The achievement was unlocked using the Computational Network Toolkit, Microsoft’s homegrown system for deep learning. With Google's DeepMind making waves in speech and image recognition (and speaking like humans do), the technology is Microsoft's timely contribution to the fast-paced artificial intelligence (AI) research and development. The achievement comes decades after speech pattern recognition was first studied in the 1970s. The new technology uses neural language models that allow for more efficient generalization by grouping similar words together. “We’ve reached human parity,” says Xuedong Huang, Microsoft's chief speech scientist. The rate is the same as (or even lower than) the human professional transcriptionists who transcribed the same conversation. "t’s the lowest ever recorded against the industry standard Switchboard speech recognition task," Microsoft reports. The technology scored a word error rate (WER) of 5.9%, which was lower than the 6.3% WER reported just last month. A study published last Monday, heralded as an historic achievement by Microsoft, details a new speech recognition technology that's able to transcribe conversational speech as well as humans - or at least, as best as professional human transcriptionists (which is better than most humans).
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |