.
 This will enable users who are installing HTS to determine if they have installed everything correctly.
 > Gavin Potter

Front page   Edit Diff Backup Upload Copy Rename Reload   New List of pages Search Recent changes   Help   RSS of recent changes