Talk:List of speech recognition software

Untitled

Article merged: See the old talk pages here and here.

Just in case somebody wonders why I changed the article:

• VoxForge is not speech recognition software but a free speech corpus and acoustic model repository.
• "Free Software implies "Open Source" and all of the listed projects are actually Free Software, none is merely Open Source (which, by the way, can be proprietary as well!). 62.226.31.103 (talk) 19:18, 25 February 2009 (UTC)

No, free implies you don't have to pay for it. Not all opensource software is free. --97.67.109.242 (talk) 16:52, 14 December 2012 (UTC)

There's a long introduction at the beginning of this list that's unnecessary. Since this is just a list of software, I think it should be removed, can somebody confirm this? 128.138.64.196 (talk) 03:27, 16 April 2009 (UTC)

I'd agree that the long introduction is not necessary. It could, however, maybe be used in the Speech Recognition article. Crusher7485 (talk) 20:13, 30 April 2009 (UTC)

The introduction doesn't seem to belong, and it doesn't cite any sources. It also reads like a personal reflection on speech recognition, rather than an encyclopedia article introduction. I've added the "citation" and "tone/style" templates to the introduction section. Of course, if this section is moved, I'd recommend moving the templates with it. Fire (talk) 17:35, 30 July 2009 (UTC)

Agreed. The tone and style are inconsistent with Wikipedia or any encyclopedic style. Also, the many examples have nothing to do with the topic -- a LIST of voice recognition software. The tone also seems almost like an essay someone wrote for a class and decided to drop in here. The information (though uncited) may be valid and useful, but the delivery is awkward and, for this particular enrty (a list of software) inappropriate. Perhaps some of the information presented could be merged into the voice recognition article. Finally, also agreed that it takes too long to get to the meat of the article -- the list itself. Parenthetically -- it might be useful to create a matrix of voice recognition accuracy percentages across applications. --68.183.146.87 (talk) 10:39, 26 November 2009 (UTC)

This article would be better if instead of just listing all the applications, it was a comparison of the underlying recognition engine and the features of each. Comparison_of_speech_synthesizers is a similar field that has such a page. Ksevio (talk) 14:00, 8 April 2011 (UTC)

External links

I just removed the entire external links section, since it'd been tagged for cleanup since January of 2012 and it was 23 links, all of which went to various products.

Links I removed were:

• Verbio ASR Automatic Speech Recognition & TTS
• MIRSK Digital
• VoiceAttack
• SpeechGear
• Auditory Sciences
• Sonic Extractor
• e-speaking
• Freesr Free Speech Recognition Software
• iSpeech Speech Recognition and Text-to-Speech
• AT&T Watson
• Loquendo ASR
• LumenVox
• Tatzi
• Clap Commander
• Voice Finger
• Dragon Medical
• Simon GPL, to help disabilited persons
• VoxSigma speech-to-text software
• iATROS speech recognition software
• RWTH ASR
• Speech To Text Software Information
• Speech Recognition Software Tools Directory
• MediaInsight speech recognition technology and services

--rahaeli (talk) 18:00, 30 May 2013 (UTC)

Organize into a wikitable

This article needs some significant clean up. I think the best way to organize would be to put everything into a large table with columns for "Title, Description, Website, Open Source, License, Operating System." --WikiTryHardDieHard (talk) 17:01, 5 January 2014 (UTC)

External links added for speech recognition software

Hi all,

I just added a sub-title for web-based software, as it is a new rising thing, and very powerful (and free). I thought of adding the following 2 external links, that I would like you to review - and decide whether to add or not.

The following list presents notable speech recognition software that operate in browser as web apps. They make use of HTML5's web-speech-API. They gain popularity as they are usually free, do not require installation and give good results as they use Google's engines for the speech recognition itself.

Application name	Description	Website	Open Source	License	Price	Note
Dictation	Speech Recognition in the Browser	https://dictation.io/			Free
Speechlogger	Natural Speech Recognition & Translation	https://speechlogger.appspot.com/	Yes		Free

Thanks,

Ronen Ronen Rabinovici (talk) 19:52, 27 October 2014 (UTC)

CMU Sphinx multi-platform not just Linux

The current Wikipedia article on CMU Sphinx says that Sphinx 2 was "released ... at LinuxWorld in 2000". However, "Sphinx 4 is a complete re-write ... entirely in" Java and is Cross-platform. I assume that's the same as "multi-platform". I plan to change this current article to say that CMU Sphinx is multi-platform. If it's not, I hope someone will fix the issue both here and in the article on CMU Sphinx. DavidMCEddy (talk) 17:02, 4 June 2016 (UTC)

Inclusion criteria

I think one of the common methods for determining what entries to be included should be used:

1. Only include entries with their own Wikipedia articles
2. The above as well as entries verified by independent sources.
3. Both of the above as well as entries of products from notable corporations with their own Wikipedia articles.

Thoughts or other ideas? --Ronz (talk) 19:05, 5 December 2016 (UTC)

Adobe Premiere Pro

You should include that PPro has speech-to-text recognition since at least CS4: [1]. --2003:71:4E16:4B24:DCAF:A475:D717:A (talk) 18:44, 12 January 2018 (UTC)

Okay, I've googled some more, and while the feature was introduced with CS4 (released c. 2008/9), it was dropped again by CC2015 (aka PPro 8) because Adobe felt the software wasn't developing fast enough in newer versions: [2]. Still some more googling turned up that Adobe's solution was basically a plugin bought from Speechmatic (not to confuse with SpeechMagic already mentioned in our WP list here), who are still selling the tool as a standalone program to business customers: [3] --2003:71:4E16:4B24:DCAF:A475:D717:A (talk) 19:14, 12 January 2018 (UTC)