Article View: comp.dsp
Article #1692Getting the sounds for speech synthesis
From: Philip Colmer
Date: Wed, 17 Apr 1991 11:21
Date: Wed, 17 Apr 1991 11:21
21 lines
1358 bytes
1358 bytes
My apologies if this is the wrong group to post to with the following question ... in which case, can someone point me at a better or correct group? What I would like to know is ... when people are building speech synthesisers, typically based on allophones or phonemes, how are they getting the samples? I've tried recording whole words and then using sample manipulating software to cut the required bits out, but because of the variation in pitch, the concatenated samples sound like a drunk :-) Not quite the result I'm after. My current technique is to sample an existing sound chip, but it didn't have a particularly good sound in the first place, and I am now interested in female, French and German voices. Can anyone help? --Philip Colmer ------------------------------------------------------------------------------ Philip Colmer, OA Project Leader, Acorn Computers Ltd (pcolmer@acorn.co.uk)
Technical Details
Message-ID:
<6440@acorn.co.uk>Path:
arc1-ca.pugleaf.net!utzoo!utgpu!news-server.csri.toronto.edu!rpi!uwm.edu!bionet!agate!ucbvax!bloom-beacon!eru!hagbard!sunic!mcsun!ukc!acorn!pcolmerShow Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!utzoo!utgpu!news-server.csri.toronto.edu!rpi!uwm.edu!bionet!agate!ucbvax!bloom-beacon!eru!hagbard!sunic!mcsun!ukc!acorn!pcolmer From: pcolmer@acorn.co.uk (Philip Colmer) Newsgroups: comp.dsp Subject: Getting the sounds for speech synthesis Message-ID: <6440@acorn.co.uk> Date: 17 Apr 91 11:21:05 GMT Sender: pcolmer@acorn.co.uk Distribution: comp Organization: Acorn Computers Ltd, Cambridge, England Lines: 21