Windows Speech Recognition

06
2014-04
  • Spike

    Why is Windows Speech Recognition (the app) in Windows 8 and 8.1 so pathetic?

    I've been using it since they first put it on their OS years ago and it has hardly improved in the slightest.

    It still has a hard time understanding the most basic things. And I don't want this to turn into a hardware debate. My hardware is fine and I've tried cheap junk and really expensive hardware. I've tried headphones (with a Mic) and I've tried desk microphones and I am now using a mic that's built into my new all in one pc. So far this is the best mic I've had, by far. But still - Windows Speech Recognition is pretty much useless for any task.

    I know Speech is difficult. But I also know that they can do MUCH better than this. I know this because I own a (one of the cheapest models) HTC 8S (Windows Phone) and it has the BEST recognition I have ever used in my entire life. It almost always understands what I say - 100% of the time. What I don't understand is why can't they use their brains for a change instead of letting their products die. Why can't they realize they have great Speech recog on their phones and find a way to incorporate this tech into the Windows OS on the PC?

    And if by any chance they are using the same stuff on the PC that is on the phone, then they must have made changes because it's completely **.

    So I've been looking for maybe an update or a new version of Windows Speech Recognition app, but have not been able to find one. Is there any way I can drastically improve the accuracy of this thing?

    • Answers
  • Saurabh Sharma

    The only solution for now is to "Train Computer to better understand you":

    Control Panel\Ease of Access\Speech Recognition

    In other case, you can modify some issues by Speech Dictionary: Right Click Speech Recognition bar > Open the Speech Dictionary

    And I think Microsoft is bringing a solution to above problem in next Windows code-name Threshold. see http://www.bing.com/dev/en-us/dev-center. They are also bringing Siri like voice assistant over next release of Windows Phone OS.


    • Related Question

    voice - Speech recognition - MP3 to text software
  • pako

    I'm looking for a speaker independent program (commercial or free) that would enable me to transcribe MP3 files containing speech recordings (especially podcasts) to text. I wanted to try Dragon Naturally Speaking, but it seems like it only supports transcribing my own speech recordings. So what are the alternatives?


    • Related Answers
  • moioci

    Dragon Naturally Speaking will import mp3 files and try to transcribe them. It prefers to tune its voice recognition to the individual speaker, but does a fair job without tuning. It would probably work best if your podcast speakers sound like Tom Brokaw.

  • studiohack

    One possible solution would be to upload your video to Youtube, and try the automatic captions that you can enable...it is not too accurate yet, but you can download the captions file and edit it yourself, if that helps...as for copyright/piracy issues for the song, you could make the video private on your profile, if that's even possible?

  • Zach

    Podzinger would be a great solution, but I'm not sure that ramp (the new name for the company that used to be EveryZing, who produced Podzinger) offers the service for free anymore...

    http://en.wikipedia.org/wiki/Podzinger

  • nvuono

    I would warn against trying Dragon Naturally Speaking--I wrote some scripts on my jailbroken iphone to copy/convert all the voicemail files from my phone to a folder on my PC and had the Dragon Naturally Speaking transcription service run against them.

    The result of running the transcription against files with different speakers was absolutely unusable. I've tried some of the open source alternatives but speaker-independent voice recognition still seems limited to very small dictionaries.