Downloads: 116

Survey Paper | Computer Science & Engineering | India | Volume 5 Issue 11, November 2016

A Survey Paper on Real-Time Document Commendations Based on User Discussions

Pramila S. Gaidhani | Manisha Naoghare ^[3]

Abstract: This paper discourses the problem of extraction from talks, with the goal of utilizing these watchwords to recover for each short conversation part, a little number of conceivably relatable reports, which can be prescribed to members, just-in-time. The purpose of meetings is to facilitate direct communication between participants. Document plays an important role in meetings. Documents contain facts that are currently discussed, but they are not necessarily at hand, the method known as extraction and grouping is overviewed which impulsively recommend the documents that are related to users current activities for an ongoing discussion. In any case, even a short audio fragment contains a mixed bag of words, which are conceivably identified with a few topics, also, utilizing Automatic Speech Recognition (ASR) framework slips errors in the output. Along these lines, it is hard to assumption correctly the data needs of the discussion members. Firstly propose a calculation to remove decisive words from the yield of an ASR framework (or a manual transcript for testing) to coordinate the potentially differing qualities of subjects and decrease ASR commotion. At that point, make use of a technique that to make many implicit queries from the selected s which will in return produce list of relevant documents. The scores demonstrate that our proposition moves forward over past systems that consider just word recurrence or theme closeness, and speaks to a promising answer for a report recommender.

Keywords: Automatic Speech Recognition, Extraction, Document recommendation, Conditional Random Fields

Edition: Volume 5 Issue 11, November 2016,

Pages: 1125 - 1128

Similar Articles with Keyword 'Automatic Speech Recognition'