ArkCase – Transcription Functionality

Welcome to ArkCase. Today I’m going to show you the transcribe functionality.

The transcribe functionality, is ArkCase the product integrated with AWStranscription service.

Today you’ll see a seamless demo between uploading of audio and video files or rich media with into ArkCase, and the automated transcription utilizing the AWS service for transcription. And, what the user interface looks like and how it returns the information from AWS. Will then allow you to see what the breakdown looks like on confidence threshold, what the actual individual transcription sections look like. We’ll show you the caption text within the actual audio or video file, and we’ll also show you how to compile a consolidated list of all the transcription information. So let’s go ahead and demo the transcription functionality.

So let’s go ahead and login. Once you log in you’re going to land on the home screen. This is a familiar screen for those that have seen other ArkCase videos. We’re going to go to the left navigation and go down to the admin module. We’re going to start with the configuration around the transcription or transcription management section. When we go into that there’s a couple of options that you have. We can set this up as automated transcription and once you actually automate the process any time you upload a supported file like an mp4 or a WAV file. We can actually send this off to the transcription service and automatically start transcribing the video. In some cases uploading the video can take a long time and also transcribing can take a long time. So having it automated allows you to send that off automatically and not have to worry about it. Once again, if you decide you do not want to automatically send this off to transcription you can change whether or not you’re sending it off from automatic transcription or even allow transcription at all. If you unselect enable transcription you will not even have that service running at all.

You also have the ability to handle media files and how you want to handle the actual transcription with new versions or copying existing versions. Because you can retransfer videos if they don’t meet the needs of the actual confidence threshold. Which takes me into this lower section you do have your confidence threshold, this is a configuration you can set. Once again this will be an individual threshold for each section or word count the actual transcribe video. That way it’ll bring attention to the actual user who is reviewing the transcription, that there may be some manual changes that need to be made or Corrections, and we’ll talk a little bit about that.

So let’s actually go into the actual case module and we’re going to use a case that actually. I created a little bit earlier, and we’re going to look up this case, and as you can see here it’s for the transcribe demo. Our case is a system that allows you to not only create cases but to store information in those cases specifically documents. Documents all types of formats. Today we’re talking about mp4s and WAV files we use those as an example, but once again you can upload any other types of formats.

So we’re going to go ahead and take a look at this folder structure. I went ahead and created a couple of folders one called audio one caught video. And we’re actually going to go ahead and upload a video in an audio file today and show you what that looks like. So let’s go ahead and right-click we’re actually going to go and pick a video doctype. And we’re actually going to select a specific video.

Today I’m gonna use a police body cam. Once again you can upload many different types of videos. They can be short, long, this one happens to be a shorter version so it actually uploaded very quickly. So, I’m gonna go ahead and double check and take a look and see if it’s actually been automatically sent off for processing. All I have to do is double click and it open up in the viewer.

Once it loads in the viewer you’re gonna see a couple of different things. Not only are you gonna see the video that you can actually stream live. You also see some of the information what the language of the video was currently right now, It’ll have a word count it will process that also give you an overall confidence. And then it actually tells you that the transcription status is processing. Which means this is currently out for transcription. As you can see here it does default with the transcription tab, to be where all of your different transcription sections are, and we’ll actually go through what that looks like. You also will have the ability to see where in the overall workflow this transcription is, as you can see here it’s currently in the first kind of starting of sending this off through the actual process. This is a very intense process as it pertains to sending this information off the transcription returning the actual information, and then being able to see it actually complete and show here on the user interface. We do have the ability to also compile this once it has actually come back and we’ll talk through that actual situation.

So let’s go ahead and let’s close out of this window.

Let’s move on to an audio file. Since we’re letting that video transcribe and go through the actual process of transcribing it.

Let’s actually upload an audio file.

Today we’re gonna go ahead and grab an interview audio file. This happens to be a way the other one was an mp4 but once you actually do that you’ll notice we can also double click on this one, it will load in the very similar viewer. As you can see once again it’s loaded in the viewer. You do have the ability to stream this live you do once again have the language word count confidence and that it is actually being processed currently.

Once again this can be played at any one time, you can … You can play the video right now you also can do a manual transcription if you decide to do that. But once again we’re going to let this process from an automated perspective and we’re gonna come back and take a look at the actual transcribed audio and video files.

Now that it’s been a few minutes. Let’s go ahead and check our actual audio and video file. To make sure that the transcription is back from the AWS transcription service.

So let’s go ahead and open up the actual police body cam video. Once we open up the video you’ll actually notice now we do have a word count and we also have a confidence level and now we see that the transcriptions status is complete.

As you can see here, we also have this individual transcription area has been highlighted. Obviously it’s a highlighting with an icon and a color, because it did not meet our 87% confidence. So we now can jump right into the video by clicking on the actual play button here, and it will take us right to the forty second mark.

The reason that’s important is, I’m going to now have to correct this specific transcription so, so to correct this I need to go ahead and click the correct button. I’m going to go ahead and say that this whole thing is totally wrong and I’m going to say,- “Put your hands behind now” that I’ve actuall entered in that information, I’m good to go and I can actually save this correction that I’ve now actually updated. I do at this point have the ability to compile this video. This is a very short video but due to the actual short period of time to demo, this we’re just showing you a very quick and easy video.

Let’s take a look at the audio file.

Don’t click it on the audio file once again. Well load in the same viewer and as you’ll see here there’s actually 69 words sex and overall confidence of 96% and it’s actually been completed. As you can see here there’s quite a few more actual areas. In the configuration earlier you may have noticed it litters a twenty word count. So, each section is configured to be in its own section if it’s 20 words, so once it’s 20 words are moved to the next section. So as you can see here, we actually have a start time of one second and this section is 96% correct. As you scroll through where our comments level is pretty decent, I think the lowest here is 93%. If you want to jump to a specific section to make sure that it’s good, you can click the plus on. So, as you can see you’re not only are we playing the audio and very similarly in the video we actually are showing the in from here at the bottom. We’re actually showing you the actual transcribed information within the video.

Once again, you do have the ability to click the correct and actually correct the information. If you did correct any information, you would save the information here and once again you can compile.

By compiling it’s grabbing all of the text that’s been transcribed and producing an actual compiled file. So let’s go ahead and compile that. Once the action is successful all we have to do is go back out to our document management section. So as you can see here, we now have an actual transcribed doctype. You do have the ability to open up in the viewer, or in this case we’re gonna go ahead and just download it native format. Because we want to print it and take it to some meeting that we have. All you have to do is open up that actual word document from the tray, and you’ll see the transcription here all stitched together.

Once again, you can update or manipulate this transcription by right-clicking, and either editing online or checking off or checking out offline.

Once again, I hope you enjoyed the actual transcription functionality demo.

Once again this is ArkCase that is integrated with AWS transcription service, that allows for the transcription of audio and video files or rich media.

Once again this was ArkCase and this was a demo of the transcription functionality.