From 1ff8b46a94c0007e64166ade3e3a6db98498bda0 Mon Sep 17 00:00:00 2001 From: proff Date: Mon, 11 Oct 1999 16:51:41 +0000 Subject: 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. The quality of this voice is not as high as us1 and us2 This voice can be activated via (voice_us3_mbrola) -Julian Assange --- audio/festvox-us3/pkg/COMMENT | 1 + audio/festvox-us3/pkg/DESCR | 16 ++++++++++++++++ audio/festvox-us3/pkg/PLIST | 9 +++++++++ 3 files changed, 26 insertions(+) create mode 100644 audio/festvox-us3/pkg/COMMENT create mode 100644 audio/festvox-us3/pkg/DESCR create mode 100644 audio/festvox-us3/pkg/PLIST (limited to 'audio/festvox-us3/pkg') diff --git a/audio/festvox-us3/pkg/COMMENT b/audio/festvox-us3/pkg/COMMENT new file mode 100644 index 00000000000..ea29d79706e --- /dev/null +++ b/audio/festvox-us3/pkg/COMMENT @@ -0,0 +1 @@ +MBROLA based American English male voice for festival diff --git a/audio/festvox-us3/pkg/DESCR b/audio/festvox-us3/pkg/DESCR new file mode 100644 index 00000000000..2d12612e9ce --- /dev/null +++ b/audio/festvox-us3/pkg/DESCR @@ -0,0 +1,16 @@ +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. + +The quality of this voice is not as high as us1 and us2 + +This voice can be activated via (voice_us3_mbrola) + +-Julian Assange diff --git a/audio/festvox-us3/pkg/PLIST b/audio/festvox-us3/pkg/PLIST new file mode 100644 index 00000000000..1f972f70609 --- /dev/null +++ b/audio/festvox-us3/pkg/PLIST @@ -0,0 +1,9 @@ +@comment $NetBSD: PLIST,v 1.1.1.1 1999/10/11 16:51:41 proff Exp $ +@comment the next two entries are symlinks +share/festival/lib/voices/english/us3_mbrola/us3mrpa +share/festival/lib/voices/english/us3_mbrola/us3 +share/festival/lib/voices/english/us3_mbrola/usradio +share/festival/lib/voices/english/us3_mbrola/festvox/us3_mbrola.scm +share/festival/lib/voices/english/us3_mbrola/festvox/usdurtreeZ.scm +@dirrm share/festival/lib/voices/english/us3_mbrola/festvox +@dirrm share/festival/lib/voices/english/us3_mbrola -- cgit v1.2.3