Speech recognition used to be horribly inaccurate. It only worked for a handful of people a handful of the times. But now it's pretty good, thanks to the combined efforts of Nuance, Microsoft, Apple, and Google, who have thrown in countless resources to really improve it.
Of all those companies, few have matched Google's commitment to voice recognition, which has made it a cornerstone of its mobile and services strategy.
One of Google's first forays was the short-lived Corta-411 (or Google Voice Local Search). It launched in 2008 and allowed people to look up business phone numbers using their voice. Speech recognition technology has also been a centerpiece of Android, and with the release of JellyBean, what are the biggest improvements in Android 4.2 and 4.3? What are the biggest improvements in Android 4.2 and 4.3? If you're stuck on 4.0 Ice Cream Sandwich or 4.1 Jelly Bean, should you upgrade? Read More
Earlier this week, Google finally introduced speech recognition in Google Docs.
Users can literally dictate your documents (as I am doing with this article) without the need to install any additional software or plugins. It's a significant step for the online office suite, but is it a good thing?
Before I start digging into its features, I want to mention how it gets Google Voice Typing. If you have a Google account, you already have this. Simply open Google Docs and open a new or existing document. Then a window will appear asking if you want to try voice dictation. Click Try it .
Then you have to give Google Docs permission to use your microphone. That's just a matter of clicking. Allow to a popup window.
Next, you need to select the language you want to use with Google Voice Typing. The range of languages and dialects on offer ranges from English and Spanish to Afrikaans and Arabic.
Then click on the microphone icon and start talking.
One of the biggest obstacles to speech recognition reaching the mainstream is that it's often not accurate enough. . It used to be a fact that if you see the use of speech recognition, you will have to spend a few hours editing and proofreading your text. So how is Google doing on offer in this regard?
Pretty favorably, actually . For the most part, Google Voice Typing understood what I said, even though I have a regional accent in English (we'll talk about accents later ).
I was particularly impressed with how Google's voice recognition handled background noise. As I was writing this article, a Yorkshire Terrier was barking in my living room and my window was partially open. I live on a busy street where cars are constantly passing by. But despite that, Google was able to filter that out and focus on what he was saying.
The biggest problem was that Google Voice Typing often struggled with punctuation. I would say “comma”, “period” and “full stop”, and I would interpret it as me wanting to write. "comma", "period", and "full stop". This was frustrating for two reasons.
Firstly, because it would provoke me, using the correct punctuation first, before immediately going back to the written version of the word. There was no way to stop this, and you would have to manually edit the document to correct it.
But, perhaps worse, I couldn't stop it from happening. There is no dictionary where you can override the spelling. It just happens, and you have to deal with it.
I don't want to underestimate how frustrating this is. It's very annoying . But it's also something I'm confident will get better as more and more people use this feature, and as Google commits more resources to improving its speech recognition.
Other than that particular annoyance, I was quite pleased with the accuracy of Google's speech recognition.
I was surprised by the number of languages and dialects that Google Voice Typing supports. In English only, it supports dialects from New Zealand, Australia, India, South Africa, the United States, and Great Britain, to name just a few. The problem is that there really isn't an American accent, just as there isn't a British accent. Rather, there is a variety of accents and dialects that differ from place to place.
It is true that the United Kingdom has an accent for each postcode. The MakeUseOf team has a range of different accents amongst the British staff. Christian Cawley speaks with a thick Middlesbrough accent. Rob Nightingale, who hails from Southport, has a more northern accent. While Mark O'Neil has a Scottish twang.
I live in Liverpool, so I have a Scouse accent that shifts slightly towards the Atlantic, largely thanks to my American girlfriend and time spent living in Switzerland.
And it's fair to say that speech recognition programs often struggle to understand regional English dialects. When Siri came out, for example, her inability to understand Scottish users became a joke..
But Google's offer was exceptional. Trust me when I tell you that you won't have to practice speaking with a different accent. What apps and websites will help improve my accent when speaking another language? What apps and websites will help improve my accent when I speak another language? I really want to make my pronunciation match that of a native speaker. Is there an app or website that can help me? Read more . I've talked to a handful of friends who also have a regional English accent, and they've had similarly positive experiences with it. While I admit it's a small sample and completely unscientific, it's certainly promising.
Speech recognition programs have traditionally been limited by an inability to keep up with the speed dictated by the user. Admittedly, I was a little concerned that Google's offering was no different, especially since it's an online service, rather than a program that runs on my MacBook Pro.
But I was impressed. Google was able to keep up with my high rate of caffeine and was not a bottleneck for my productivity. It was the complete opposite of my experiences with other voice dictation tools.
I don't know if that was because I have fast FTTC (Fiber to the Cabinet) What is the difference between FTTC and FTTP and why should I care? What is the difference between FTTC and FTTP, and why should you care? We have all been there at one time or another. Sick of our Internet service, looking for a new way to connect to the Internet, but confused by the different options. Read More Internet connection at home, or the fact that Google has an unlimited supply of fast servers at your disposal. Either way, I was able to do things.
Built-in microphones tend to be hit or miss. In my experience, they're either great, like they are on Apple laptops, or they're not. There is rarely a happy medium.
As a general rule of thumb, the cheapest laptops are the best laptops under $300:everything you need to know the best laptops under $300:everything you need to know Finding a good laptop under $300 it's almost impossible these days, but it can be done if you know what to look for. Here you will find everything you need to know to make a purchase. Read More It's just one of those features that device manufacturers often overlook.
I started dictating this article using my MacBook Pro's internal microphone. Although Google Docs frequently said it was having trouble hearing me, that didn't translate into slower or inaccurate dictation. Everything worked fine.
I also tried Google Voice Typing with an expensive Yeti external microphone. These are podcast-quality microphones that retail on Amazon for over $100.
Blue Yeti USB Microphone - Silver Blue Yeti USB Microphone - Silver Buy Now On Amazon $94.49
It is true that I did not notice any difference in terms of accuracy or speed of dictation. However, the biggest advantage of using this mic was that I was able to plug in a pair of AKG headphones and use them as a monitor. This allowed me to be more aware of background noise and self-adjust if I was being too loud or too quiet.
Google's voice recognition isn't perfect. But that's not a surprise, as solid speech recognition is a pretty difficult feat to pull off. There are many things that I felt could be improved.
This primarily focuses on how the software treats punctuation and sentence structure. In an ideal world, Google would automatically insert punctuation based on the rhythm and cadence of your voice, but we're a long far from that.
It's also a shame this software hasn't yet found its way into other Google offerings, like Gmail. Ideally, I'd like the opportunity to download Google Voice Typing as an app, and use it with other pieces of software, like iWork Pages. Pages 5.0 for Mac Includes the Smart Inspector Panel, But Fewer Features Pages 5.0 for Mac Includes the Smart Inspector Panel, But Fewer Features There are many lightweight and easy-to-use text editors for Mac users, but for projects that require desktop publishing features, Apple's recently revised pages are still a good solution. Read More o IA Writer Markdown Editor iA Writer for Mac and iOS:The Best Word Processor You've Ever Used iA Writer for Mac and iOS:The Best Word Processor You've Ever Used, whether it's a school newspaper or a publication blog. all of us, at some point, find ourselves in the position of having to dump a bunch of characters into a text file. While the cell phone ... Read more .
But those are two minor annoyances, Google Voice Typing is as good as it gets. For contrast, I wrote this section of the article using OS X's built-in speech recognition, and it was neither as accurate nor as fast.
If this doesn't persuade people to switch to Google Drive, I don't know what will.
Now to you! Have you been tempted by Google Drive's voice recognition? Have you already tried it? Tell me all about it in the comments below..
