Microsoft recently achieved a new milestone in its ability to recognise conversational speech through Switchboard, with a 5.1% word error rate (WER), beating its previous record of 5.9%.<\/p>\n
According to a Microsoft blog post: “Switchboard is a corpus of recorded telephone conversations that the speech research community has used for more than 20 years to benchmark speech recognition systems.”<\/p>\n
The speech recognition systems are tasked through transcribing conversations about topics such as sport or politics, and are based on neural networks and other artificial intelligence technologies.<\/p>\n
To boost its acoustic modelling, the research team improved its capabilities by adding a convolutional neural network combined with bidirectional long-short-term memory.<\/p>\n
The post added: “Moreover, we strengthened the recogniser’s language model by using the entire history of a dialog session to predict what is likely to come next, effectively allowing the model to adapt to the topic and local context of a conversation.\u201d<\/p>\n
According to Tech Republic<\/em>, additional technologies like the Microsoft Cognitive Toolkit 2.1 and Azure GPUs helped improve speed and explore architectural differences.<\/p>\n Despite the new levels of WER, Microsoft also noted in the post that there are still many challenges to address with speech recognition.<\/p>\n Written by Leah Alger<\/p>\n","protected":false},"excerpt":{"rendered":" Microsoft recently achieved a new milestone in its ability to recognise conversational speech through Switchboard, with a 5.1% word error rate (WER), beating its previous record of 5.9%. According to a Microsoft blog post: “Switchboard is a corpus of recorded telephone conversations that the speech research community has used for more than 20 years to…<\/p>\n","protected":false},"author":12,"featured_media":9948,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"content-type":"","pmpro_default_level":"","footnotes":""},"categories":[93],"tags":[798,1831,26,1830,1828,1649,1829],"yoast_head":"\n