http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#utm_source=feed&utm_medium=feed&utm_campaign=feed anime - manga - sci-fi - art Thu, 26 Apr 2012 06:03:42 +0000 hourly 1 http://wordpress.org/?v=3.0.2 http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-9 tim Fri, 14 Mar 2008 10:03:37 +0000 http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-9 I don't think the technology works *quite* like you're describing - the user has to be consciously concentrating on the words it wants the system to pick up - not just on what the user hears, or is thinking. It's a little like talking into speech recognition software; it works more effectively if you more pronounced, etc. In other words, there is a VERY conscious effort involved. With that in mind, the procedure I described above for transcribing what you hear actually might be a real pain in the arse... I don’t think the technology works *quite* like you’re describing – the user has to be consciously concentrating on the words it wants the system to pick up – not just on what the user hears, or is thinking. It’s a little like talking into speech recognition software; it works more effectively if you more pronounced, etc. In other words, there is a VERY conscious effort involved. With that in mind, the procedure I described above for transcribing what you hear actually might be a real pain in the arse…

]]> http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-8 flotsky Fri, 14 Mar 2008 09:50:03 +0000 http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-8 I guess you want to pick up a dominant and consistent volume level, and transcribe that. You could ignore sudden loud noises to some extent I think, say you were listening to someone, and another person shouted nearby, you could possibly not transcribe that, sort of like the noise gates or whatever it is you have when you record speech to stop overly loud sound. I guess this is entering into the transcription territories that Google video was trying to deal with at some stage, they were trying to create searchable video, but their solution was just to manually transcribe the key points of a long video. That's kind of fallen by the wayside with them buying Youtube. I guess you want to pick up a dominant and consistent volume level, and transcribe that. You could ignore sudden loud noises to some extent I think, say you were listening to someone, and another person shouted nearby, you could possibly not transcribe that, sort of like the noise gates or whatever it is you have when you record speech to stop overly loud sound. I guess this is entering into the transcription territories that Google video was trying to deal with at some stage, they were trying to create searchable video, but their solution was just to manually transcribe the key points of a long video. That’s kind of fallen by the wayside with them buying Youtube.

]]> http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-7 tim Fri, 14 Mar 2008 09:15:13 +0000 http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-7 Hmmm. I wonder how well that would work. By just concentrating (or focusing - to use the syntax from my story) on what you hear, would it easily transcribe everything? Must be easier than manually dictation? Hmmm. I wonder how well that would work. By just concentrating (or focusing – to use the syntax from my story) on what you hear, would it easily transcribe everything? Must be easier than manually dictation?

]]> http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-6 flotsky Fri, 14 Mar 2008 08:27:14 +0000 http://timmaughanbooks.com/2008/03/13/technology-finally-catching-up-with-me/#comment-6 you want it hooked up with aural transcription, everything you hear is turned into text you want it hooked up with aural transcription, everything you hear is turned into text

]]>