Subject: Re: [AUDITORY] Phoneme database From: Kamil Adiloglu <kamil.adiloglu@xxxxxxxx> Date: Thu, 31 Oct 2013 10:09:35 +0100 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>--089e0141aa04076ee704ea05cfce Content-Type: text/plain; charset=ISO-8859-1 Dear Giampiero, thank you for your reply. I would rather like to have the second case of course. And this is what I had in mind what you've suggested, in case that I cannot find an already isolated one. But there are still those two databases (Oxford and USF). I don't know how they made the recordings. In particular the one from USF seems to have visual info as well. Best Regards Kamil On Thu, Oct 31, 2013 at 9:58 AM, Giampiero Salvi <giampi@xxxxxxxx> wrote: > Dear Kamil, > what do you mean exactly with "isolated phoneme database"? Do you mean > phonemes spoken in isolation, or a database with files each containing > a phone extracted from continuous speech recordings? > > In the first case, the models you train won't be of much use for ASR: > due to coarticulation, the actual sounds (phones) you will find in > speech will differ greatly from your isolated phoneme recordings. > > In the second case, you could generate such database from TIMIT with a > script. > > Best regards > Giampiero > > On 31 October 2013 09:39, Kamil Adiloglu <kamil.adiloglu@xxxxxxxx> wrote: > > Dear list, > > I am looking for a phoneme database to train a supervised machine > learning > > method for ASR. There is the well-known TIMIT database, which contains > the > > phoneme labels for each recording, but an isolated phoneme database > would be > > much better for me. I also found some websites mentioning the Oxford > > Acoustic Phonetic Database or the University of South Florida Audiovisual > > Phone Database, but no clue about how to find the databases themselves. > Any > > help would be highly appreciated. > > > > Best Regards > > Kamil Adiloglu > > > > > > -- > Giampiero Salvi > Associate Professor > KTH, School of Computer Science and Communication > http://www.speech.kth.se/~giampi > --089e0141aa04076ee704ea05cfce Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr"><div><div>Dear Giampiero,<br></div>thank you for your repl= y. I would rather like to have the second case of course. And this is what = I had in mind what you've suggested, in case that I cannot find an alre= ady isolated one. But there are still those two databases (Oxford and USF).= I don't know how they made the recordings. In particular the one from = USF seems to have visual info as well.<br> <br></div>Best Regards<br>Kamil<br></div><div class=3D"gmail_extra"><br><br= ><div class=3D"gmail_quote">On Thu, Oct 31, 2013 at 9:58 AM, Giampiero Salv= i <span dir=3D"ltr"><<a href=3D"mailto:giampi@xxxxxxxx" target=3D"_blank">= giampi@xxxxxxxx</a>></span> wrote:<br> <blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1p= x #ccc solid;padding-left:1ex">Dear Kamil,<br> what do you mean exactly with "isolated phoneme database"? Do you= mean<br> phonemes spoken in isolation, or a database with files each containing<br> a phone extracted from continuous speech recordings?<br> <br> In the first case, the models you train won't be of much use for ASR:<b= r> due to coarticulation, the actual sounds (phones) you will find in<br> speech will differ greatly from your isolated phoneme recordings.<br> <br> In the second case, you could generate such database from TIMIT with a scri= pt.<br> <br> Best regards<br> Giampiero<br> <div class=3D"HOEnZb"><div class=3D"h5"><br> On 31 October 2013 09:39, Kamil Adiloglu <<a href=3D"mailto:kamil.adilog= lu@xxxxxxxx">kamil.adiloglu@xxxxxxxx</a>> wrote:<br> > Dear list,<br> > I am looking for a phoneme database to train a supervised machine lear= ning<br> > method for ASR. There is the well-known TIMIT database, which contains= the<br> > phoneme labels for each recording, but an isolated phoneme database wo= uld be<br> > much better for me. I also found some websites mentioning =A0the Oxfor= d<br> > Acoustic Phonetic Database or the University of South Florida Audiovis= ual<br> > Phone Database, but no clue about how to find the databases themselves= . Any<br> > help would be highly appreciated.<br> ><br> > Best Regards<br> > Kamil Adiloglu<br> ><br> <br> <br> <br> </div></div><span class=3D"HOEnZb"><font color=3D"#888888">--<br> Giampiero Salvi<br> Associate Professor<br> KTH, School of Computer Science and Communication<br> <a href=3D"http://www.speech.kth.se/~giampi" target=3D"_blank">http://www.s= peech.kth.se/~giampi</a><br> </font></span></blockquote></div><br></div> --089e0141aa04076ee704ea05cfce--