[DECtalk] Question About Formant vs Natural Speech

joshknnd1982 at gmail.com joshknnd1982 at gmail.com
Sun Jun 19 10:23:41 EDT 2022


The units are probably the same as they always have been, very small
recordings of human speech broken down into phonemes or maybe diphones.
Except there is a whole lot of them probably taking hundreds of megabytes
but probably compressed somehow to make them smaller.


-----Original Message-----
From: Dectalk <dectalk-bounces at bluegrasspals.com> On Behalf Of Don
Sent: Sunday, June 19, 2022 9:58
To: dectalk at bluegrasspals.com
Subject: Re: [DECtalk] Question About Formant vs Natural Speech

On 6/19/2022 6:52 AM, joshknnd1982 at gmail.com wrote:
> Actually, vocalizer is unit-selection speech and I think the new 
> neural-tts voices like alexa may be hmm-based speech, hmm or h-m-m 
> means hidden Markov model.

And what do you think the "units" are?  :>

_______________________________________________
Dectalk mailing list
Dectalk at bluegrasspals.com
https://bluegrasspals.com/mailman/listinfo/dectalk



More information about the Dectalk mailing list