Subject: [AUDITORY] COVAREP - Call for contributions From: Gilles Degottex <gilles.degottex@xxxxxxxx> Date: Mon, 29 Jul 2013 16:45:46 +0300 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>--e89a8f643358a5b79504e2a6b5da Content-Type: text/plain; charset=ISO-8859-1 ====================== CALL for contributions ====================== We are pleased to announce the creation of an open-source repository of advanced speech processing algorithms called COVAREP (A Cooperative Voice Analysis Repository for Speech Technologies). COVAREP has been created as a GitHub project (https://github.com/covarep/covarep) where researchers in speech processing can store original implementations of published algorithms. Over the past few decades a vast array of advanced speech processing algorithms have been developed, often offering significant improvements over the existing state-of-the-art. Such algorithms can have a reasonably high degree of complexity and, hence, can be difficult to accurately re-implement based on article descriptions. Another issue is the so-called 'bug magnet effect' with re-implementations frequently having significant differences from the original. The consequence of all this has been that many promising developments have been under-exploited or discarded, with researchers tending to stick to conventional analysis methods. By developing the COVAREP repository we are hoping to address this by encouraging authors to include original implementations of their algorithms, thus resulting in a single *de facto* version for the speech community to refer to. We envisage a range of benefits to the repository: 1) *Reproducible research:* COVAREP will allow fairer comparison of algorithms in published articles. 2) *Encouraged usage:* the free availability of these algorithms will encourage researchers from a wide range of speech-related disciplines (both in academia and industry) to exploit them for their own applications. 3) *Feedback:* as a GitHub project users will be able to offer comments on algorithms, report bugs, suggest improvements etc. *SCOPE* We welcome contributions from a wide range of speech processing areas, including (but not limited to): Speech analysis, synthesis, conversion, transformation, enhancement, speech quality, glottal source/voice quality analysis, etc. *REQUIREMENTS* In order to achieve a reasonable standard of consistency and homogeneity across algorithms we have compiled a list of requirements for prospective contributors to the repository. However, we intend the list of the requirements not to be so strict as to discourage contributions. - Only published work can be added to the repository - The code must be available as open source - Algorithms should be coded in Matlab, however we strongly encourage authors to make the code compatible with Octave in order to maximize usability - Contributions have to comply with a Coding Convention (see GitHub site for coding convention and template). However, only for normalizing the inputs/outputs and the documentation. There is no restriction for the content of the functions (though, comments are obviously encouraged). *LICENCE* Getting contributing institutions to agree to a homogenous IP policy would be close to impossible. As a result COVAREP is a repository and not a toolbox, and each algorithm will have its own licence associated with it. Though flexible to different licence types, contributions will need to have a licence which is compatible with the repository, i.e. {GPL, LGPL, X11, Apache, MIT} or similar. We would encourage contributors to try to obtain LGPL licences from their institutions in order to be more industry friendly. *CONTRIBUTE!* We believe that the COVAREP repository has a great potential benefit to the speech research community and we hope that you will consider contributing your published algorithms to it. If you have any questions, comments issues etc regarding COVAREP please contact us on one of the email addresses below. Please forward this email to others who may be interested. Existing contributions include: algorithms for spectral envelope modelling, adaptive sinusoidal modelling, fundamental frequncy/voicing decision/glottal closure instant detection algorithms, methods for detecting non-modal phonation types etc. Gilles Degottex <degottex@xxxxxxxx>, John Kane <kanejo@xxxxxxxx>, Thomas Drugman <thomas.drugman@xxxxxxxx>, Tuomo Raitio <tuomo.raitio@xxxxxxxx>, Stefan Scherer <scherer@xxxxxxxx> *Website* - http://covarep.github.io/covarep *GitHub* - https://github.com/covarep/covarep --e89a8f643358a5b79504e2a6b5da Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr"><div style=3D"font-family:arial,sans-serif;font-size:12.80= 0000190734863px">=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D</div><div style=3D"font-family:arial,sans-serif;font-size:12.8000= 00190734863px">CALL for contributions</div><div style=3D"font-family:arial,= sans-serif;font-size:12.800000190734863px"> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D</div><di= v style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px"><br= ></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190734= 863px">We are pleased to announce the creation of an open-source repository= of advanced speech processing algorithms called COVAREP (A Cooperative Voi= ce Analysis Repository for Speech Technologies). COVAREP has been created a= s a GitHub project (<a href=3D"https://github.com/covarep/covarep" target= =3D"_blank">https://github.com/covarep/covarep</a>) where researchers in sp= eech processing can store original implementations of published algorithms.= </div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px">Over the past few decades a vast array of advanced speech process= ing algorithms have been developed, often offering significant improvements= over the existing state-of-the-art. Such algorithms can have a reasonably = high degree of complexity and, hence, can be difficult to accurately re-imp= lement based on article descriptions. Another issue is the so-called 'b= ug magnet effect' with re-implementations frequently having significant= differences from the original. The consequence of all this has been that m= any promising developments have been under-exploited or discarded, with res= earchers tending to stick to conventional analysis methods.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px">By developing the COVAREP repository we are hoping to address thi= s by encouraging authors to include original implementations of their algor= ithms, thus resulting in a single=A0<i>de facto</i>=A0version for the speec= h community to refer to.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px">We envisage a range of benefits to the repository:</div><div styl= e=3D"font-family:arial,sans-serif;font-size:12.800000190734863px"> 1)=A0<b>Reproducible research:</b>=A0COVAREP will allow fairer comparison o= f algorithms in published articles.</div><div style=3D"font-family:arial,sa= ns-serif;font-size:12.800000190734863px">2)=A0<b>Encouraged usage:</b>=A0th= e free availability of these algorithms will encourage researchers from a w= ide range of speech-related disciplines (both in academia and industry) to = exploit them for their own applications.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= 3)=A0<b>Feedback:</b>=A0as a GitHub project users will be able to offer com= ments on algorithms, report bugs, suggest improvements etc.</div><div style= =3D"font-family:arial,sans-serif;font-size:12.800000190734863px"> <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px"><b>SCOPE</b></div><div style=3D"font-family:arial,sans-serif;font= -size:12.800000190734863px">We welcome contributions from a wide range of s= peech processing areas, including (but not limited to): Speech analysis, sy= nthesis, conversion, transformation, enhancement, speech quality, glottal s= ource/voice quality analysis, etc.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px"><b>REQUIREMENTS</b></div><div style=3D"font-family:arial,sans-ser= if;font-size:12.800000190734863px"> In order to achieve a reasonable standard of consistency and homogeneity ac= ross algorithms we have compiled a list of requirements for prospective con= tributors to the repository. However, we intend the list of the requirement= s not to be so strict as to discourage contributions.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <ul><li style=3D"margin-left:15px">Only published work can be added to the = repository<br></li><li style=3D"margin-left:15px">The code must be availabl= e as open source<br> </li><li style=3D"margin-left:15px">Algorithms should be coded in Matlab, h= owever we strongly encourage authors to make the code compatible with Octav= e in order to maximize usability<br></li><li style=3D"margin-left:15px">Con= tributions have to comply with a Coding Convention (see GitHub site for cod= ing convention and template). However, only for normalizing the inputs/outp= uts and the documentation. There is no restriction for the content of the f= unctions (though, comments are obviously encouraged).<br> </li></ul></div><div style=3D"font-family:arial,sans-serif;font-size:12.800= 000190734863px"><br></div><div style=3D"font-family:arial,sans-serif;font-s= ize:12.800000190734863px"><b>LICENCE</b></div><div style=3D"font-family:ari= al,sans-serif;font-size:12.800000190734863px"> Getting contributing institutions to agree to a homogenous IP policy would = be close to impossible. As a result COVAREP is a repository and not a toolb= ox, and each algorithm will have its own licence associated with it. Though= flexible to different licence types, contributions will need to have a lic= ence which is compatible with the repository, i.e. {GPL, LGPL, X11, Apache,= MIT} or similar. We would encourage contributors to try to obtain LGPL lic= ences from their institutions in order to be more industry friendly.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px"><b>CONTRIBUTE!</b></div><div style=3D"font-family:arial,sans-seri= f;font-size:12.800000190734863px"> We believe that the COVAREP repository has a great potential benefit to the= speech research community and we hope that you will consider contributing = your published algorithms to it. If you have any questions, comments issues= etc regarding COVAREP please contact us on one of the email addresses belo= w. Please forward this email to others who may be interested.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px">Existing contributions include: algorithms for spectral envelope = modelling, adaptive sinusoidal modelling, fundamental frequncy/voicing deci= sion/glottal closure instant detection algorithms, methods for detecting no= n-modal phonation types etc.</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px">Gilles Degottex <<a href=3D"mailto:degottex@xxxxxxxx" target= =3D"_blank">degottex@xxxxxxxx</a>>, John Kane <<a href=3D"mailto:ka= nejo@xxxxxxxx" target=3D"_blank">kanejo@xxxxxxxx</a>>, Thomas Drugman <<a= href=3D"mailto:thomas.drugman@xxxxxxxx" target=3D"_blank">thomas.drugma= n@xxxxxxxx</a>>, Tuomo Raitio <<a href=3D"mailto:tuomo.raitio@xxxxxxxx= o.fi" target=3D"_blank">tuomo.raitio@xxxxxxxx</a>>, Stefan Scherer <<= a href=3D"mailto:scherer@xxxxxxxx" target=3D"_blank">scherer@xxxxxxxx= </a>></div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <br></div><div style=3D"font-family:arial,sans-serif;font-size:12.800000190= 734863px"><b>Website</b>=A0-=A0<a href=3D"http://covarep.github.io/covarep"= target=3D"_blank">http://covarep.github.io/covarep</a>=A0</div> <div style=3D"font-family:arial,sans-serif;font-size:12.800000190734863px">= <b>GitHub</b>=A0=A0-=A0<a href=3D"https://github.com/covarep/covarep" targe= t=3D"_blank">https://github.com/covarep/covarep</a></div><div style=3D"font= -family:arial,sans-serif;font-size:12.800000190734863px"> <br></div></div> --e89a8f643358a5b79504e2a6b5da--