ALTERNATE SPEECH ENGINES

 

In the event that your installation of Windows does not contain a speech engine, or the installed speech engine has become corrupt, there still may be a way for VoiceAttack users to still be able to use speech recognition. Although not a guaranteed fix, this section outlines some new options that are available for you to try.
(TLDR; Click here)

Alternate Speech Engines for VoiceAttack

For certain locales, Windows will come with a speech engine pre-installed. These are actually very good speech engines, with very high accuracy and even come with dictation facilities. The downside is that if you do not speak one of a select collection of languages (English, German, Spanish, French, Chinese or Japanese), your copy of Windows might not come with (or might have a different version of) a speech engine that you can use effectively. The latest version of VoiceAttack makes an attempt to provide a way for an alternate speech platform to be used. With the latest version of VoiceAttack, you will be able to install Microsoft's Speech Platform 11, along with your choice of a longer list of speech recognition engines in various languages. With the addition of the new speech platform, you will also have the opportunity to download from an equally extensive list of text-to-speech synthesizers (TTS voices).

Of course, there are some drawbacks to this alternate speech platform, and they are the reasons why VoiceAttack was not implemented with it in the beginning (however, there is a silver lining... more in a moment):

First, you have to install MORE software. The files are not huge (and they don't take that long to install), but its just MORE software to manage.

Second, dictation functionality is not provided with this platform. Not a big deal for just about everybody, but for the few that want to use VoiceAttack to accept, 'freeform' speech, they won't be able to do so.

Third, since the dictionary that the speech engine uses is based solely on your commands, you will need to set a high confidence level (greater than 75). Otherwise, the speech engine will try to make a best guess at what you are saying and that will usually not end well.

Fourth, 'unrecognized' commands will not be reported in the log, as the speech engine does not raise any event when a voice command is unrecognized.

Fifth, recognition is very good, however, it is never as good as a speech engine that is trained to your individual voice. Which leads to the silver lining: The speech engines in this platform do not require voice training (I can hear the cheers).

To get started with the new speech platform, you first need to install the Microsoft Speech Platform runtime. You can usually find this on Microsoft's site, or you can download it from the VoiceAttack.com site:

If you are using the 32-bit version of VoiceAttack, you will need the 32-bit runtime:
Click here to download the 32-bit Microsoft Speech Platform Runtime (2.5 MB)

If you are using the 64-bit version of VoiceAttack, you will need to download the 64-bit runtime:
Click here to download the 64-bit Microsoft Speech Platform Runtime (2.6 MB)

How to find out what version of VoiceAttack you are running (32 or 64 bit):
If you go to VoiceAttack's Options screen and the title bar includes "64-bit" (for example "VoiceAttack v1.8.9 64-bit"), you are running the 64-bit version of VoiceAttack. If you only see the version number, you are running the 32-bit version of VoiceAttack. Note: You can navigate to the Options screen by clicking the small wrench icon in the lower-right corner of the main screen.

Once you have the platform runtime installed, you will then need to pick the appropriate speech engine and TTS synthesizer(s) you would like to install. Again, these can be downloaded from Microsoft's site, or you can download them from here:

Click here to browse the Microsoft Speech Platform Runtime speech engines


Once you have the runtime, speech engines and/or TTS synthesizers installed properly, VoiceAttack will detect them the next time VoiceAttack is launched.


Some things to note:

You don't have to have BOTH the speech engine and the TTS synthesizer installed to work. You can have either one or both, depending on what you want to do.

If your system already supports a preinstalled, working speech engine, for fun you can install the alternate speech platform and try out the speech engines and/or text-to-speech synthesizers. Once the alternate speech files are installed, the options for selecting which platform to use can be found on the System/Advanced tab of the, 'Options' screen. Also, if you would like to try adding additional speech engines for English, German, Spanish, French, Chinese or Japanese to Windows, and your copy of Windows supports it, check out this How-To in the VoiceAttack User Forums for information on installing additional languages: http://voiceattack.com/smf/index.php?topic=45.0