Microsoft’s speech recognition system hits a new accuracy

Microsoft announced that its conversational speech recognition system reached a 5.1% error rate, its lowest so far.

This surpasses the 5.9% error rate reached last year by a group of researchers from Microsoft Artificial Intelligence and Research and puts its accuracy on par with professional human transcribers who have advantages like the ability to listen to text several times.

Both studies transcribed recordings from the Switchboard corpus, a collection of about 2,400 telephone conversations that have been used by researchers to test speech recognition systems since the early 1990s.

Overall, researchers from the latest study reduced the error rate by about 12 percent compared to last year’s findings by improving the neural net-based acoustic and language models of Microsoft’s speech recognition system.

Notably, they also enabled its speech recognizer to use entire conversations, which let it adapt its transcriptions to context and predict what words or phrases were likely to come next, the way humans do when talking to one another.

UCJ, UNILORIN.