Sarah Hawkins (sh110@cam.ac.uk)
Mon, 4 Oct 1999 22:37:14 +0100 (BST)
If people want Mark's first para, I suggest a couple of small changes:
1. To avoid weakness or negativity, I think it's good to avoid starting
papers with words like Despite, although, etc. It sounds more positive (to
me) to the main claim first, and any "despites" or "althoughs" in a
following clause.
2. Intonation is part of prosody. Did you mean timing or rhythm, Mark?
3. re fine detail: I'm so sorry to bang on about it, but I reiterate that
I think we should try to use the word "systematic" when we write about
fine detail or variation.
I have suggested a few changes to fit in with these views. Please look
partiuclarly carefully at the rewrite around dull and repetitive
intonation and unexpressive porsody: you may prefer qutie different
wording.
Thanks for doing this, mark
Sarah
On Wed, 29 Sep 1999, Mark Huckvale wrote:
> Jill asked me to have a go at rewriting the first paragraph of the paper,
> taking into account recent work in corpus-based methods of synthesis.
> I think it says much the same things but in a more contemporary context.
>
> Mark
> ----------------------------------------------------------------------
> Speech synthesised by rule has yet to make a significant impact as an
> output channel for information systems,
> despite continued engineering advances in text to speech (TTS) systems.
A constant complaint is the
> perceived 'unnatural' quality of the synthetic speech: that the speech does
> not sound as if it could have been produced by a human speaker. Such
> problems persist despite improvements in textual analysis, pronunciation
> and signal generation. For example: although the use of a large corpus of
> recorded speech for polyphone concatenation has produced signals with
> sections with a highly-natural voice quality, utterances still exhibit
> disfluencies, broken rhythm and lack of coherence. Contemporary synthetic
> speech still suffers from
from unexpressiveand often inappropriate prosody
and from poorly
> modelled coarticulation,
These failings arise
> from the poverty of the linguistic representation underlying the utterance
> to be produced, as well as a fundamental lack of attention to the
systyematic
fine
> detail in human production -
systematic fine
detail that listeners expect and also
> utilise when listening in noise.
>
>
>
Sarah
_____________________________________________________________________
Dr. Sarah Hawkins Email: sh110@cam.ac.uk
Dept. of Linguistics Phone: +44 1223 33 50 52
University of Cambridge Fax: +44 1223 33 50 53
Sidgwick Avenue or +44 1223 33 50 62
Cambridge CB3 9DA
United Kingdom
This archive was generated by hypermail 2.0b3 on Mon Oct 04 1999 - 22:38:33 BST