Producing text in the form that is expected makes copy much easier to read and reduces confusion. For example, if you worked somewhere where speed measurements were commonplace and it read ’30 miles per hour’ all the time, then it would not only make for long sentences but would also be harder to read as the consumers are used to seeing MPH. It also means that when reading they are not focused on why it’s written differently and can remain focused on the content instead.
Why is it tricky to get right?
We don’t always say things quite the way we should, for example, I saw ‘miles an hour’ not ‘miles per hour’, but I mean MPH either way. In addition, different use cases often require different uses of words and abbreviations. In fact, even within the same use case at different times or when different people are talking the expectations change. For example, a default output of ‘Dr.’ is great for most, but what if the context you are working in needs it to read ‘Doctor’ or for your report you need ‘et cetera’ spelt out and not written as ‘etc’.
Can Speech Recognition fix that too?
The Custom Dictionary feature in Speechmatics ASR products can help solve these kinds of issues like a human would. This involves providing just a little context to help the ASR along. Just adding the required form to the Custom Dictionary can work, however, that will not work all the time, and for cases such as the ‘miles an hour’ one mentioned above, it cannot. But all is not lost, Speechmatics can help you here too.
Watch this space for our newest feature addition, coming soon…
Watch the example below!
Ian Firth, Speechmatics