diff options
| author | proff <proff@pkgsrc.org> | 1999-10-11 16:44:40 +0000 |
|---|---|---|
| committer | proff <proff@pkgsrc.org> | 1999-10-11 16:44:40 +0000 |
| commit | b70f353883887c30fb452aac44746aba8bfdd2ee (patch) | |
| tree | e875166831b12d1711ba1dc9ba5f7323d635a50a /audio/festvox-us2/pkg | |
| parent | c16ded344597d0c8c4a79d40b83986689d7ca764 (diff) | |
| download | pkgsrc-b70f353883887c30fb452aac44746aba8bfdd2ee.tar.gz | |
MBROLA based American English male voice for the festival speech
synthesis system.
This voice provides a American English male 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_us2_mbrola)
-Julian Assange <proff@iq.org>
Diffstat (limited to 'audio/festvox-us2/pkg')
| -rw-r--r-- | audio/festvox-us2/pkg/COMMENT | 1 | ||||
| -rw-r--r-- | audio/festvox-us2/pkg/DESCR | 14 | ||||
| -rw-r--r-- | audio/festvox-us2/pkg/PLIST | 9 |
3 files changed, 24 insertions, 0 deletions
diff --git a/audio/festvox-us2/pkg/COMMENT b/audio/festvox-us2/pkg/COMMENT new file mode 100644 index 00000000000..87c6eee5e67 --- /dev/null +++ b/audio/festvox-us2/pkg/COMMENT @@ -0,0 +1 @@ +MBROLA based Americal English male voice for festival diff --git a/audio/festvox-us2/pkg/DESCR b/audio/festvox-us2/pkg/DESCR new file mode 100644 index 00000000000..be6662024c1 --- /dev/null +++ b/audio/festvox-us2/pkg/DESCR @@ -0,0 +1,14 @@ +MBROLA based American English male voice for the festival speech +synthesis system. + +This voice provides a American English male 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_us2_mbrola) + +-Julian Assange <proff@iq.org> diff --git a/audio/festvox-us2/pkg/PLIST b/audio/festvox-us2/pkg/PLIST new file mode 100644 index 00000000000..dd8ff45aff5 --- /dev/null +++ b/audio/festvox-us2/pkg/PLIST @@ -0,0 +1,9 @@ +@comment $NetBSD: PLIST,v 1.1.1.1 1999/10/11 16:44:40 proff Exp $ +@comment the next two entries are symlinks +share/festival/lib/voices/english/us2_mbrola/us2mrpa +share/festival/lib/voices/english/us2_mbrola/us2 +share/festival/lib/voices/english/us2_mbrola/usradio +share/festival/lib/voices/english/us2_mbrola/festvox/us2_mbrola.scm +share/festival/lib/voices/english/us2_mbrola/festvox/usdurtreeZ.scm +@dirrm share/festival/lib/voices/english/us2_mbrola/festvox +@dirrm share/festival/lib/voices/english/us2_mbrola |