tag:blogger.com,1999:blog-6005334108330583722.post1046563965428591409..comments2010-11-27T00:26:34.534-05:00Dawnhttp://www.blogger.com/profile/00149191486108175617noreply@blogger.comBlogger8125tag:blogger.com,1999:blog-6005334108330583722.post-86745531265797741062010-11-27T00:26:34.534-05:002010-11-27T00:26:34.534-05:00Hi,<br />You might find some ideas I described on stickyminds useful? Improving the Accuracy of Tests by Weighing the Results<br />http://www.stickyminds.com/s.asp?F=S11983_COL_2JulianHartyhttp://www.blogger.com/profile/15418816908129476730noreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-10576993508398317352010-10-22T18:17:07.689-04:002010-10-22T18:17:07.689-04:00I would like to first understand the voice recognition system. Understand the region demographic area that will be deployed for accents. Once I had that understood I could start on the translation software. Each component would introduce possible failures but broken down in functional components you could redirect probably with a database of unusual posts to start correction process. Take some time and in this case as much as I hate the words - test quality in!.....blak, cant believe I said that.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-54472962357344238292010-10-07T15:45:38.016-04:002010-10-07T15:45:38.016-04:00A related problem:<br /><br />web says:<br />component current fault<br /> CPU 1 26.00 85 <br /><br />telnet says:<br /> cpu 1 n/a 85<br /><br />Now I don&#39;t know what the current temp is but<br />1. I know they should be same.<br />2. I know they should have a value between 0 and 200<br />3. I know it should have a bounds of about 2C up or down on each check within same day or something is wrong.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-34962124616770093982010-10-01T00:37:54.463-04:002010-10-01T00:37:54.463-04:00Interesting Post.Software Testinghttp://www.qaguild.comnoreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-29453450559844403752010-09-22T16:32:08.873-04:002010-09-22T16:32:08.873-04:00It is pretty obvious that they are testing words.<br /><br />I remember vividly --<br />when we were very young we loudly sang <br />&quot;My country tis of V sweet land of livery&quot;<br /><br />It didn&#39;t make any sense - much of what we did in school did not make any sense, esp when you&#39;re four.<br /><br /><br />Croud Sourcing might work if you can mostly trust the testers / users.<br /><br />please press 2 for no good. Some telco did that for awhile. They asked for feedback on their automated system <br /><br />It is pretty obvious that they are NOT parsing the sentence. This is a difficult problem - but in the same order of magnitude of voice to text.<br /><br />if you Knew the type of communication - you could filter for the words one used to not say on TV .. like ass which should not be in business communication.<br /><br />if you had some semantic parsing .. large step up . you could verify some of the info -- like you are not your own child.<br /><br />in related news...<br />You could check if they were same .. same sentence said by different speakers should at least agree. Here all three were different.<br /><br />if you had a text to speech .. you could run it back and compare .. speech to text .. text to speech <br /><br />assuming you had that technology - which may or may not exist.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-88581409259147666822010-09-21T22:00:33.318-04:002010-09-21T22:00:33.318-04:00Intresting post. <br /><br />Another difficult software would be optimization algorithm.<br /><br />&quot;How can you confirm whether the result is truly optimal ?&quot; <br /><br />Coming back to Google Voice- I guess you will have to break the test into smaller components<br /><br />A) Does it detect the language (and then stop trying to make a fool of itself - if its not English) ?<br /><br />B) Test words rather than sentences<br /><br />C) Test the words together in a sentence after they pass individual tests.RNhttp://www.blogger.com/profile/07430438348232305102noreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-80533386892342778782010-09-01T14:28:50.718-04:002010-09-01T14:28:50.718-04:00I&#39;ve actually worked on a voice transcription project before, and I can tell you, that even a few years ago, that it often takes a lot of time to train the translation software before it can be relied on as reliably accurate.<br /><br />I&#39;m not sure how you&#39;d go about testing something like this and verifying that A B or C is the correct translation. I can remember as a child, waiting for my mother&#39;s soaps to go off so I could watch some cartoon, and I was almost convinced that Central And Mountain was some place or show LOL.Veretaxhttp://www.blogger.com/profile/03855355676637483294noreply@blogger.comtag:blogger.com,1999:blog-6005334108330583722.post-52203984710452063482010-08-31T22:17:37.382-04:002010-08-31T22:17:37.382-04:00very related: https://www.socialtext.net/writing-about-testing/index.cgi?breaking_the_bug_reporting_rules<br /><br />This is a huge gaping hole, let us find some answers.Chris McMahonhttp://www.blogger.com/profile/16339861008904941703noreply@blogger.com