On Tue, Apr 9, 2013 at 9:42 AM, Chris Warburton <[email protected]>wrote:
> > My intuition, based on a very limited course on speech recognition at > University and my own heavy bias towards programming languages, is that > 'serious' use of speech commands will end up evolving some terse, > phonetic, unambiguous vocal programming language. A related point: vocal non-speech recognition is considerably faster and more accurate than speech recognition. I was pointed to James Landay's extensive works when I queried about this in the past [1]. From one such paper: "The results from the study validated our hypothesis that non-speech voice input can offer significantly faster discrete input compared to a speech-based input method by as much as 50%." [2] [1] http://homes.cs.washington.edu/~landay/pubs/publication-list.htm [2] http://dub.washington.edu/djangosite/media/papers/voice-games-interact2011.pdf > I also think that tonal audio output may be preferable to spoken output > as the amount of data increases. For example, imagine a service monitor > that hums along as requests are processed, becoming discordant when it > starts seeing error messages. This lets us internalise the status of the > system, noticing immediately when something is out of the ordinary. > Indeed! Tonal output is something I've experienced when I was young, but I haven't seen much over the last couple decades. I would like tones for my on-screen phone keyboards, so I know what buttons I press without looking. I've also been thinking about applications in security systems - e.g. associating tones with faces or machine-recognition of behaviors.
_______________________________________________ fonc mailing list [email protected] http://vpri.org/mailman/listinfo/fonc
