Microsoft Speech Recognition Makes Advances

Researchers at the Microsoft Artificial Intelligence & Research group have created a speech recognition system which understands conversation just

as humans do & made fewer errors than a human professional transcriptionist. The researchers wrote in a paper: “The error rate of professional transcriptionists is 5.9% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, & 11.3% for the CallHome portion where friends & family members have open-ended conversations.” The automated system烙 goes past the human benchmark for the first time to reach “human parity”. Switchboard is a standard set of conversational speech & text used in speech recognition tests. Microsoft believes that the technology can be used heavily in entertainment devices like game consoles & speech-to-text transcription software as well as personal assistants like Microsoft’s Cortana