Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
MBROLA based American English female voice for the festival speech
synthesis system. This voice provides a American English female voice using the MBROLA synthesis method. It uses a modified CMU lexicon for pronunciations. Prosodic phrasing is provided by a statistically trained model using part of speech and local distribution of breaks. Intonation is provided by a CART tree predicting ToBI accents and an F0 contour generated from a model trained from natural speech. The duration model is also trained from data using a CART tree. This voice can be activated via (voice_us1_mbrola) -Julian Assange <proff@iq.org> wq
- Loading branch information
proff
committed
Oct 11, 1999
1 parent
55b5cc2
commit 7a5fed2
Showing
5 changed files
with
62 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,35 @@ | ||
# $NetBSD: Makefile,v 1.1.1.1 1999/10/11 16:00:02 proff Exp $ | ||
|
||
DISTNAME= festvox_us1 | ||
PKGNAME= festvox-us1-1.4.0 | ||
WRKSRC= ${WRKDIR}/festival | ||
CATEGORIES= audio | ||
MASTER_SITES= ftp://ftp.cstr.ed.ac.uk/pub/festival/1.4.0/ | ||
|
||
MAINTAINER= proff@iq.org | ||
HOMEPAGE= http://www.cstr.ed.ac.uk/projects/festival.html | ||
|
||
DEPENDS+= festival-1.4.0:../festival \ | ||
festlex-poslex-1.4.0:../festlex-poslex \ | ||
festlex-cmu-1.4.0:../festlex-cmu \ | ||
mbrola-301h:../mbrola \ | ||
mbrolavox-us1-980512:../mbrolavox-us1 | ||
|
||
LICENSE= no-commercial-use | ||
|
||
NO_BUILD= yes | ||
|
||
FHOME= ${PREFIX}/share/festival | ||
MBROLA= ${FHOME}/lib/voices/english/us1_mbrola | ||
|
||
post-extract: | ||
@ chmod -R a+r ${WRKSRC} | ||
@ find ${WRKSRC} -type d -print0 | xargs -0 chmod 755 | ||
|
||
do-install: | ||
cd ${WRKSRC} && pax -r -w * ${FHOME} | ||
#ugh | ||
ln -fs ../../../../../mbrola/voices/us1 ${MBROLA} | ||
ln -fs ../../../../../mbrola/voices/us1/us1mrpa ${MBROLA} | ||
|
||
.include "../../mk/bsd.pkg.mk" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
$NetBSD: md5,v 1.1.1.1 1999/10/11 16:00:02 proff Exp $ | ||
|
||
MD5 (festvox_us1.tar.gz) = d0c3e727003e715a65daf01003101813 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
MBROLA based American English female male voice for festival |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,14 @@ | ||
MBROLA based American English female voice for the festival speech | ||
synthesis system. | ||
|
||
This voice provides a American English female voice using the MBROLA | ||
synthesis method. It uses a modified CMU lexicon for pronunciations. | ||
Prosodic phrasing is provided by a statistically trained model using | ||
part of speech and local distribution of breaks. Intonation is | ||
provided by a CART tree predicting ToBI accents and an F0 contour | ||
generated from a model trained from natural speech. The duration | ||
model is also trained from data using a CART tree. | ||
|
||
This voice can be activated via (voice_us1_mbrola) | ||
|
||
-Julian Assange <proff@iq.org> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,9 @@ | ||
@comment $NetBSD: PLIST,v 1.1.1.1 1999/10/11 16:00:02 proff Exp $ | ||
@comment the next two entries are symlinks | ||
share/festival/lib/voices/english/us1_mbrola/us1 | ||
share/festival/lib/voices/english/us1_mbrola/us1mrpa | ||
share/festival/lib/voices/english/us1_mbrola/usradio | ||
share/festival/lib/voices/english/us1_mbrola/festvox/us1_mbrola.scm | ||
share/festival/lib/voices/english/us1_mbrola/festvox/usdurtreeZ.scm | ||
@dirrm share/festival/lib/voices/english/us1_mbrola/festvox | ||
@dirrm share/festival/lib/voices/english/us1_mbrola |