Slashdot Mirror

It isn't exactly innovative, though - there have been ways of adapting TTS voices to sound like a particular speaker that require less training than this for years. There's even an open source implementation of it in Festvox.

I'm amazed asterisk@home wasn't the first thing posted here. Don't be fooled by the @Home part. This is a full fledged install of asterisk that is only limited by the hardware you install it on. You can have a working PBX in an hour. I'm planning to install this at all my remote sites (6 of them) with free extension call throughout and then plan to install it at my main location (150 phones) and have it all interconnected. A VERY powerful solution.

(Note: I just copied the rest of this from the handbook so I don't have to retype it all)

The Asterisk@Home project enables the home (or small office) user to quickly set up a full featured Asterisk PBX with a web based interface in about an hour on a dedicated PC. Even if you are new to Linux, Asterisk@home handles that by handling the complete Linux install for you. In order to get up and running all you need to do is download the Asterisk@Home .iso and burn it to a CD. Boot that CD and you will get a very complete Asterisk and Linux install.

Asterisk@Home provides a nicely integrated install of some of the best software from the Asterisk community, such as the Asterisk Management Portal, which provides an intuitive Web GUI for configuring asterisk, and the Flash Operators Panel, which lets you see and control your Asterisk PBX in realtime, and FAX support through span-dsp.

What is included in Asterisk@Home 2.0:

Linux CentOS 4.2 - http://www.centos.org/ - CentOS is 100% compatible rebuild of the Red Hat Enterprise Linux (RHEL), in full compliance with Red Hat's redistribution requirements. CentOS 2, 3, and 4 are built from publically available open source SRPMS provided by Red Hat. CentOS conforms fully with the upstream vendor's redistribution policies and aims to be 100% binary compatible. CentOS mainly changes packages to remove upstream vendor branding and artwork. CentOS is for people who need an enterprise level operating system with stability to match without the associated cost and support.
Apache Web Server (2.0.52)
MySQL Database (4.1.12) - SQL database for Call Detail Reports and optional configuration information.
Php (4.3.9)
Asterisk 1.2 - http://www.asterisk.org/ An open source software implementation of a telephone private branch exchange (PBX). A PBX connects one or more telephones on one side to one or more telephone lines on the other side. A good example of this is a small company with 100 internal telephones sharing 20 outgoing/incoming telephone lines. A PBX can be more cost effective then having 100 direct telephone lines.
AMP 1.10.010 BETA - http://www.coalescentsystems.ca/ - Asterisk Management Panel is a web based GUI that allows you to easily manage Asterisk without having to edit sometimes complicated text configuration files. This package is can really make a difference in learning and configuring asterisk easily.
Flash Operator Panel 0.24 - http://www.asternic.org/ - Flash Operator Panel is a switchboard type application for the Asterisk PBX. It runs on a web browser with the flash plugin. It is able to display information about your PBX activity in real time. You can see what all of your extensions, trunks, and conferences are doing. You can also hang up, transfer, initate a call or create a conference call.
Festival Speech Engine version 1.96 - http://festvox.org/festival/ - Festival is a speech synthesis system. It allows you to enter text that the Asterisk@Home server "reads out loud" to anyone calling the server. Using this, you can be sure the same voice is used across the whole asterisk server.
SugarCRM with Cisco XML Services interface + Click to Dial - http://www.sugarcrm.com/crm/ - SugarCRM is designed to a be a complete customer/contact manager. Using SugarCRM we can manage all types of communications (faxes, te

Rather than "Starter Edition," here's some suggestions, if anyone from Redmond just happens to read this. (I know they won't do it - it's more a mental exercise while I eat)

1. Go download this, and make it natively multi-user if it isn't already. Give it a strong native security model, too...you can get some ideas here, and the best part is, they won't mind you doing that if you don't try and patent said ideas. Also, modularise your GUI, and don't prevent users from accessing the CLI when they want to.

2. Have the CLI composed of this and this for us CLI types.

3. Make the Add/Remove Programs panel essentially a net-aware frontend for either this or this.

4. Use this for hardware detection. Also re drivers, get rid of the suicidal policy of seeing third-party hardware vendors as the enemy, and actually support them...via tools, docs, etc. These people are your friends...they'll help you stay relevant.

5. Download this and use it as your default FS, and then get this and this, (although you already seem to know about this last one) and incorporate both of those into your stock UI. You've essentially got WinFS right there, without all the added complexity you'd no doubt throw into it if you tried to code it from scratch.

6. For the Agent angle, incorporate the last point, as well as putting help/docs in a non-binary format, making them searchable with this, converting said search results for use with this, and then use the AIML output as input for something like this. Also, instead of making the agent a tightly anthropomorphic personality, make it more generic, and more as though it's simply "the operating system" communicating with a user, rather than that dog or Clippit instead.

7. Give Outlook a major overhaul. This and this are examples of directions it IMHO should go in.

Just some random ideas, anywayz. Dreaming's fun. ;) I'll probably get modded Offtopic, but it was worth it.

We were hoping AT&T would do a better job than IBM at supporting their voice synthesizer. IBM pulled the Linux version of ViaVoice off the market without so much as a peep to their adoring fans on Slashdot, and wiped all mention of the Linux version from their web server. (Goggle isn't even allowed to cache it.) After IBM milked the slashdot linux fanboy publicity for all it was worth, they appearently didn't see any purpose in actually SUPPORTING the product -- so once their libraries stopped working against the latest Gnu/Linux libraries (happy birthday RMS!), they dropped their Linux voice synthesizer product like a hot potato instead of bothering to recompile it and issue an update.

So we hoped AT&T would show more comittment to the promises they made on their web site about their flagship voice synthesizer product, but...

Has anyone actually tried buying a single user copy of Natural Voices from AT&T? YOU CAN'T ANYMORE! They used to sell the synthesizer for workstations and voices for competitive prices (in the 100s of dollars range). So we bought a few voices to evaluate, and sent some simple technical questions into the email address they provided for support, never receiving a reply.

After several weeks they never answered any of our questions, but we decided to buy some more voices to evaluate anyway. But by then, AT&T had pulled the consumer single user version of Natural Voices off of the market (and it took weeks of phone tag to find that out because they don't give out "technical" information on the phone, and they never answer their email support address).

Now if you want to buy a Natural Voice from AT&T, you have to buy the server edition for tens of thousands of dollars. Had their support not absolutely sucked, it might have been worth us paying such a high price, but no way we'd ever consider going with AT&T, after they demonstrated such horrible unresponsive service.

Actually it's a good thing we didn't go with AT&T's voice synthesizer, because we need support for voice authoring tools, and AT&T is incompetent in that regard, since they refuse to give out technical information over the phone, and never answer their email. No support whatsoever. Zilch. Nada. Forget about it.

Fortunately we found some excellent open source software that works together (and whose authors are MUCH more responsive than IBM or AT&T): the Festival Speech Synthesis System, the FestVox voice authoring tools, the small fast Flite runtime speech engine, the Edinburgh Speech Tools, the CSLU speech tools, the OGI Festival tools, and the MBROLA Multilingual Speech Project. This is state of the art research software, where IBM and AT&T got their ideas.

The quality of the commercial voices comes more from throwing lots of time and money into the production process -- the commercial software is not any more advanced than the open source research projects -- in fact the research projects inspired the commercial products!

-A speech synthesizer user who's been jerked around by AT&T and IBM, and is now happy to have no other choice but to use excellent open source software.

For all of these creative artists, most laboring in obscurity, being well-enough known to be pirated would be a crowning achievement. Piracy is a kind of progressive taxation, which may shave a few percentage points off the sales of well-known artists (and I say "may" because even that point is not proven), in exchange for massive benefits to the far greater number for whom exposure may lead to increased revenues.

A few weeks ago, I wrote Microsoft Mac FUD, Phooey, complaining about Microsoft Macintosh Business Unit head Kevin Browne's comments on the eve of Macworld.

This is such a despicable tactic. Microsoft embraced Apple and gave them funding at the height of the antitrust investigation, as a way of sustaining the idea that there was still competition in the market. Now that Apple's back on their feet, and OS X is giving them a run for the money, they pull out of the market. This decision may end up as badly for Microsoft's Office division as Lotus' decision to skip Windows.

Hackers and "alpha geeks" push the envelope, start to use the new technology, and get more out of their systems long before ordinary users even know what's possible.

A good example that's still a bit far out, but that I'm confident is significant. I held a summit of peer-to-peer networking developers, and when we were sitting around having a beer afterwards, a young FreeNet developer said to Kevin Lenzo (who was there because of his early work on IRC infobots): "You sound familiar."

Kevin mentioned that he was the developer of festvox, an open source speech synthesis package, and that he was the source of one of the voices distributed with the package. "Oh, that's why. I listen to you all the time. I pipe IRC to festival so I can listen to it in the background when I'm coding."

Now I'll guarantee that lots of people will routinely be converting text to speech in a few years, and I know it because the hackers are already doing it. It's been possible for a long time, but now it's ripening toward the mainstream.

" ... I know several who have started using Darwin on Intel hardware as there[sic] Unix underpinnings of choice ... "

Todd Hoff writes:

I'm a Windows-only user and I plan to switch to the Mac on my next purchase because of XP's DRM approach. Using XP would be like voluntarily entering a jail cell and closing the door.

From an interface perspective, I don't find the Mac superior.

Amen to your DRM concerns. Apple has been relatively more enlightened on the subject of DRM, recognizing that most users are fundamentally honest, and unwilling to support the extreme position of fear-mongering media executives.

When industry gets handed lemons on this scale, it has no choice but to turn them into marketing. A common reckoning is that one-third of software is used illegally, but not every theft represents a lost sale. If economic theory has any claim on the real world, Microsoft's pricing should naturally gravitate toward producing an optimum amount of theft. That is, thieves who wouldn't use the product if they had to pay for it, but who might become future customers or who become part of a network of users that makes the software more valuable to legitimate buyers.
...
A sore subject at its antitrust trial, for instance, was Microsoft's practice of awarding large discounts to computer makers who bought a Windows license for every machine they shipped, whether or not Windows was actually loaded. This was supposed to be proof of monopolistic intent, but the only real competitor for Windows is a Windows bootleg. Microsoft's pricing strategy was designed to induce customers not to steal.
...
The entertainment industry is still getting used to the idea that anybody who wants to take the trouble can get its products for free. But as Microsoft has been showing for years, that's no excuse for not making bundles of money.

1) What would you use to convert (english) sentences to speech samples (in real time, if possible perfomance-wise).

Others already mentioned Festival - and I wholeheartedly recommend it. (Under BSDish license.)

I especially recommend it with the OGI CSLU patch, even when it's not really open source (only for non-commercial use). Festival is great, it sounds nice even with the normal voice set... but this patch makes it sound really great.

I've used this program to read me some looong texts. (I don't want to do unnecessary large printouts, want to spare the batteries of my PDA, and I don't want to wreck my eyes completely with the monitor...) Strangely, the first text I fed through the OGIFestival was some H.P. Lovecraft story that featured artificial voice... =)

I wish they'd make the changes available under the same license as Festival so I could just apt-get the thing, now I need to do some patch tricks to get it up and running =/ But it's still fairly easy to build by following the instructions.

Type in something rude, turn up the volume and have fun!

SpeechWorks' OpenVXI, originally promoted as an open source VXML interpreter, has turned out not to be a good one. Speechworks developers maintain the code, and refuse to incorporate the patches and requests of the open source community, in favor of keeping OpenVXI tied to Speechworks products. The codebase could be forked, but it's really not worth investing the effort in such a brittle product tied to proprietary solutions.

Bayonne, the GNU telephony server, is great and getting better all the time. It currently supports a strong scripting language for DTMF applications, and Bayonne's XML plugin structure and built-in support for multiple telephony cards makes it the logical choice for open source VXML.

All that's needed at this point is to finish integrating Bayonne with an open source Text-To-Speech engine (most-likely candidates are Flite or Festival), Automatic Speech Recognition engine (in this case, Sphinx) and write the XML plugin. But there is a shortage of coders with the skill and time to do this.

I really think small business and the average Slashdotter could benefit from an open source VXML solution. Small businesses could create professional telephony apps that could make them much more competitive (from accepting credit cards securely over the phone to providing dedicated 24-hr support numbers for their products), while creative coders could use it for everything from Eliza-style chatbot answering machines to having your boxen call you up and describe a hack attempt as it's being made.

I'd love to see a VXML enabled Bayonne blow TellMe and others out of the water. If you're intrigued and you'd like to get involved, check out Bayonne's Sourceforge site and sign up for the mailing list.

I was disappointed by the bad speech encoding. I had expected in 2002 you'd actually be able to synthesize a voice that sounds close to human or at least be understandable. The old amiga 500 had a utility that was much more understandable than this is.

I don't know about the Amiga but I had an old TI99-4A that had a speech synthesis module. It was quite good at reading most words but had a built in list of words it could read. You could get it to read other words but it meant that you had to express the word in a special way so that the module could pronounce it properly. That really defeats the point of text to speech.

I think text to speech has come on a long way since those days but it seems like slow progress which is due to the complexity of the subject. There is a good open source text to speech engine called Festival. You can test it with your own text here

The CMU speech folks, Alan Black and Kevin Lenzo, told me last Thursday that they'd have a package for the Linux iPAQ in another week. And it's going to be small enough to include by default.
-russ

For what it's worth, SpeechWorks International licensed an earlier version of the AT&T synthesizer. You can find demos here. The version in the NYT seems to have been developed with different constraints. Many TTS engines are designed to achieve real time play back or to use limited amounts of CPU. For instance, synthesized speech during game play should only use 5% or maybe 10% of the processor. Whereas a system for Hollywood may demand considerable CPU power to produce small utterances (say 100 CPU seconds per second of speech). This is completely acceptable for many purposes where perceived quality is the primary criteria.

There is also an open source TTS engine called Festival, developed at the University of Edinburgh and at Carnegie Mellon University. You can find out more here. Or, just download the source.