A New Real-Time AI Platform from Microsoft, and a Speech Recognition Milestone

Earlier this week, our research team reached that 5.1 percent error rate with our speech recognition system – a new industry milestone that substantially surpasses the accuracy we achieved last year. We reduced our error rate by 12 percent from last year's level, using improvements to our neural net-based acoustic and language models. We introduced an additional convolutional neural network combined with bidirectional long-short-term memory (CNN-BLSTM) model for improved acoustic modeling. Additionally, our approach to combine predictions from multiple acoustic models now does so at both the frame/senone and word levels. We published a technical report that has the full system details.