From owner-freebsd-ports Wed Oct 13 12:58:51 1999 Delivered-To: freebsd-ports@freebsd.org Received: from suburbia.net (suburbia.net [203.4.184.1]) by hub.freebsd.org (Postfix) with ESMTP id 63081151E5; Wed, 13 Oct 1999 12:58:43 -0700 (PDT) (envelope-from proff@suburbia.net) Received: by suburbia.net (Postfix, from userid 110) id 715116C4C8; Thu, 14 Oct 1999 05:58:40 +1000 (EST) To: freebsd-ports@freebsd.org, ports@openbsd.org Subject: festival-1.4.0 + mbrola (state of the art speech synth) ported to NetBSD Cc: freebsd-audio@freebsd.org Cc: proff@iq.org Cc: editor@daemonnews.org From: Julian Assange Date: 14 Oct 1999 05:58:40 +1000 Message-ID: Lines: 69 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: owner-freebsd-ports@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org 23 diphone databases (voices)! 4 pronunciation dictionaries! 6 dialects! More lines of code than emacs! State of the art research! Built in scheme virtual machine! 32 inter-dependent packages! 2 sexes! The ultimate package for not only those working on speech research, but blind users and those who merely want icb or irc or their shell prompt to come alive. ftp://ftp.netbsd.org/pub/NetBSD/packages/pkgsrc/audio/README.html Translating these packages to OpenBSD or FreeBSD port format should be trivial. Julian. Festival is an advanced multi-lingual speech synthesis system developed at CSTR. It offers a full text to speech system with various APIs, as well an environment for development and research of speech synthesis techniques. It is written in C++ with a Scheme-based command interpreter for general control. You will also need to install at least one festvox-* (festival voice) package (infact, the festvox packages are dependent on this package). festival --tts foo.bar will speak ASCII file foo.bar, (SayText "Oh Dad! We're ALL Devo!") My ZenIRC/ZenICB lisp code is packaged seperately and is available on request. -Julian Assange Current version Version 1.4.0 (June 1999) is now available free for unrestricted use o English (British and American), Spanish and Welsh text to speech o Externally configurable language independent modules o phonesets, lexicons, letter-to-sound rules, tokenizing, part of speech tagging, intonation and duration. Festival 1.4.0 has the following improvements over the previous release (1.3.1 January 1999) o distributed under a free X11-type licence o generalization of stats modules, ngram, CART, wfst with viterbi so they can be shard more easily o Tidy up of Utterance/Relation/Item architecture o Initial JSAPI support o Three new us voices using MBROLA databases o Tilt code overhaul o XML load for Relations o Fringe graphic display (ALPHA) released seperately http://www.cstr.ed.ac.uk/projects/fringe.html Previous (1.3.1) features: * English (British and American), Spanish (mexican) and Welsh text to speech * Externally configurable language independent modules + phonesets, lexicons, letter-to-sound rules, tokenizing, part of speech tagging, intonation and duration. * Waveform synthesizers: + diphone based: residual excited LPC (and PSOLA not for distribution) + MBROLA database support. * Portable (Unix) distribution. * On-line documentation. * SABLE markup, Emacs, client/server (including Java), scripting interfaces. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-ports" in the body of the message