<html><head><style> body {height: 100%; color:#000000; font-size:12pt; font-family:Times New Roman;}</style></head><body>Don,<br><span>For me, whether a speech synthesizer is tolerable or not depends on a few factors.</span><br><span>1. How realistic the voice sounds, naturalness.</span><br><span>2. Whether the synthesizer can handle the amount of text given to it by the screen reading software without crashing.</span><br><span>3. If I can listen to the synthesizer for a long period without getting ear fatigue.</span><br><br><span>Let me provide two examples. Years ago I purchased AT&T voices from nextup.com for use with the the TextAloud program. Since AT&T voices are SAPI5 compatible, I chose to use them with my screen reader. That was a mistake. The voices are so large in size that they would consistently crash after being my JAWS screen reader voice for a minute or two. To me, the AT&T voices I purchased also sound monotone, so I could not tolerate listening to AT&T voices for hours on end in any event. I think there is a newer version of the AT&T voices from Wizard Software which NextUp does not have access to/does not sell. I can only share my perspective based on the voices which I have.</span><br><br><span>On my Windows 10 system at home, I prefer either Eloquence or Microsoft Mark. When I am using JAWS Professional Edition on my work laptop, I prefer Microsoft Mark or the Vocalizer British English Vocalizer voice Malcolm although I happen to reside in the U.S. Malcolm sounds natural, does not crash and I enjoy listening to him for hours.</span><br><br><span>These are my thoughts. I know that some people evaluate a synthesizer voice on how fast it can talk. I do not use that criteria myself as an end-user because I prefer slow or medium speed. If a voice is set too fast, I cannot understand it.</span><br><span>Blake</span><br><span> </span><br><br>----- Original Message -----<br>From: mattias jonsson <mj@mjw.se><br>To: DECtalk <dectalk@bluegrasspals.com><br>Sent: Sun, 21 Jul 2019 06:40:35 -0400 (EDT)<br>Subject: Re: [DECtalk] Intelligibility/Listenability criteria<br><br>my favorite voices: vocalizer swedish alva for swedish,vocalizer evan us english<br><br><br>Den 21 juli 2019 10:18:11 skrev Damien Garwood <damien@daygar.plus.com>:<br><br>> Hi Don,<br>> Here are my criteria:<br>><br>> 1. Understandability<br>> As a screen reader user who has to listen to speech synthesis on a <br>> constant basis while using a computer, understandability is first and <br>> foremost. If the synthesiser can't be understood, then you're not going <br>> to get the feedback you need. In my opinion, ESpeak ticks every box, <br>> except this, so I can't use it.<br>> 2. Responsiveness. Again, because the speech is reading everything for <br>> me, I don't want a synthesiser that acts sluggishly with any kind of <br>> latency, whether that be a second, or 50 milliseconds, whether through <br>> lack of performance optimisation or through audio silence. When I press <br>> a key, I want instant feedback. This automatically rules out most <br>> natural-sounding synthesisers.<br>> 3. Accuracy: It needs to be able to read text accurately for the <br>> language it is designed for. It's not enough simply to have a phonetics <br>> dictionary, but it also needs to be able to distinguish between words <br>> (Present noun versus present verb, for instance).<br>> 4. Flexibility: The voice timbres should be available to the user, and <br>> for the most part should adjust smoothly to the change. This is <br>> important if a user has specialist needs and cannot use the synth in its <br>> default state. Speed and pitch are definitely a must. Again, this rules <br>> out natural synths, since due to the nature of recorded samples they <br>> start to begin to sound unnatural if you attempt to adjust the speed and <br>> pitch. The bigger the change, the more unnatural.<br>> Like Jason, I also prefer formant synths. My favourite by far is <br>> Keynote, which to me is the most understandable, but I do love DECTalk <br>> for its flexibility. I also like Eloquence and the synthetic version of <br>> Orpheus.<br>> Cheers,<br>> Damien.<br>><br>> On 21/07/2019 05:53 am, Don wrote:<br>>> Hi,<br>>> <br>>> Perhaps a bit off-topic for this list... if so, my apologies.<br>>> <br>>> I'm looking for opinions as to how one evaluates the "effectiveness"<br>>> of a particular synthesizer. Said another way, how one decides that<br>>> synthesizer A is "better" than synthesizer B. Ideally, criteria that<br>>> would allow you to rank a set of them!<br>>> <br>>> I've been auditioning various synthesis devices and techniques<br>>> to try to come to my own conclusions on this. Then, hopefully,<br>>> work backwards to come up with some objective criteria by which<br>>> they could each be "scored" (even if that was done using bogus<br>>> rating units).<br>>> <br>>> "Intelligibility" is, of course, the prime issue. "Listenability"<br>>> coming into play for any prolonged use. Finally, "naturalness"<br>>> when it comes to extended use.<br>>> <br>>> For example, the old Votrax units were intelligible -- once you<br>>> learned their "accent". But, listenability was rather poor... you<br>>> quickly developed ear fatigue. And, the idea of naturalness was<br>>> never even considered!<br>>> <br>>> With gobs of resources (hardware, software, processing power), you<br>>> can achieve quite acceptable results. This seems to be the approach<br>>> most "modern" synthesizers -- and techniques -- adopt. The real problem<br>>> lies with limited resources attempting to handle unconstrained input.<br>>> (If you know what you're going to be asked to speak, it's really easy to<br>>> come up with a good presentation!)<br>>> <br>>> Limiting the user's exposure to the synthetic voice can reduce ear fatigue.<br>>> So, dealing with it for 10 minutes might be tolerable while 2 hours<br>>> would be torture.<br>>> <br>>> But, having to face the prospect of completely unconstrained input can<br>>> tax even that brief usage. "Dr. Jones' car -- bearing the license plate<br>>> FTDKTR -- has been parked in front of his house on Jones Dr. since 12:34A<br>>> this morning when his Polish butler finished polishing it." Imagine you<br>>> have no other way of inspecting the input text...<br>>> <br>>> So, what makes a synthesizer "tolerable" or "intolerable"? What is the<br>>> "threshold of pain" when it comes to tolerating an underperforming<br>>> synthesizer?<br>>> _______________________________________________<br>>> Dectalk mailing list<br>>> Dectalk@bluegrasspals.com<br>>> http://bluegrasspals.com/mailman/listinfo/dectalk<br>>> <br>> _______________________________________________<br>> Dectalk mailing list<br>> Dectalk@bluegrasspals.com<br>> http://bluegrasspals.com/mailman/listinfo/dectalk<br><br>_______________________________________________<br>Dectalk mailing list<br>Dectalk@bluegrasspals.com<br>http://bluegrasspals.com/mailman/listinfo/dectalk<br></body></html>