The researchers explored if they needed to show word-level or phrase-level confidence, as it was traditionally considered to be helpful. Google mentions that while building Live Transcribe, they faced a challenge regarding displaying transcription confidence. Addressing transcription confidence level issue After rigorous analysis, Google decided to choose smartphones because of its ” sheer ubiquity” and enhanced capabilities. Google considered different devices ranging from computers, tablets, smartphones, and small projectors, etc., to effectively display auditory information and captions. This, in turn, would ensure that the core user needs are satisfied while maximizing the app’s potential.
AudioSet is an image-like model that is capable of detecting speech, automatically managing network connections to the cloud ASR engine, and minimizing data usage over long periods of use.Īdditionally, the Google team partnered with Gallaudet University to make Live Transcribe intuitive, with the help of user experience research collaborations. The on-device neural network-based speech detector is built using Google’s dataset for audio event research, called AudioSet, announced last year.
0 kommentar(er)
