©2003 Kåre Sjölander and Jonas Beskow
Introduction Download Documentation Links Forum
WaveSurfer user forum

FAQ  FAQ
Search  Search
Memberlist  Memberlist
Register  Register
Profile  Profile
Login  Login

Wavesurfer formant output format.

 
Post new topic   Reply to topic    www.speech.kth.se/wavesurfer Forum Index -> WaveSurfer
View previous topic :: View next topic  
Author Message
zak



Joined: 04 Sep 2002
Posts: 6
Location: UmeŚ

PostPosted: Wed Oct 29, 2003 10:39 pm    Post subject: Wavesurfer formant output format. Reply with quote

Hi,

I'm currently structuring a data set of child speech which will have to be manually marked on a number of levels, including information regarding the formant tracks. Since I haven't come across a set of parameters for the automatic formant tracker that works with child speech, I will need to have the opportunity to fix the tracks in the cases when they seem funny, and of course be able to save my corrections.

The problem is that it seems that the EMU database system suits my analysis needs aftre the markup has been done. This system seems to be able to read (as well as adjust) formant
tracks in the ESPS format, but not plain text format (which seems to be the available option in Wavesurfer).

I would, however, really like to use Wavesurfer when transcribing since it incorporates some really nice features (like waveform blowup) that will come in handy. So, it seems that I will have to find a way to be able to adjust formants in Wavesurfer and analyse them using EMU.

Does the forum have any suggestions on what to do? I do of course appriciate any help I can get!

/Fredrik Karlsson
Back to top
View users profile Send private message Visit posters website
kare



Joined: 16 Aug 2002
Posts: 371
Location: KTH, Centre for Speech Technology

PostPosted: Fri Oct 31, 2003 5:05 pm    Post subject: Reply with quote

If you have access to ESPS, you could try converting WaveSurfer's text files into ESPS binary files using the ESPS tool addfeahd, have to admit I haven't tested this idea though.
What are your analysis needs? (Just out ot curiousity)

KŚre
Back to top
View users profile Send private message Visit posters website
zak



Joined: 04 Sep 2002
Posts: 6
Location: UmeŚ

PostPosted: Sun Nov 02, 2003 4:33 pm    Post subject: Reply with quote

kare wrote:
If you have access to ESPS, you could try converting WaveSurfer's text files into ESPS binary files using the ESPS tool addfeahd, have to admit I haven't tested this idea though.
What are your analysis needs? (Just out ot curiousity)

KŚre


Regarding the formants, I really need as plausable transitions into the vowel and as accurate steady state frequency values as possible. The analysis need I refered to regarding the EMU speech database mainly concern extracting data to R. The EMU <-> R connection is just excellent.

In summary, my question is caused by the excellent features of WaveSurfer (such as the waveform blowup and possibility of multiple spectrogram displays) and the seemingly quite capable query ablilities of the EMU speech database.

/Fredrik
Back to top
View users profile Send private message Visit posters website
Display posts from previous:   
Post new topic   Reply to topic    www.speech.kth.se/wavesurfer Forum Index -> WaveSurfer All times are GMT + 1 Hour
Page 1 of 1

 
Jump to:  
You can post new topics in this forum
You can reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB 2.0.1 © 2001, 2002 phpBB Group