[prev in list] [next in list] [prev in thread] [next in thread] 

List:       festival-talk
Subject:    FT: Output speed of Festival 1.4.2 slows down unexpectedly
From:       Alan W Black <awb () cs ! cmu ! edu>
Date:       2003-11-27 16:25:50
[Download RAW message or body]

message from Alan W Black <awb@cs.cmu.edu> to festival-talk
= = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =


 Piklu Gupta writes on 27 November 2003:
 > Hi there,
 > we are using festival in client-server mode to read an English  web page
 > aloud. We have, however, encountered a problem once the text of the page,
 > stripped of its tags by a shell script is output as a wav file. The file is
 > about a minute in duration but halfway through playback it begins to become
 > slower and the pitch lowers accordingly. The text is relatively short, and
 > would most likely cause Festival no problems in interactive mode. We have
 > increased the heap size but this has made no difference. I'd be grateful for
 > any explanations/possible solutions.

Not sure what could cause this, if the input is being treat as a
very long single sentence (as a single utterances) the pitch 
can drop to a low level and sit there at a monotone.  Though I've
not heard it slowing down.

Using the festival_client standalone program you can ensure you 
don't get things a single utterance is you use --async and --ttw
but you'll get (potentiall) multiple waveform files sent back as they
are synthesized.

festival_client --async --ttw --aucommand 'na_play $FILE' fred.txt

If this doesn't help can you point me at the some text and an example
waveform that is being generate and I might be able to trace this
further.

Alan


 >  
 > 
 > Best wishes
 > 
 >  
 > 
 > Piklu
 > 
 >  
 > 
 >  
 > 
 > --
 > 
 > Dr. Piklu Gupta
 > 
 > Fraunhofer IPSI
 > 
 > Dolivostr. 15
 > 
 > D-64293 Darmstadt
 > 
 > gupta@ipsi.fraunhofer.de
 > 
 >  
 > 
 > <html>
 > 
 > <head>
 > <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
 > 
 > 
 > <meta name=Generator content="Microsoft Word 10 (filtered)">
 > 
 > <style>
 > <!--
 >  /* Style Definitions */
 >  p.MsoNormal, li.MsoNormal, div.MsoNormal
 > 	{margin:0cm;
 > 	margin-bottom:.0001pt;
 > 	font-size:12.0pt;
 > 	font-family:"Times New Roman";}
 > a:link, span.MsoHyperlink
 > 	{color:blue;
 > 	text-decoration:underline;}
 > a:visited, span.MsoHyperlinkFollowed
 > 	{color:purple;
 > 	text-decoration:underline;}
 > span.EmailStyle17
 > 	{font-family:Arial;
 > 	color:windowtext;}
 > @page Section1
 > 	{size:595.3pt 841.9pt;
 > 	margin:70.85pt 70.85pt 2.0cm 70.85pt;}
 > div.Section1
 > 	{page:Section1;}
 > -->
 > </style>
 > 
 > </head>
 > 
 > <body lang=DE link=blue vlink=purple>
 > 
 > <div class=Section1>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>Hi there,</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>&nbsp;</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>we are using festival in client-server mode to read
 > an English &nbsp;web page aloud. We have, however, encountered a problem once
 > the text of the page, stripped of its tags by a shell script is output as a wav
 > file. The file is about a minute in duration but halfway through playback it
 > begins to become slower and the pitch lowers accordingly. The text is
 > relatively short, and would most likely cause Festival no problems in
 > interactive mode. We have increased the heap size but this has made no difference.
 > I&#8217;d be grateful for any explanations/possible solutions.</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>&nbsp;</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>Best wishes</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>&nbsp;</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>Piklu</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>&nbsp;</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span lang=EN-GB style='font-size:
 > 10.0pt;font-family:Arial'>&nbsp;</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span style='font-size:10.0pt;
 > font-family:Arial'>--</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span style='font-size:10.0pt;
 > font-family:Arial'>Dr. Piklu Gupta</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span style='font-size:10.0pt;
 > font-family:Arial'>Fraunhofer IPSI</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span style='font-size:10.0pt;
 > font-family:Arial'>Dolivostr. 15</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span style='font-size:10.0pt;
 > font-family:Arial'>D-64293 Darmstadt</span></font></p>
 > 
 > <p class=MsoNormal><font size=2 face=Arial><span style='font-size:10.0pt;
 > font-family:Arial'>gupta@ipsi.fraunhofer.de</span></font></p>
 > 
 > <p class=MsoNormal><font size=3 face="Times New Roman"><span style='font-size:
 > 12.0pt'>&nbsp;</span></font></p>
 > 
 > </div>
 > 
 > </body>
 > 
 > </html>

= = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
			       Sent Via festival-talk@cstr.ed.ac.uk
		        To unsubscribe mail majordomo@cstr.ed.ac.uk
[prev in list] [next in list] [prev in thread] [next in thread] 

Configure | About | News | Add a list | Sponsored by KoreLogic