Login or Register to Ask a Question and Join Our Community


UNIX and Linux Applications

Change voice in festival

Login to Discuss or Reply to this Discussion in Our Community

 
Thread Tools Search this Thread
Special Forums UNIX and Linux Applications Change voice in festival
# 1  
Old 09-19-2011
Change voice in festival
I installed festival under /opt/TTS so presume that precedes in the following unless noted otherwise.
I examined festival/lib/siteinit.scm and found the default voice was: voice_cmu_us_awb_arctic_hts (which I did not include with the install) which doesn't matter because the lin is commented out.
The install included
festvox_cmu_us_rms_cg.tar.gz
festvox_cmu_us_slt_arctic_hts.tar.gz and
festvox_kallpc16k.tar.gz
which are American Male using clustergen, American Female, HTS, and American English Male residual LPC diphone, I think.
I found a recent source saying to modify siteinit.scm second to last line to change the voice (...awb_arctic above ) with what was in voices but what is there is:
festival/lib/voices/english/kal_diphone
and under that are nothing like voice_... (I just show english/...)
Hence, I need to know how to change between the voices in version 2.1. Is there someone that can help out there?
BTW yes it is working but I am unfamiliar with the vocal output and cannot tell from where the male voice is coming.
Login or Register to Ask a Question

Previous Thread | Next Thread

5 More Discussions You Might Find Interesting

1. What is on Your Mind?

Place Your Bits! - Who Will Win The Voice Season 3

New Event for Fans of The Voice Who Will Win The Voice Season 3 Place Your Bits! Wikipedia Reference Page (0 Replies)
Discussion started by: Neo
0 Replies

2. UNIX and Linux Applications

Festival halting

I finally got festival text 2 speech to work. I followed a set of instructions but had to make edits to set it up to work (albeit a few warnings). At the end I tried using quit with double quotes inside parentheses and without but could not stop the program (i.e. comes back with "festival>"). ... (0 Replies)
Discussion started by: slak0
0 Replies

3. Ubuntu

Voice plugin not working!

Hi, I am using Ubuntu 10.04. I installed Google talk voice and video plug-in. But audio is not working for me and video is working fine. So can I do some tweaking to enable it again? Note that I have just Mozilla Firefox with me (0 Replies)
Discussion started by: nixhead
0 Replies

4. Ubuntu

My Google voice plugin problem.

I am encountering problem in Google microphone while voice chat. Voice input is almost no, although I've installed Adobe flash plugin. Please Help! (0 Replies)
Discussion started by: nixhead
0 Replies

5. UNIX for Dummies Questions & Answers

how to fork voice wid text???

hello... i am working in LINUX on a client/server voice communication project!!! so far i am done wid compiling code for reading/playin sound card and also sending text from server to client. now i need ur help in using fork() though i do have basic concept about fork but i need detail help in... (0 Replies)
Discussion started by: TAM
0 Replies
Login or Register to Ask a Question

LEARN ABOUT CENTOS

festival_client

FESTIVAL(1)						      General Commands Manual						       FESTIVAL(1)

NAME

       festival_client - client access to festiva; text-to-speech server mode

SYNOPSIS

       festival_client [options] [file0] [file1] ...

DESCRIPTION

       Allows sending commands and/or test to a festival test-to-speech server.  Festival may be started in server mode using the option --server

       festival-clinet	allows waveforms ot be generated faster as not time is required for start up.  See the festival manual for more details on
       recommended use.

OPTIONS

       --server <string>
	       hostname (or IP number) of server

       --port <int> {1314}
	       port number of server process (1314)

       --output <string>
	       file to save output waveform to

       --otype <string> {riff}
	       output type for waveform

       --passwd <string>
	       server passwd in plain text (optional)

       --prolog <string>
	       filename containing commands to be sent to the server before standard commands (useful when using --ttw)

       --async Asynchronous mode, server may send back multiple waveforms per text file

       --ttw   Text to waveform: take text from first arg or stdin get server to return waveform(s) stored in output or operated on by aucommand.

       --withlisp
	       Output lisp replies from server.

       --tts_mode <string>
	       TTS mode for file (default is fundamental).

       --aucommand <string>
	       command to be applied to each waveform retruned from server. Use $FILE in string to refer to waveform file

BUGS

       This still isn't as general as it should be.  It seems to require lots of special little options which suggests the general options  aren't
       right.

AUTHOR

       Alan W Black and Paul Taylor
       (C) Centre for Speech Technology Research
       University of Edinburgh
       80 South Bridge
       Edinburgh EH1 1HN
       http://www.cstr.ed.ac.uk/projects/festival.html

								   1st Aug 1997 						       FESTIVAL(1)