Today, I was reading an article in the January/February 2010 issue of Speech Technology, titled ‘Text-To-Speech’ by Caroline Henton.
The article was about a test used for evaluating the latest text-to-speech (known as TTS) products.
I’m interested in the technology for several reasons; one being my friend Tori_Z uses it to “read” blogs and other web pages. Another reason is my younger brother’s PhD (in Computer Science) thesis was about using computers to parse human language – or machine language recognition – his work dealt with making a computer understand someone, anyone, that spoke to it with an emphasis on the ums, likes, you knows, ahs, and errs and backtracking that people do when they speak naturally.
As I read the article I was struck by how difficult the test was – it consisted of 10 utterances to test TTS performance in pronunciation accuracy, text normalization, pausing, and other aspects of prosody.
Here are the ten utterances – how well can you read and pronounce these phrases? And Tori? I hope your blog reading program doesn’t choke to badly here!
1) McCain called Obama a liberal, and then he insulted him.
2) Jenny gave Peter instructions to follow.
3) I want doors I can shut!
4) Was the red book read or do we have to read it?
5) Bring me a blue towel, and a red one.
6) Cumin, fenugreek, bouillabaisse, rouille, riesling.
7) 124th Avenue, 120 4th Avenue, 100 24th Avenue.
8) Suisun City, Poughkeepsie, Coeur d’Alene, Streatham, Guildford.
9) Barrasso, Boustany, Faleomavaega, Grijalva, Kratovil, Radanovich, Sebelius.
10) Ralph Vaughn Williams, Ralph Fiennes, Nicolas Sarkozy, Nicholas Nickleby, Maria Callas, Black Maria.
I found numbers 6, 7, 8, 9, and 10 to be near tongue twisters. Apparently, number 9 is a partial list of current members of Congress. Four vendors submitted their products for evaluation and they actually preformed rather well. I’m amazed by how fast the technology is improving.
The article closed with:
“For future progress in speech synthesis, more attention to general purpose TTS (and less to, say, in-vehicle navigation) and the semantic disambiguation of homographs (read/read; Maria/Maria) would be universally beneficial.”
Uh huh, I umm... yeah... like, I agree with that, for sure.
:)
17 comments:
I can just imagine it now. Now more keyboards. Just speak and the computer does the rest. Wow.
Would love to hear it try jambalaya, Tchoupitoulas or Pontchartrain correctly...
Technology is just amazing! Interesting post Iggy thanks HUGS
this was interesting to read, Iggy, and some of those sentences were definitely tongue twisters. I have to say I have mixed thoughts about how far technology is coming and what computers can do and not do in discerning people's voices. I'm being replaced by a computer with voice recognition and instead of my skills as a transcriptionist, I'm now known as an editor, I'm eding and teaching the software how to pick up those nuances a bit better so eventually it might permanently replace us. and that is scary when we allow computers to do jobs that people used to do. I'm all for technology but I wonder at what price to humanity......
the nice thing about snow is it does eventually melt and how many snowstorms do you see in August, right?
be safe!
betty
i only hope that the world will not become TOO automated and technologified. i know that's not a word, but it is now, and the machines better learn to pronounce it!
You can ignore the snow all you want but I don't think it is going away, for a couple weeks at least. You don't want to know what Accu-weather said about Monday and later next week too!
Aaaa, um hu, 'dat's cool.
I don't mind the snow, as long as it stops by March. Hope you are staying safe inside your home!
And OMG, I don't even know how to begin to pronounce 8, 9, and 10.
8-9-10? yeah, right.
I read this in a hurry yesterday, but wanted to wait until I had time to re-read it slowly. (I just noticed in the first sentence that I unintentionally used a homograph lol). I cannot imagine how TTS distinguishes it all. The tongue twisters were amazing. I had trouble with many of them. Especially the ones you noted. Great post. Huge hugs.
Stay ssafe and warm friend, and don't get lost in those 10+ inch snow, snow drifts!
I had to read this three times to understand what it was saying. Maybe I need some technolody that can make things easier for me to understand.
I need a dictionary and an encyclopedia, please. :\
I know how to say Poughkeepsie. :p
(it's snowing today)
I heard someone say that it wasn't going to quit snowing until Al Gore "cries uncle." hee hee.
I love stuff like those "utterances."
Tongue twisters are fun!
but it scares me to think a computer could tell the difference between read and read.
Hummm--ya--that sounds like a pretty good ting, ya know? But kin a computer transcribe slang and local accents, ya know? But, ya--sounds good--youbetcha! ;)
I read this earlier. OK, OK... Jaws read it. LOL! I think it must have confused Jaws way too much though, because as I went to comment something tripped the main fuse of our electric, and we spent half the afternoon trying to convince the electric to stay on. LOL!
It didn't go away!
I couldn't even pronounce some of those words, so how could a TTP progam do it? LOL
Post a Comment