home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.amiga.multimedia
- Path: sparky!uunet!haven.umd.edu!decuac!pa.dec.com!engage.pko.dec.com!nntpd.lkg.dec.com!snoc01.enet.dec.com!king
- From: king@snoc01.enet.dec.com (Randall King, Sydney, Aussieland)
- Subject: Re: C= : Where's the Speech?
- Message-ID: <1993Jan3.041859.13620@nntpd.lkg.dec.com>
- Sender: usenet@nntpd.lkg.dec.com (USENET News System)
- Organization: Digital Equipment Corporation
- References: <Bz1v4z.4qI@undergrad.math.waterloo.edu> <Bz276t.n1x@news.iastate.edu> <57432@dime.cs.umass.edu> <If_atQu00hsB4p7WdZ@cs.cmu.edu>
- Date: Sun, 3 Jan 1993 20:05:43 GMT
- Lines: 42
-
- >The prosodic model sucks. Coarticulation isn't modelled well, rate
- >dependent phone deletion doesn't happen properly. The synthesiser can't
- >speak any language but American English. The source model is probably
- >white noise instead of modelled glottal pulses. The text to speech
- >algorithm makes frequent errors. I defy anyone to listen to the Amiga
- >read their mail to them without needing to look at it as well.
- >
- >The speech is far from perfect. There are better synthesisers out there,
- >and plenty of room for improvement. Anyone who has heard a human being
- >speak should know that the speech can be improved a lot.
- >
- >That not withstanding, amiga's speech synthesis is pretty good as
- >non-research systems go, and has such an important place in Amiga
- >software that it needs to be kept and improved. If a serious effort were
- >made to support multiple languages, amiga speech would be a uniquely
- >useful product.
- >
- >I'm not sure that speeding up the model with a DSP is the only way of
- >improving the speech, however, - switching to something like
- >interpolated demisyllable synthesis instead of the current source/filter
- >articulatory model might help more.
- >---
- >In any case, rest assured that Marc knows nothing about speech synth,
- >but that the Amiga needs it.
-
-
- I know absolutely nothing technical about speech (a prosodic model could
- be a torture instrument or a species of fish for all I know). And I have
- to declare an organisational interest too.
-
- But I can tell you that the DECtalk synthesis commercially available from DEC
- for the last five years gives realistic speech with inflections and intonations
- and few errors. Admittedly it costs more than an Ami, but it definitely aint
- stuck in the research labs.
-
- C= have given it a good shot. You've got to give points for commercial
- innovation in 1985, but it just aint in the league when it comes to anything
- other than novelty eg. answering your phone without sounding like a
- moron. I can't hear that V2.04 did much really either. Sorry folks.
-
-
-
-