Microsoft’s Speech Recognition Technology Has Hit Human-Level Accuracy

Megalith

24-bit/48kHz
Joined
Aug 20, 2006
Messages
13,000
After 25 years of research, Microsoft’s speech recognition technology has finally reached human parity: the system now has a word error rate of only 5.1%, a reduction of 12% over the last year. The achievement was made possible with a convolutional neural network combined bidirectional long-short-term memory.

While achieving a 5.1 percent word error rate on the Switchboard speech recognition task is a significant achievement, the speech research community still has many challenges to address, such as achieving human levels of recognition in noisy environments with distant microphones, in recognizing accented speech, or speaking styles and languages for which only limited training data is available. Moreover, we have much work to do in teaching computers not just to transcribe the words spoken, but also to understand their meaning and intent. Moving from recognizing to understanding speech is the next major frontier for speech technology.
 
Last edited:
I wonder how much processing power the trained network requires to translate a single voice in real-time. Can it run on a smart phone? Can it run on a high end desktop CPU? Can it run on a high end desktop GPU?
 
  • Like
Reactions: PaulP
like this
Back
Top