Re: speech database (Jont Allen )

Subject: Re: speech database From: Jont Allen <jontalle@xxxxxxxx> Date: Wed, 25 May 2016 05:22:54 -0600 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY> This is a multi-part message in MIME format. --------------030904050408080901080609 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: quoted-printable Dear Joe, You might look at the LDC "fletcher articulation" database https://www.ldc.upenn.edu/ if you want the specifics, ask. This has 20 talkers with about half of them saying all possible CV, VC=20 and CVC syllables. It is recorded in several different formats with different microphones=20 and conditions (isolated syllable and syllable with carrier phrase). You will find some examples on my website: http://auditorymodels.org/ Specifically these examples are at: http://auditorymodels.org/index.php/AuditoryModels/HomePage Here are some example sounds in carrier phrases: http://173.161.115.245/Private/phrases.zip Scroll down to: Interspeech 2013 Demos of /Cue-modified/ speech where you will find demos where I used some isolated CV sounds. Jont Allen On 05/24/2016 03:55 AM, Sollini, Joseph wrote: > > Dear list, > > I am looking for recommendations for speech databases of English=20 > speakers, containing male and female voices of different ages.=20=20 > Ideally the voices would cover large range of speakers with both a=20 > range of similar and dissimilar sounding speakers (i.e. across=20 > different pitch, vocal tract length, formant frequencies).=20=20 > Alternatively does anyone know of some realistic speech generation=20 > software that allows manipulation of these parameters and is suitable=20 > for generating large stimulus batteries? Basically I=E2=80=99m hoping to= have=20 > a database of speakers that allows me to (as much as possible)=20 > parametrise the characteristics of speakers voices. > > I have found a few potential databases and speech generation packages=20 > but I=E2=80=99d really love to know which ones people prefer (and to know= =20 > which ones I=E2=80=99ve missed). > > All help welcome! > > Joe > > Dr Joseph Sollini > > Post-doctoral researcher > > UCL Ear Institute > --------------030904050408080901080609 Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable <html> <head> <meta content=3D"text/html; charset=3Dutf-8" http-equiv=3D"Content-Type= "> </head> <body bgcolor=3D"#FFFFFF" text=3D"#000000"> Dear Joe, You might look at the LDC "fletcher articulation" database <a class=3D"moz-txt-link-freetext" href=3D"https://www.ldc.upenn.edu/">= https://www.ldc.upenn.edu/</a> if you want the specifics, ask. This has 20 talkers with about half of them saying all possible CV, VC and CVC syllables. It is recorded in several different formats with different microphones and conditions (isolated syllable and syllable with carrier phrase). You will find some examples on my website: <a class=3D"moz-txt-link-freetext" href=3D"http://auditorymodels.org/">= http://auditorymodels.org/</a> Specifically these examples are at: <a class=3D"moz-txt-link-freetext" href=3D"http://auditorymodels.org/in= dex.php/AuditoryModels/HomePage">http://auditorymodels.org/index.php/Audito= ryModels/HomePage</a> Here are some example sounds in carrier phrases: http://173.161.115.245/Private/phrases.zip [ 173.161.115.245/Private/phrases.zip ]  Scroll down to: <h3>Interspeech 2013 Demos of Cue-modified speech</h3> where you will find demos where I used some isolated CV sounds. Jont Allen <div class=3D"moz-cite-prefix">On 05/24/2016 03:55 AM, Sollini, Joseph wrote: </div> <blockquote cite=3D"mid:12277_1464149215_574524DF_12277_313_3_VI1PR0101MB2221B4796CA0E6= C094E27BDEAA4F0@xxxxxxxx" type=3D"cite"> <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dutf= -8"> <meta name=3D"Generator" content=3D"Microsoft Word 15 (filtered medium)"> <style></style> <div class=3D"WordSection1"> Dear list,<o:p></o:p> <o:p>=C2=A0</o:p> I am looking for recommendations for speech databases of English speakers, containing male and female voices of different ages.=C2=A0 Ideally the voices would cover large range of speakers with both a range of similar and dissimilar sounding speakers (i.e. across different pitch, vocal tract length, formant frequencies).=C2=A0 Alternatively does anyone know of some realistic speech generation software that allows manipulation of these parameters and is suitable for generating large stimulus batteries?=C2=A0 Basically I=E2=80=99m = hoping to have a database of speakers that allows me to (as much as possible) parametrise the characteristics of speakers voices.<o:p= ></o:p> <o:p>=C2=A0</o:p> I have found a few potential databases and speech generation packages but I=E2=80=99d really love to know wh= ich ones people prefer (and to know which ones I=E2=80=99ve missed).<= o:p></o:p> <o:p>=C2=A0</o:p> All help welcome! <o:p></o:p> <o:p>=C2=A0</o:p> Joe<o:p></o:p> <o:p>=C2=A0</o:p> <div style=3D"mso-element:para-border-div;border:none;border-bottom:so= lid windowtext 3.0pt;padding:0cm 0cm 1.0pt 0cm"> <o:p>=C2=A0</o:p>= </div> <= o:p>=C2=A0</o:p> Dr Joseph Sollini<o:p></o:p> P= ost-doctoral researcher<o:p></o:p> U= CL Ear Institute<o:p></o:p> <div style=3D"mso-element:para-border-div;border:none;border-bottom:so= lid windowtext 3.0pt;padding:0cm 0cm 1.0pt 0cm"> <o:p>=C2=A0</o:p>= </div> <o:p>=C2=A0</o:p> </div> </blockquote> </body> </html> --------------030904050408080901080609--

This message came from the mail archive
/var/www/html/postings/2016/
maintained by:

DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University