For a long time, speech recognition was going to be the next big thing. People would dictate documents naturally and flawlessly in half the time that they could type them, freeing up time for other activities. Eventually, however, people became tired of waiting for speech recognition to reach an adequate standard for regular use, and the concept became derided as a novelty and unusable for day-to-day work.
Now, however, speech recognition has come of age and it's sneaked back into people's lives via a side entrance. Google, Apple and Microsoft all have speech recognition functionality built into their mobile operating systems, and you don't have to go out and buy a CD from which to install it as was the case during the first wave of interest.
Speech recognition software has followed the classic Hype Cycle: an initial burst of inflated expectations followed by a trough of disillusionment, a gradual enlightenment about the technology's actual usefulness, and an eventual levelling out of productivity.
There is logic to using speech recognition software on mobile devices, because often it can be quicker and easier than fiddling around with an on-screen keyboard. Mainstream adoption of speech recognition software on desktop PCs, however, has never happened. That may be partly due to people recognising some of its limitations, its perceived lack of suitability for an office environment, or simply because people moved on and just forgot about it.
Whatever the reason, speech recognition software is now at the level for which people had initially hoped. It is accurate, useful and gradually beginning to bleed into our lives.
There are a variety of different speech recognition tools and software packages, each offering specific functionality. Some are more fully loaded and advanced than others, but generally, they can be used for controlling a user's computer and dictating to a document. This article provides an overview of some of the most popular speech recognition tools and software packages available.
Nuance's Dragon NaturallySpeaking software is regarded as the market leader where speech recognition is concerned. NaturallySpeaking was launched in 1997 and is now up to its thirteenth iteration. There are a host of versions available depending on the user's requirements and the software offers a huge amount of functionality. According to Nuance, NaturallySpeaking is the world's best-selling speech recognition software for the PC.
NaturallySpeaking Professional Edition aims to provide business users with a means of controlling their computers and dictating documents, and Nuance claims it is three times faster than typing. As a result, it says, productivity can be improved and cost savings made. Amongst the functionalities provided are the capabilities to manage email, search the web and automate business processes.
NaturallySpeaking allows users to dictate into Microsoft Office applications and OpenOffice, create emails, tasks and meetings in Microsoft Outlook, search the web using any major browser, and post to social media services such as Facebook and Twitter. The software recognises a number of standard commands, such as creating files, scheduling calendar entries and searching a user's computer. It's also possible to set up custom commands.
Beyond its desktop functionality, Nuance can automatically transcribe user dictations into approved voice recorders, and mobile apps are available for iOS or Android. iOS users can record audio files whilst Android devices can be used as a wireless microphone.
NaturallySpeaking Professional Edition costs £549. Prices vary for other editions, depending on the functionality. For more information on the package, check out our full Dragon NaturallySpeaking Premium 13 review.
If you only need basic speech-to-text dictation functionality, then TalkTyper may well be adequate. TalkTyper is a simple, free-to-use website that captures user speech and renders it in plain text ready for being copied and then pasted elsewhere. It's not possible to sign up for an account, meaning that the website is designed simply for immediate and straightforward use.
TalkTyper was created with the aim of making voice dictation freely available to anyone who needed it. According to TalkTyper, it first became possible when Google added speech input functionality to its Chrome browser.
Once a user has loaded the TalkTyper website, they can click the microphone button and begin dictating. In addition to basic dictation, users can add basic punctuation by using commands like "period", "question mark" and "new paragraph".
If they are happy with the resulting text, they can add it to their saved text pad. Having finished their dictation, the user is able to add symbols, copy the text, print it, send it to Twitter, send it via an email or translate it into a different language.