Systems and methods for voice-assisted media content selection
摘要
說明書
A VAS may employ natural language understanding (NLU) systems to process voice inputs. NLU systems typically require multiple remote servers that are programmed to detect the underlying intent of a given voice input. For example, the servers may maintain a lexicon of language; parsers; grammar and semantic rules; and associated processing algorithms to determine the user's intent.
As it relates to voice control of media playback systems, however, such as multi-zone playback systems, conventional VAS(es) may be particularly limited. For example, a traditional VAS may only support voice control for rudimentary device playback or require the user to use specific and stilted phraseology to interact with a device rather than natural dialogue. Further, a traditional VAS may not support multi-zone playback or other features that a user wishes to control, such as device grouping, multi-room volume, equalization parameters, and/or audio content for a given playback scenario. Controlling such functions may require significantly more resources beyond those needed for rudimentary playback.
In addition to the above-mentioned limitations, typical VAS(es) may integrate with relatively few, if any, media content services. Thus, users generally can only interact with less than a handful of media content services through typical VAS(es), and are usually restricted to only those providers associated with a particular VAS.
