Return to the archive index

Re: Timeleine'Puter (was Small Storage Devices

On Mon, 04 May 1998 13:17:24 +0000,  "R. Paul McCarty" <> wrote:

>I'd really like to add audio to my wearable to do at least text to
>speech, but I'm hesitant to add yet another card to the pc/104 stack, or
>add the serial port driven doubleTalk box.  Has anyone thought about
>using an off the shelf speech synthesizer chip? I've seen single chips
>at radio shack that do text to speech, and although the quality of the
>output may be pretty bad, it would be a way to add speech capability to
>my wearable without adding alot of additional electronics and boards.  I
>did a quick search and there are lots of vendors selling single chip
>speech synthesizers, so I imagine some of them are pretty easy to build
>serial interfaces to.
>
>Any suggestions for chips? and whether this is relatively easy to do?
>
>-Paul

How about a DSP solution, like the Analog Devices 2181.  I'm planning on getting an EZ-Kit to
investigate this.

My plan is to use an outboard DSP peripheral connected via a serial or parallel port.  This will
allow speech input and output with lower CPU overhead. 

For speech input the DSP periph samples the mic input and sends feature vectors (Mel scaled
cepstrum, etc) to the wearable.  Higher level analysis (HMM/neural net etc) takes place on the
wearable)

For speech output, the wearable sends low bandwidth data (LPC-10, GSM, maybe even MP3) and drives a
speaker/headphone.

Any advice/ideas?

From Wear-Hard Mailing list Archive (WH)
Maintained by R. Paul McCarty

Archive created with babymail