How to improve the quality of the automatic subtitles in video calls?

When on a video call, and if available, I tend to take advantage of the automatic subtitles to help get through the call, and most deaf people would do the same.

But automatic subtitles are not perfect. They’re not terrible, but they’re not perfect. However, there are steps everyone can take to make it as accurate as possible and make it easier for the technology to pick up the words.

You can find out about how you can make the most out of automatic captions/subtitles in video calls by watching the video:

…listening to the podcast…

…or by reading the transcripts below.

---

So how do you make the most out of automatic subtitles that you see on video calls like Skype or Google Meet?

You see, I use them sometimes. They’re not perfect. I don’t think they will ever be perfect, but it will do in a circumstance.

And unless you have someone who is a professional who can do it like an on-demand, then it will do for now until we find a better solution, until you can have the budget to have someone doing it live for you.

But over the years, it has gotten better. The technology for captioning live on video call, it has gotten better. But still, we need to make it easier for the technology to be able to pick up the words as accurate as possible.

I don’t know if you’ve noticed, but I did say I “use them sometimes” and that because, first of all, I’m not profoundly deaf. I can hear certain things, but I still use them sometimes, depending on what I’m doing and depending on what I’m hearing.

But also there are a couple of things. It depends on whether the video or platform has it or not, and not all of them have it. It depends on the quality of the audio itself when I hear other, people and there are various processes that I go through and I want to go through to ensure that video call a comfortable and smooth as possible when you’re communicating with someone who is deaf.

I’ve got a separate article, separate video about that. You can find that in description, but this one will be more focused on automatic captions specifically automatic subtitles instead of the whole process of video calls.

So like I said, they’re not bad, they’re not horrible. They can be helpful. But the other issue that I tend to encounter on most platforms, for example:

• They don’t tend to have punctuation. There’s no full stop or comma. So you can get lost in the sentences and the paragraph, if you imagine there are no full stop or commas or anything like that.
• sometimes they don’t break the paragraph, they don’t break it into something more easy to scan. They’re not make it easy to consume. And you can get lost in it
• Video calls are especially difficult when you have those calls where there are certain jargon used or technical word; anything in your industry that is not necessarily an every day word. It makes it more complicated because on most occasion, the subtitles will not be able to pick up the word accurately as you can.
• As you can expect, you can’t edit the subtitles. You can just look at it and say, “oh, wait, no, I have to adjust that for the other person can see what I’m trying to say and I want to edit it”. That’s not possible.
• It doesn’t always tell you who is speaking. So one-on-one is not a problem. You know who is speaking one-on-one, maybe a very, very small group. But imagine if it’s a bigger group, lots of people involved and there are no indication of who is speaking, who is saying what.

When you combine everything together, it’s so easy to get lost in a conversation and becomes overwhelming.

It’s not a surprise that you will see incorrect grammar and incorrect words displayed just makes it even more confusing and frustrating.

There is no such thing as the one good platform. There is no best one. They all vary in accuracy and quality, so I won’t be able to give you which one the best.

So that means you kind of have to juggle between one platform to another, depending on what works at that occasion.

And like I said earlier, there’s no such thing as a perfect automatic subtitles and it’s not going to be perfect. But you can get it quite close to it.

And you can make it even more closer to accuracy if you get a few tips like the following:

1. Wear headphones and use a microphone

Number one would be to have a headset and microphone. And I’m not saying you have to have one of those big fancy microphones and you have to spend a lot of money on it.

At a very bare minimum, it’d be great if you can plug in your hands-free kit that you get with your mobile phone, just plug it in.

They have a small microphone attached to it and you plug in and you get put on your ear pods and put it in your ear. And that’s it. That’s the bare minimum that I would expect.

But if you can get it better than that, it would be awesome, you can get those really good quality gamer-style headphones that they’re not as expensive as you think.

But the quality of the audio is really good, and because the quality of the audio is really good, the technology is able to pick up the words.

And on top of that, because you have plugged and you’re listening in to the ear pods and not outside the speaker from your laptop, that means the sound will come out from your laptop, it will go to your ears and it won’t come out from speaker of the laptop.

The problem with that one comes out of a laptop, it will go into the microphone and the audio quality is just not that great, which makes it even more difficult for the technology to pick up the words.

2. Don’t talk over each other

Number two would be to don’t talk over each other if you can. I know it’s difficult when you have a conversation and you want to say something.

But if people are talking to each other or the multiple conversations happening in the background and you are just trying to say something to another person, which you shouldn’t do anyway, that makes it so hard for the technology to pick up the words.

If you can even pick up a word yourself, I’d be very surprised but imagine if you can’t pick up what the other person is saying because people are talking over each other, how do you expect the technology, the automatic subtitles, to be able to pick it up?

3. Be in a quiet environment

Number three, to make sure that you are in a quiet environment. It makes sense. Any background noise, any kind of noise that will distort your voice.

Again, it makes it hard for the technology to pick up your words. So if you are thinking about having a video call in a cafe with all the background noise happening, then you making it difficult for the people who are listening to you and you’re making it difficult for the automatic subtitles to pick up what you are saying.

4. Ensure you have good internet connection

Number four is to have good quality internet connection.

It’s not possible for every single person, I can appreciate that, but it does make a difference. The internet connection will make sure that your audio quality is high as possible.

There’s no lags and it doesn’t get cut off. And also, again, it just makes it easy for the technology to pick up what you’re saying. It’s a combination of both. And that is really useful. And you can only really have that if you have good Internet connection.

5. Be concise and straight to the point

And number five would be to just be concise and straight to the point and not necessarily waffle on and on and on, going on and on and on.

And it’s just to make it easy to consume information for anyone but again, it just for a person reading the subtitles, when you are talking on and on and on, it’s really hard to keep up. It’s really hard to understand what’s going on.

So if what you’re saying is straight to the point, it’s concise and you just say what you need to say in a few sentences as possible or whatever it requires, then that’s great.

But if you go on and on and on, then it doesn’t help anyone, least of all the person who is depending on the subtitles when they look at paragraph after paragraph after paragraph of just you talking on and on and on.

---

Automatically subtitles will never be perfect but with the help of those five tips, you can make it as close to accuracy as possible. There are other things, of course, like you speak clearly and don’t mumble and there are a lot of things like that.

But in general, these are the five main points I want to focus on and to make sure that you are aware of when you’re speaking to someone who is dependent on automatic subtitles, it makes a huge difference.

Like I said, I’ve got a separate article, a separate video about how to video call a deaf person and it goes through a variety of things to make it a much better overall experience.

But hopefully with the help of these five tips, it makes a big difference and you’ll be able to get your message across and have the communication on a video call with a deaf person.

I hope that helps. Make sure you check out the post I did about video calling deaf people. But again, let me know if you have any other questions. Let me know in the comment. If you’d like to make sure you subscribe and make sure you hit that Like button.

It would be an awesome thing for you to do. It really mean a lot to me if you can do that.

In the meantime, I will speak again soon.

Take care!

Share with your friends: on Twitter on Facebook on LinkedIn