Paper Info
Title
Parallelizing Speaker-Attributed Speech Recognition for Meeting Browsing
Abstract
The following article presents an application for browsing meeting recordings by speaker and keyword which we call the Meeting Diarist. The goal of the system is to enable browsing of the content with rich meta-data in a graphical user interface shortly after the end of meeting, even when the application runs on a contemporary laptop. We there-fore developed novel parallel methods for speaker diarization and multi-hypothesis speech recognition that are optimized to run on multicore and many core architectures. This paper presents the underlying parallel speaker diarization and speech recognition realizations, a comparison of results based on NIST RT07 evaluation data, and a description of the final application.
Year
DOI
Venue
2010
10.1109/ISM.2010.26
Multimedia
Keywords
Field
DocType
multi-hypothesis speech recognition,final application,speech recognition realization,core architecture,contemporary laptop,browsing meeting recording,speaker diarization,nist rt07 evaluation data,parallelizing speaker-attributed speech recognition,novel parallel method,underlying parallel speaker diarization,speaker recognition,feature extraction,engines,graphic user interface,graphical user interfaces,speech,meta data,speech recognition,graphical user interface,multicore
Metadata,Laptop,Computer science,Speech recognition,Feature extraction,NIST,Speaker recognition,Graphical user interface,Speaker diarisation,Natural language processing,Artificial intelligence,Multi-core processor
Conference
ISBN
Citations 
PageRank 
978-0-7695-4217-1
4
0.57
References 
Authors
11
3
Name
Order
Citations
PageRank
Gerald Friedland1112796.23
Jike Chong213611.62
Adam Janin325034.11