On Thu, 26 Oct 2006 12:17:49 +0200, Dave Long wrote: > > There's good voice-recognition software that supposedly needs about > > 15MIPS (ViaVoice) to run in real-time, and you may not even need > > real-time. I don't know how much bandwidth to how much memory > > speech-recognition needs, though. > > Looks like a fair amount: ViaVoice not only specs system memory > (64-96M) but also 256K of L2 cache. There are some people nearby > working on automatic segmentation/speaker recognition/tagging and > search, etc., and they use serious crunch for their applications, but > maybe they'd have some ideas for what sorts of things could be done > cheaply.
That's unfortunate. There might be some tradeoffs available between memory use, CPU use, vocabulary size, market size (as restricted by patents) and well-known-ness --- Walsh transforms might be "good enough" but not well-investigated, but need less memory, for example. Maybe I should ask Eric Brewer.
