• Please review our updated Terms and Rules here

Software Automated Mouth

Does it do speech-to-text, or just text-to-speech? I don't have any Apple to try it on, but I'm curious as to how it compares to more modern software. I just spent 2.5 hours yesterday installing & training Dragon Point & Speak. What a disappointment! It's speech recognizer really sux!

--T
 
S.A.M. as I know it is a software speech synthesizer, i.e. it will "speak" what you write to it, but no attempt at recording or recognizing. There were other hard/software solutions for various computers that tried to do that with various success.

S.A.M. was able for the Apple II, Atari 8-bit and Commodore 64; maybe even IBM PC(jr).
 
Speak and Spell, wasn't it? I think it uses a special chip that generates the speech, also available for other computers, rather than being software generated by the computer's sound chip.
 
the latest computer collector newsletter has an article on text to speech:


>> WELCOME TO THE COMPUTER COLLECTOR NEWSLETTER

>> W: http://news.computercollector.com E: news@computercollector.com

>> Vol. 4, Issue 4: Jan. 24, 2005: News/opinion, tidbits, classifieds

****************************************
NEWS & OPINION

The history of computer text-to-speech synthesis
by Evan Koblentz

Does your computer talk? Or rather, does it talk any better than it
could approximately 25 years ago?

That's right: we're "talking" about Software Automated Mouth, better
known as SAM, developed mostly by Mark Burton in 1979. The company,
SoftVoice, still exists today at http://www.text2speech.com. The
story of how Steve Jobs used SAM to make the Macintosh computer
"introduce itself" in 1984 is detailed at this very long web address:
http://www.folklore.org/StoryView.py?project=Macintosh&story=Intro_Dem
o.txt&topic=Marketing&sortOrder=Sort+by+Date&detail=medium&showcomment
s=1 (copy and paste the link because it will break across lines) but
we prefer http://homepage.mac.com/vectronic/appleii/sam.html
where you can actually download the stuffed software for Apple II
computers! (Soon we're acquiring a //c and looking forward to getting
this great memory from the past.) There is also a Wikipedia entry at
http://en.wikipedia.org/wiki/Software_Automatic_Mouth although we
don't particularly trust the accuracy of Wikipedia entries.

SAM is very neat, but we wondered: what came before it? What is the
real history of computer text-to-speech synthesis? In short, what was
the first machine -- computer or not -- to speak for itself? A-
Googling we went in search of some answers.

We found the web site http://www.ling.su.se/staff/hartmut/kemplne.htm
where Prof. Hartmut Traunmüller reports: "The first attempts to
produce human speech by machine were made in the 2nd half of the 18th
century. Ch. G. Kratzenstein, professor of physiology in Copenhagen,
previously in Halle and Petersburg, succeeded in producing vowels
using resonance tubes connected to organ pipes (1773)."

But there is a difference between the first attempts at something and
the first actual success. The professor continues: "[Wolfgang] Von
Kempelen's machine was the first that allowed to produce not only some
speech sounds, but also whole words and short sentences," described in
a paper by Von Kempelen in 1791.

Kempelen, as many computer history buffs already know, is more famous
for building a supposedly automated chess-playing machine, described
in great detail by writer Tom Standage in his 2002 book, "The Turk".
That chess machine turned out to be a fraud -- a short human was
always hidden inside -- but the speaking machine was real. Standage
explains how telegraph pioneer Charles Wheatstone built a copy of the
machine in 1863 and demonstrated it to a young Alexander Graham Bell.
(Visit http://www.ling.su.se/staff/hartmut/farkas.htm for many more
web sites and biographical references about Von Kempelen.)

Jump back to 1979: Texas Instruments was one of a few companies
selling handheld language translator devices. TI engineers
understood, however, that merely reading a foreign language was
useless if you didn't know how to pronounce the word. So they built
speech synthesis into the product using off-the-shelf technology from
their own parts bin: anyone remember the "Speak & Spell" toy? TI used
the toy chip while Burton and his colleagues were working on software
solutions! There are some fascinating specifications and other
details at http://www.datamath.org/Speech/LanguageTutor.htm. (I used
to own one of these devices, but gave it to VCF chief Sellam Ismail.
Unfortunately I did not record any audio clips from it.)

So again, we ask: does your computer talk any better than it could
approximately 25 years ago? Share your early text-to-speech tales
with us at news@computercollector.com.

[Note: we requested an interview with Mark Barton. We'll post the
results of that interview on the CCN web site when available.]

---------------------------------------
 
carlsson said:
Speak and Spell, wasn't it? I think it uses a special chip that generates the speech, also available for other computers, rather than being software generated by the computer's sound chip.
Click to expand...

Speak & Spell was quite a different animal, marketed as an educational toy for children, but it probably utilized the same chip, a TI proprietary design. The speech synthizer was an add-on for the TI99, which jacked into the expansion port on the side. It had a built-in vocabulary of several hundred words, plus a good number of built-in phonomes that could be programmed to pronounce other words not in the vocabulary. Funny thing is tho, IIRC, you couldn't program it directly from TI BASIC. You needed to have another cartridge, the Terminal Emulator to program the phonomes with. There were also a few games cartridges released which utilized the speech synthizer to speak with.

--T
 
SAM, etc....

SAM, etc....

Just to clear this up... my inspiration for writing about SAM, etc. in this week's Computer Collector Newsletter was actually a conversation with Rick a few days ago... we were talking along with several other people in the weekly chat at http://www.geocities.com/c64friends/ ... the topic happened to turn to synthesis and I brought up SAM, then Rick said he'd posted the relevant link here for me (and others) to get to afterwards.

Anyway, to Vic and everyone else: I hope you found the article educational and entertaining. I'm always looking for new story ideas if anyone has some (and looking for writers too... you try putting out a newsletter virtually alone each week!) :)
 
Gee, 1773.. if one produced a machine that could make sounds similar to human speech, I would suppose you got accused of witchcraft, or maybe that was a century earlier.
 
Anyway, to Vic and everyone else: I hope you found the article educational and entertaining. I'm always looking for new story ideas if anyone has some (and looking for writers too... you try putting out a newsletter virtually alone each week!)


_________________
Evan Koblentz, editor
Computer Collector Newsletter

http://news.computercollector.com

news@computercollector.com
Click to expand...

Holy smokes, you do most of that newsletter yourself?

Although nothing ever beats getting a physical newsletter in the mail, I love getting the CCN in my virtual mail box.

Thanks for all your work!

Chris
 
S.A.M.

S.A.M.

There were two different versions of S.A.M.--one all done with software throught the 1-bit speaker port of the Apple II, and one using an 8-bit DAC card with an audio amplifier.

Both used the standard phoneme synthesis algorithm in the public domain.

The tricky part was making reasonably good speech by generating a pulse-width modulated stream of pulses to the speaker. (I know, I built one of these myself. ;-)

The TI chip was based on linear predictive coding (LPC), that permits pretty intelligible speech with very low data rates. Unfortunately, it takes a lot of analysis to derive the LPC coefficients for a particular utterance, so the "dictionaries" for the chip were limited.

The most common way the TI chip was used with computers was with a "dictionalry" of phonemes and the standard phoneme synthesis algorithm, making it sound about like any of the other phoneme synthesizers (like the SC-01 or the SSI 263).

Street Electronics' Echo II was an Apple speech synthesis card based on the TI chip, and it had both phoneme synthesis (unlimited robotic vocabulary) and LPC-synthesized whole words, which were much higher quality but with a limited vocabulary.
 
I recently picked up a Super Speak & Spell at the thrift store, but I wasn't too impressed. It does come off as being yet another cheap-ass toy (very limited capabilities).
OTOH, I have been playing for the past few days with the latest addition to my vintage computer collection; an Epson HX-20 with an Adaptive Communication Systems RealVoice Expansion Unit. Not too shabby, for 20-year-old technology, especially when compared to state-of-the-art for today. Check this link for an interactive demo of ATTs latest offering:

http://www.research.att.com/projects/tts/demo.html

One of the local BBSs where I used to hang out was an Assistive Technology site, and a lot of hard-of-hearing people in Michigan were still using RealVoice at the time the board went down for good (Y2K issues) on Dec 31, 1999, and probably still are.

WARNING: Shameless and self serving plug ahead!

If anyone reading this would like one of thier own to play with, see my current eBay auctions:

http://cgi.ebay.com/ws/eBayISAPI.dll?ViewItem&item=5220376184&rd=1&sspagename=STRK:MESE:IT&rd=1

/plug

--T
 
The Epson unit is almost certainly using the same chip as the Speak'n'Spell. The only difference is the coefficient data being sent to it.

The Speak'n'Spell had a low price target and a relatively large vocabulary, so quality is limited (though still very understandable and better than most phoneme synthesis systems).

When the chip is fed by a computer, more data can be supplied, producing the pleasant female voice well-known to Echo II fans. ;-)
 
The RealVoice is powered by the same 6301-type CPU that (x2) is at the heart of the HX-20 itself, so it is essentially a computer in it own right (probably running in "slave" mode to the HX-20's master. I dont see anything in the way of TI chips in it, just a whole bunch of ROM chips & some others with identification sanded off.

--T
 
You must log in or register to reply here.
Back
Top