作者: Jay Pierre Civelli , Mikhal Shemer , Turaj Zakizadeh Shabestary , David Tapuska
DOI:
关键词:
摘要: Provided are methods, systems, and apparatuses for detecting, processing, responding to audio signals, including speech within a designated area or space. A platform multiple media devices connected via network is configured process speech, such as voice commands, detected at the devices, respond by causing simultaneously perform one more requested actions. The capable of scoring quality request, handling requests from end points using centralized processing approach, de-centralized combination thereof, also manipulating partial into coherent whole when necessary.