On Time Document Retrieval using Speech Conversation and Diverse Keyword Clustering During Presentations
Shruti Bhavsar1, Sanjana Khairnar2, Pauravi Nagarkar3, Sonali Raina4, Amol Dumbare5
1Shruti Bhavsar, Student, Department of Computer Engineering, Pimpri Chinchwad College of Engineering & Research, Pune, India.
2Sanjana Khairnar, Student, Department of Computer Engineering, Pimpri Chinchwad College of Engineering & Research, Pune, India.
3Pauravi Nagarkar, Student, Department of Computer Engineering, Pimpri Chinchwad College of Engineering & Research, Pune, India.
4Sonali Raina, Student, Department of Computer Engineering, Pimpri Chinchwad College of Engineering & Research, Pune, India.
5Prof. Amol Dumbare, Assistant Professor, Department of Computer Engineering, Pimpri Chinchwad College of Engineering & Research, Pune, India.
Manuscript received on August 01, 2020. | Revised Manuscript received on August 05, 2020. | Manuscript published on September 30, 2020. | PP: 529-535 | Volume-9 Issue-3, September 2020. | Retrieval Number: 100.1/ijrte.C4544099320 | DOI: 10.35940/ijrte.C4544.099320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper we present the idea of extracting keywords from discussions, with the point of using these words to recuperate, for each small piece of conversation and generating reports to individuals. Regardless, even a smaller piece contains a blend of words, which can be effortlessly interrelated to a couple of subjects; additionally, using a customized talk affirmation (ASR) system presents slips among them. Thus it is hard to sum up effectively the data needs of the conversation individuals. We initially propose a count to kill significant words from the yield of an ASR system which makes usage of topic showing strategies and of a sub particular prize limit which supports varying characteristics in the word set, to organize the potential contrasting characteristics of subjects and diminish ASR disturbance. By then, we set forward a strategy to surmise different topically detached requests from this definitive word set, remembering the ultimate objective is to build the potential outcomes of making at any rate one appropriate proposition while using these inquiries to investigate the English Wikipedia. The readings depict that our pronouncement continue ahead over past procedures that watch simply word recurrence or idea commonality, and states the good response for a report recommended framework to be used as a piece of conversations.
Keywords: Document Recommendation, Information retrieval keyword extraction, Meeting analysis, Local database, Extraction, Keyword, Clustering.