Speech recognition the way you want!
Philips SpeechLive speech-to-text enables you to use speech recognition in many different ways on different devices and it’s not tying you to sit in front of your computer, speaking and turning voice into text.
In short: Speech-to-text can be used in the SpeechLive Mobile app on your smartphone, Desktop app on your PC, and directly in the SpeechLive web recorder in your browser.
Learn more in the quick step-by-step guide below. What’s your preferred way? The best of all, you don’t have to choose as they all work with Philips SpeechLive speech-to-text.
Sending finished dictations to automated speech recognition in the Philips SpeechLive App on your smartphone:
- Download the app “Philips SpeechLive” from the App Store and log in to your SpeechLive account (Note: You will need the speech-to-text package add-on)
- Go to Settings by clicking the cogwheel icon
- Select the slider to “Enable speech recognition features on this device”
- You will be asked to select your preferred Language upon sending through speech recognition
Once you complete your dictation, click on the ‘check’ symbol and select the “Send to speech recognition” option.
If you are connected with office staff who finalizes documents, your work is done. They will see the recording and the recognized text document in their SpeechLive work list, can edit the text and create the final document.
If finalize the document yourself, follow the below steps:
Correcting and editing text to create the final document
Log into the SpeechLive browser application: www.speechlive.com
Dictations that have been sent to speech recognition will show as “Correction Pending” with an attachment symbol – see paperclip:
Select the job and then click on the cloud with the arrow in the blue top ribbon and select “download transcript”:
The dictation will download and you can see it at the bottom of your browser window. It is downloaded as a Word file.
When the download finishes, click on the file to open the document. You can play back the audio file while you follow along in the Word document. To play back the audio file, hover over the green icon with the white check mark. The icon will change to a blue icon and then you can click this icon to open and listen to the recorded file in the online player.
You can control the playback within the task bar of the player:
Make any changes required. Once you are done correcting the document, hit the check mark to finish. Save or copy and paste the text from this word document into your document management system, an email, etc. The recording will be archived automatically according to your archive settings.
Using front-end speech recognition in the Philips SpeechLive App on your smartphone:
You can also use the SpeechLive smartphone app to convert your voice to text in real-time as you speak. Hit the plus in the red circle, as you would to create any other dictation. Select “Speech recognition” from the options that pop up.
From there, hit the record button in the middle and start speaking, and watch as your voice is transcribed into the application. When you are finished, click the blue check mark and you can send the text and recording to your team for correction, or copy and paste it to any other application on your smartphone.
Using front-end speech recognition in the Philips SpeechLive browser on your PC:
Authors also have the option to dictate directly into a text box in the SpeechLive browser on the PC to convert your voice to text in real-time as you speak.
To get started, log into www.speechlive.com with your author credentials. You will see a list of all your current dictations and their status. To start a “front-end” dictation with speech recognition, click on the round green icon in the blue ribbon above your list of dictations.
You will then be presented with the dictation box and Record icon.
In the blue ribbon, you will see the following icons:
- Make sure to select the correct language (English US)
- To open the list of commands, click on the icon to the right of the language.
- The cogwheel will allow you to add words (separated by a comma) that are specific to you and not part of the general vocabulary.
Once you have finished your dictation, you can correct the text yourself or send it as is to your team for editing and formatting. You will see 3 more Icons in the blue ribbon this time to the left:
- If you click the “X, you have the option to discard the text. You would choose this option if you have already corrected the text and copied it elsewhere. Your team would not need to do anything further and it will not show up in the list of dictations.
- If you select the check mark, the dictation along with the recognized text will be saved in the work list as “transcription finished” with the attached text and can be accessed by the author or assistant for further correction.
- The last icon allows you to edit the dictation properties (see below). This allows you to add any comments, work type info, etc. for your team.
To learn how to use speech-to-text instead of typing a document, have a look at this blog post.