Human Parity in Speech Recognition

Établi : December 1, 2015

This ongoing project aims to drive the state of the art in speech recognition toward  matching, and ultimately surpassing, humans, with a focus on unconstrained conversational speech.   The goal is a moving target as the scope of the task is broadened from high signal-to-noise speech between strangers (like in the Switchboard corpus) to include scenarios that make recognition more challenging, such as:  conversation among familiar speakers, multi-speaker meetings, and speech captured in noisy or distant-microphone environments.

Related

DataSkeptic podcast (opens in new tab) interview on human versus machine transcription

Personne

Portrait de Wayne Xiong

Wayne Xiong

Partner Group Engineering Manager