The 2Lingual developers have incorporated the new browser feature into their multilingual search tools and have now provided us with Google Multilingual Voice Search and Twitter Multilingual Voice Search. Both the tools support 51 Speech-to-Text Languages including various regional variations. For example, for English, there’s American English, British English, Canadian English, Australian English, Indian English and South African English.

Obviously, both tools work only in Google Chrome. In other browsers you simply won’t see the microphone icon to speak. Voice Search requires a Speech-to-Text capable browser like Google Chrome version 11.0.696. You’ll also obviously need a headset and microphone to speak into.

1. Search Google By Voice

• To search, click the tiny microphone icon in the search field and say out loud what you want to search for:

• If the tool couldn’t hear you, you will be offered the option to check your microphone settings:

• If what you said wasn’t clear enough, the tool will suggest other possible phrases you were probably going to search for:

If you don’t select any of the suggested alternative search queries, they will disappear in a few seconds.

• If you want to speak any other language, just select it from the drop-down:

• And keep searching:

The tool works surprisingly fast fetching results almost instantly. It does look like a huge time-saver for multi-lingual search engine users.

2. Search Twitter By Voice

Twitter multilingual voice search is a later addition to the tool that lets you search Twitter by voice. Similarly, just click a microphone icon in the search field and speak your search term:

More tools from the same developer which were previously reviewed on MUO:

• 2Lingual: Google-powered Bilingual Search Engine that makes it easy to search in 2 separate languages and provides a query translation option for your cross-lingual searches. I have included this one into my post listing 3 tools to see and compare search results side by side.
• 2lingual: Bilingual Twitter Search: Another two-language tool for Twitter.

Other Voice Search & Speech Recognition Tools:

• Tazti – Search Web, Play Music & Control Programs using Voice: a desktop speech recognition software;
• VoiceSearch: Adds Voice Search To Google Chrome: a Google Chrome extension that lets you search by voice. The supported sites include Google, Bing, Wikipedia, YouTube, Wolfram Alpha and DuckDuckGo
• Taskos: To-do List App That Responds To Voice Commands: a free smartphone app for Android phones. Through this app you can create new tasks using voice commands.

The tools look both fun and useful and they may come in handy for heavy search users. What do you think of them?

Android’s voice software is easy to customise and is already ready to use RIGHT NOW on your Android phone. There’s no need to scour the Android market for decent speech-to-text software because you already have access to it. It’s also unlikely you’ll need to find a paid alternative because this works quite well. I think you’ll be surprised.

Set Correct Dictionaries

First, make sure your phone is set up to use the correct dictionaries. Go to Settings > Voice Input and Output Settings.

Choose Voice Recognizer Settings > Language. You can fine-tune the input language not just with basic language differences, but with local accents. Your Android can differentiate between Canadian English and American English, even if most of the rest of the world can’t. I’m clearly in need of the Australian English variety, myself.

For the text-to-speech (TTS) capabilities you’ll need to go into Text-To-Speech Settings > Language. There’s not as much choice as for speech input, but you can at least pick from a few popular languages and accents. Test out the speech synthesizer by clicking Listen To An Example. Here is also where you can change the speech rate and lock in your settings to ensure applications don’t override them with their own settings. To do this, check the box for Always Use My Settings. Note that to use text-to-speech the application will need to have been written to support it.

How To Use Android Speech-To-Text Capabilities

Right, now you should have a go at using your voice features. To use your voice to write something, head to any application, find a text field and bring up the keyboard control for entering text.

Then, just to the left of the space bar you’ll see a button with a microphone and two letters indicating your language input settings. Hold that button down and your phone will ask for voice input rather than keyboard input. If you don’t hold it down long enough you will see a menu where you can change the language. This is also a useful feature, but not what you’re after right now.

A window will pop up saying “Speak Now“. Speak into the phone clearly and use full sentences. When you want to use punctuation you’ll need to speak the name of the punctuation mark. Sadly, despite my Aussie settings I still needed to use American punctuation mark terminology. So, to enter a full stop (a.k.a. a period) you’ll say “Period” to get the punctuation mark entered.

What Else Can You Do With Speech in Android?

For starters, remember that this speech-to-text function is available anywhere you can use the keyboard. That’s pretty versatile! You could dictate whole blog posts by sending yourself an email to edit later.

Android 2.2 (Froyo) also lets users search Google using speech and to use voice commands — Grab this Google Voice Search application to get going and check out this post for more information. You can even phone friends using speech only. Some applications are voice-compatible and will allow you to enter commands using your voice. This leads to some nifty ideas: think about how useful brainstorming could be with a to-do list which understands voice commands and lets you enter text with your voice. If you’re just getting into using voice on your phone, you should also read about The 5 Coolest Voice Apps For Your Android Phone.

How does Android‘s speech-to-text suit you? Does it save you time? Does it understand your accent? What do you use it for? Let us know in the comments!

For years, I’ve been looking for a high-quality free voice to text software solution that will automatically take an audio recording and transcribe it to text. Such an application will put a lot of transcription companies out of work, but it’s a dream that I believe will come true some day. Recently, I conducted another hour-long interview and in my search for such applications, I saw Jeffry’s article on how to transcribe audio using Express Scribe.

Jeffry did an awesome job covering most of the features of this application, but as he said in the last paragraph of the article – he hardly scratched the surface. A notable advanced use he noted is the application’s ability to dock recordings and integration with speech recognition software. In this article I’m going to show you how you can take advantage of those two features.

Dock & Speech Recognition to Transcribe Your Voice

Obviously, the first thing I wanted to do with Express Scribe (Windows/Mac) is to stream an audio file to automatically transcribe the interview. This is my pipe dream, so I had to try. Although the odds were good it wouldn’t work, because the computer would only be able to learn my voice. Either way, the first step is to enable the built-in voice recognition service in Windows 7 and train it to understand your voice.

Go into the Control Panel, click on “Ease of Access“, and then select “Speech Recognition.”

First select “Start Speech Recognition“, and this will enable the feature as part of your Windows experience. I very highly recommend that you click on “train your computer to better understand you” and go through the training sequence at least twice – it only takes about 5 to 7 minutes at a time. Speak as plainly and articulately as possible.

To enable speech recognition in Express Scribe, just click on Options and select the “Speech to Text” tab. You’ll see the default profile show up in the dropdown box. This is the profile that you’ve just trained to recognize your speech pattern. Click on “Add” so the profile shows up in the list.

Now that it’s ready to transcribe, the first thing I wanted to try was bringing in voice audio files and seeing how well the software transcribed them. You do this by clicking on “Dock” and then choosing the Audio File Transfer Method.

Using this selection, you then choose a folder where your external recording device, like a digital recorder, downloads files to your computer. This will import all of those files to Express Scribe. I used this feature to import audio files from my interview folder. Here’s what the transcription looked like.

As you can see, the transcription was pretty much garbage. Nine times out of ten the transcription can’t even get started, and when it does it will write a few words and then completely bomb out. Obviously, the automatic transcription of audio files that I dream about still hasn’t come true, but that doesn’t mean I’ve given up on Express Scribe. There’s still the fact that it is trained to recognize and transcribe my voice. So I could still make use of the software to transcribe my own voice recordings and dictations.

To do this live (with your microphone), all you have to do is plug in your microphone and then click “Dock” and choose the Audio Cable option. The following screen will appear, showing the audio level of your microphone and that it’s actively streaming in the live audio. Go ahead and start dictating.

Of course, if you’ve recorded your dictation on a digital voice recorder, all you have to do is hook up your voice recorder output to the microphone input of your computer, and this feature will stream in the audio (that’s actually what it’s intended for – docking your recorder).

When I was finished dictating a long sentence, I clicked “done” to see how well the software performed. As you can see below – pretty stellar. Only one word wrong (and should have been “can”), but that was because I stumbled when I spoke.

This is pretty impressive, and I can see using Express Scribe to transcribe a whole lot of recordings that I make while I’m mobile – it’ll save a whole lot of time in transcribing my audio, because I’ll only have to go back and edit any small mistakes.

The accurate transcription from audio to text is not an easy feature to find in most free voice to text software, so it was surprising to see Express Scribe do such a good job. Another nice feature is the “Incoming” feature within the Options menu. Here, you can configure a certain recording directly on your hard drive for automatic syncing.

Configure a Dropbox account linked to this directory, and you have a fast way to upload your recordings from anywhere straight to the directory where your Express Scribe software is waiting to transcribe your dictation.

In Express Scribe, you’ll have a really fast and convenient way to quickly transcribe any of your own audio recordings accurately and fast – especially if you automate it by syncing it to a Dropbox account. So, give Express Scribe a try and see how well it transcribes your voice. Share your experience in the comments area below.

With the recorded voice from the phone call and a clip of the person denying the accusation, I set to work trying to find a way to prove that the voices were one and the same.

I admit that I’m a bit obsessed with voice technologies. This is why I’ve been waiting for Google Voice to become more advanced with its voice recognition technology, and it’s why I love PC voice control apps like Tazti. However, when it comes to digitally comparing voices, I was at a loss. You’ve probably seen those spy movies where the computer can automatically identify the voice of a known criminal with the voice print alone.

To be honest, once I discovered Sonogram Visible Speech, I realized that spectrogram voice technology actually is currently a viable way to solidly identify a person by their voice alone.

Understanding Spectrogram

If you know about chemical isotopes, then you know that with isotopes, chemists can identify the chemical makeup of compounds by isolating the basic elements and using the breakdown to identify the individual components of any mixture. In much the same way, an audio spectrogram breaks down audio sound into basic frequencies. The interesting thing about the human voice is that no one speaks in one frequency. Your mouth, nasal passages and the structure of your voice box determines the mixture of frequencies that make up your somewhat unique voice.

Sonogram Visible Speech is a free spectrogram software application that will take video or audio files and break down the audio track into the entire spectrum – all of its frequencies throughout the entire time frame of the track. A completed spectrogram looks like the image below.

As you can see, the bottom track looks like the basic sound wave that you’d see in a program like Audacity, however the center pane displays each segment of the sound file in its entire frequency layout. The amazing thing about this software is that there are many other waveforms you can use to examine your sound file. These are especially for advanced users.

You can configure how each of those wave forms displays by going into the the “Options” menu, and selecting “General Adjustment.” Here you can define how the logarithmic graphs calculate output and the general display setup of all available charts.

If the sound is fairly quiet, or the voice you’re analyzing is a whisper, you may want to consider using the logarithmic frequency display. You enable it from the “Options” menu and select “Logarithmic Frequency.” This will somewhat “magnify” the significant areas of frequency in the spectrogram.

This can really help to identify clear frequency patterns that identify someone from the sound of their voice. If you’re completely lost, and you don’t know where to start, clicking on “Help” and going to “Online Help” will open up the very well written Sonogram Online Help manual. This is a great place to start if you’re new to spectrogram audio analysis.

An Experiment With Spectrograms Using Ghost Hunting

The beauty of this software is that it is good for many different uses. One of the artifacts that comes up often in ghost hunting, a personal interest of mine, is “electronic voice phenomenon” – where the voice of an apparition or ghost allegedly shows up on audio recordings. These recordings are scattered throughout the web, so I decided to pull a few off of the ghost hunter websites and do a spectrogram analysis.

The spectrogram shows that the frequencies of the voice are generally low, but to get a better picture of the voices in the recording, you need to open up the additional waveforms. The Autocorrelation View calculates “pitch” in the time frame where you hover the mouse.

The “ghost” has an average pitch frequency of about 129.0 hz. Scrolling to the end of the recording where you hear the investigator’s voice, the calculated pitch frequency is about 208.0 hz (which makes sense because it’s a female voice and the ghost recording sounds male.)

Opening up the Fast Fourier display reveals even more detail about the voices. This chart quickly breaks down the primary frequencies and displays them in a color code.

In this case, the breakdown of frequencies is spread apart, with some high, but a good number of low frequencies in the mix as well. However, the investigator in the room is clearly speaking in a voice that is clustered in frequency more toward the high end of the range, as shown here.

This quick analysis proved that the two voices are quite different, but this is only a basic example of the capabilities of this powerful software. Basically, any situation where a breakdown of frequencies of a sound wave can help – this is the software for you. It’s easy to learn, quick to set up and configure, and it performs as well or better than any paid spectrogram software on the market.

Do you have any projects that could use a spectrogram? Have you ever tried Sonogram Visible Speech? Share your insight in the comments section below.

To make the matter worse, you have to do a lot of stopping-rewinding-replaying to the audio/video files, and continuously go back and forth between the player and word processor.

Luckily, Express Scribe can help you solve the problem.

Not only can it slow down the audio files while maintaining constant pitch, it will also give you playback shortcuts that you can use from within your word processor. This amazing software is available for Mac, Windows and Linux; and it’s totally free.

Now let’s take a look at the basic features of the software. (Note: I’m using the Mac version, so there might be slight differences with the Windows and Linux version).

Slow Down, Stay Stable

To start a transcription process, open the app and click on the “Load” button from the main window and browse to the location of the file. You can load several files at once by using the Command key while selecting multiple files.

Then you can play the file using the controls that you will find in the main window. These tools consist of standard playback buttons like “Play – Stop – Rewind – Fast Forward” and other more advanced tools like “Speed” and “Playback Position” sliders.

If you do a lot of transcriptions, the Speed slider is the answer to your prayers. You can adjust the playback to be slow enough for your ten fingers to catch up. Express Scribe will keep the pitch stable and maintain the words as clear as they are in the original speed.

Once you press the “Play” button, a “Multi Channel Display” window will appear. This window allows you to adjust the volume of the left and right audio channels, or turn them on/off.

Setting Up The Hot Keys

Even though all the controls are just a click away, the purpose of using this app is so we don’t have to go back and forth between the player and the word processor. Express Scribe allows you to set up hotkeys to control its functions from within other applications.

To add hot keys, open the “Preferences“.

Then go to the “Hot-keys” tab and check the “Enable system-wide hot-keys” box. After that click the “Add” button.

Choose one of the functions from the drop-down list, and click “Change” to assign shortcut to it. Press the key combination that you chose, and click “OK.”

There are a lot of functions listed on the list, but I personally think that you should assign hotkeys only to the most important playback functions as memorizing too many shortcuts is not going to make the process faster. You should also use the most practical but unused key combinations.

Here’s the list of all my shortcuts and the hot-keys to give you a clearer picture.

• Play : “Ctrl + Alt + Right Arrow”
• Stop : “Ctrl + Alt + Period”
• Rewind : “Ctrl + Alt + Left Arrow”
• Go to start : “Ctrl + Alt + 0″
• Decrease playback speed (-5%) : “Ctrl + Alt + Down Arrow”
• Increase playback speed (+5%) : “Ctrl + Alt + Up Arrow”

Setting Up The Default Word Processor

You can open the word processor that you are going to use to write the transcription straight from the Express Scribe window. The default application is whatever application that you set to open a “.doc” file (In most computer, this will be Microsoft Word).

But if you want to use a different application as your chosen word processor – maybe something simple like TextEdit (Mac) or Notepad (Windows) – just change the default template file from the “Preferences – Other“.

First, create a blank document with the extension that you choose, and add the file to the Express Scribe template list.

Then select the file, click the “Set to default” button followed by the “OK” button.

Now every time you click the “Open Word Processor” button, Express Scribe will open your chosen application.

Another useful transcribing tool that you can use is the ability to add a time stamp to the word processor. This feature is very useful for those who do movie or interview transcriptions.

This tool can be accessed under the “Notes – Copy To Clipboard – Time” menu, or simply “Command + T” from within Express Scribe.

Barely Scratch The Surface

As an amateur transcriber, this is the extent to what I use the software for. But I have barely scratched the surface. There are more advanced features for pro-level transcribers such as support for a professional foot pedal, the ability to dock analog and digital portable recording, playing movie files (with additional plugins), and integration with speech recognition software. You can see the complete list on the website.

Have you tried to transcribe? Do you know other alternatives? Have you pushed Express Scribe to its limit? Share your experiences using the comments below.