It claims to consistently and accurately interpret numbers, currencies, percentages, addresses, dates, and times
Speechmatics has added an entity formatting functionality to its autonomous speech recognition software.
It claims that this means it can now consistently and accurately interpret how entities such as numbers, currencies, percentages, addresses, dates, and times should appear in written form. This would reduce post-processing work and make transcripts more readable.
Entity Formatting is known to be challenging in speech recognition because the way that entities are spoken in conversation varies – even between countries that speak the same language. For example, people switching between “oh” and “zero”.
Speechmatic works with several broadcast related companites, including Red Bee Media and Veritone, and its CEO, Katy Wigdahl, said: “Creating a more professional transcript will speed up our customers’ workflows by making large numbers easier to read, requiring less human editing.
“Context is also critical – there are so many nuances and ambiguities that need to be accounted for in language, such as whether ‘pounds’ is a reference to weight or currency? And whether ‘venti’ is being used as the Italian word for 20 or winds?”