2016/12/29 - (Patent) Systems and methods for collaborative note-taking¶
Reading range : from [0001] to [0045]
Background of the invention¶
This invention relates to :
Collaborative note-talking
collaborative feedback
dynamic learning
dynamic adaptation based on collaborative feedback
Participants in classes and seminars frequently switch the focus of their attention between note taking tasks and the task of assimilating the material presnted.
Two exemplary note-taking styles :
Taking detailed note but less assimilation.
Less detailed note-taking but assimilating more material in presentation.
Some meeting capture ststem using automatic speech recognition.But :
Do not integrate the presentation material
Low accuracy makes a lot of recognition errors - Misdirect the user’s focus of attention
Summary of the invention¶
Dynamically determine language models based on domain indicactors in speech would therefore be useful.
Detailed description of exemplary embodiments¶
Fig.1
[0026]The speaker based language model is used to compensate for idiosyncratic(有特性的) speech characterisitcs such as the accent of the speaker, prosody, intonnation and the like.
[0029 - 0031] Domain based on language model -> Linguistic analysis using tools of Xerox Linguistic Environment (Parser)
[0032] Correctness score based on users’ feedback.
[0037] Monitored action are used to determine a collaborative user feedback signal.
Fig. 2
[0040] Speaker identifier information like wireless microphone is optional.
[0043]Sailent tokens are determined based on the imformativity of the words in the speech information. The classification of non-function words based on parts-of-speech such as adjectives , verbs , and nouns and/or references to presentation support information is used to determine the salient tokens.