What do you think?
Rate this book
The Spoken Language Translator
This original volume describes the Spoken Language Translator (SLT), one of the first major automatic speech translation projects. The SLT system can translate between English, French, and Swedish in the domain of air travel planning, using a vocabulary of about 1500 words, and with an accuracy of about 75%. The authors detail the language processing components, largely built on top of the SRI Core Language Engine, using a combination of general grammars and techniques that allow them to be rapidly customized to specific domains. They base speech recognition on Hidden Markov Mode technology, and use versions of the SRI DECIPHER system. This account of SLT is an essential resource for researchers interested in knowing what is achievable in spoken-language translation today.
356 pages, Paperback
First published August 28, 2000
1 person is currently reading
115 people want to read
About the author
Manny Rayner
45 books16k followersMany people have been protesting against what they describe as censorship on Goodreads. I disagree. In fact, I would like to say that I welcome the efforts that Goodreads management is making to improve the deplorably low quality of reviewing on this site.
Please, though, just give me clearer guidelines. I want to know how to use my writing to optimize Amazon sales, especially those of sensitive self-published authors. This is a matter of vital importance to me, and outweighs any possible considerations of making my reviews interesting, truthful, creative or entertaining.
Thank you.
Please, though, just give me clearer guidelines. I want to know how to use my writing to optimize Amazon sales, especially those of sensitive self-published authors. This is a matter of vital importance to me, and outweighs any possible considerations of making my reviews interesting, truthful, creative or entertaining.
Thank you.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 3 of 3 reviews
December 19, 2017
Definitely one of the two three four five best books by me!
October 26, 2012
In this book you learn how important it is to speak language rather than mumble it. For example, if I said to you: “Hum ma num ma mum pa lo ma oh,” you would take me for a lunatic. If I said: “Hello there, my name is Greg. My role in this narrative is vital,” you would understand me. Of course, you can’t translate spoken language, you need to write it down and then translate it, so this title is silly and misleading. Apart from these criticisms, I believe this might be the most important academic text since Lydia Barthes’s On the Importance of Crushing Harold’s Balls in a Vice.
Want to read
November 23, 2009Thoughts while reading this.
p. 3 Well, I've been getting the smallest idea of SLT over the last months, but I mean small. I only just know where the on/off switch is on my computer, so my perspective is of somebody completely ignorant.
The first thing that comes to mind, reading the introduction, is what an incredibly difficult, ambitious thing it is, SLT. I'm sure the authors do not oversell it when they say, p. 2 that if it could fulfill all its aims it would transform human society.
The second thing is that this book was written in 2000 and, as far as I can see, not revised for the 2007 edition. Surely much must have changed. And surely the resources of larger computers make an ongoing difference?
It must be incredibly frustrating to be in fields where one is waiting, waiting, waiting for what is ongoingly inevitable, the increasing power of computers that will permit progress. To have to wait for technology to catch up with ideas. Oh dear.
The next thing I find myself thinking, when the authors discuss the need for accuracy, is the difference between a human translator and a computer. I wonder if an important aspect of intelligent translation is that a human, having made a mistake, may well soon enough recognise and correct it in whatever way might be appropriate.
Can SLT do that? Is this something it would need deep reasoning capability to achieve? Is it possible? It seems to me that however accurate one hopes to make the system, the possibility of being able to recognise mistakes would be a great asset.
Well. Food for thought as I cook dinner. All my technology is up to the task, I'm so lucky.
A couple of days later...
By p. 6 (!) I thought I was on a roll....but suddenly, as you read p. 6, your eyes are disconcertingly drawn to p. 7. They hit you with something that made me get out my garlic necklace, worn as a rule only when reading Manny's Stephanie Meyer reviews. Little did I know it would come in handy for a science text book. So, I put on my garlic necklace and anything else I hope will ward off evil. Dear reader, you are probably already thinking 'oh no, not -' Yes, I'm afraid so. It's a flow chart. My eyes glaze over and I dare say yours too.
Now, my attitude when I picked up this book was to do it properly. The authors wanted me to read a flow chart, I'd damn well read it, if it killed me. Back in a bit.
8 hours, 16 cups of tea and 5 scones later, I have a pain in my stomach. It's this $%#&@ chart. So, I've tried. Honestly I tried. But it is time to move on. And then I discover something that wll make life easier for the rest of you. The flow chart is explained in words. Ladies and gentlemen, I am back in business.
p. 3 Well, I've been getting the smallest idea of SLT over the last months, but I mean small. I only just know where the on/off switch is on my computer, so my perspective is of somebody completely ignorant.
The first thing that comes to mind, reading the introduction, is what an incredibly difficult, ambitious thing it is, SLT. I'm sure the authors do not oversell it when they say, p. 2 that if it could fulfill all its aims it would transform human society.
The second thing is that this book was written in 2000 and, as far as I can see, not revised for the 2007 edition. Surely much must have changed. And surely the resources of larger computers make an ongoing difference?
It must be incredibly frustrating to be in fields where one is waiting, waiting, waiting for what is ongoingly inevitable, the increasing power of computers that will permit progress. To have to wait for technology to catch up with ideas. Oh dear.
The next thing I find myself thinking, when the authors discuss the need for accuracy, is the difference between a human translator and a computer. I wonder if an important aspect of intelligent translation is that a human, having made a mistake, may well soon enough recognise and correct it in whatever way might be appropriate.
Can SLT do that? Is this something it would need deep reasoning capability to achieve? Is it possible? It seems to me that however accurate one hopes to make the system, the possibility of being able to recognise mistakes would be a great asset.
Well. Food for thought as I cook dinner. All my technology is up to the task, I'm so lucky.
A couple of days later...
By p. 6 (!) I thought I was on a roll....but suddenly, as you read p. 6, your eyes are disconcertingly drawn to p. 7. They hit you with something that made me get out my garlic necklace, worn as a rule only when reading Manny's Stephanie Meyer reviews. Little did I know it would come in handy for a science text book. So, I put on my garlic necklace and anything else I hope will ward off evil. Dear reader, you are probably already thinking 'oh no, not -' Yes, I'm afraid so. It's a flow chart. My eyes glaze over and I dare say yours too.
Now, my attitude when I picked up this book was to do it properly. The authors wanted me to read a flow chart, I'd damn well read it, if it killed me. Back in a bit.
8 hours, 16 cups of tea and 5 scones later, I have a pain in my stomach. It's this $%#&@ chart. So, I've tried. Honestly I tried. But it is time to move on. And then I discover something that wll make life easier for the rest of you. The flow chart is explained in words. Ladies and gentlemen, I am back in business.
Displaying 1 - 3 of 3 reviews