Paper Info
Title
Named entity recognition from Conversational Telephone Speech leveraging Word Confusion Networks for training and recognition
Abstract
Named Entity (NE) recognition from the results of Automatic Speech Recognition (ASR) is challenging because of ASR errors. To detect NEs, one of the options is to use a statistical NE model that is usually trained with ASR one-best results. In order to make NE recognition more robust to ASR errors, we propose using Word Confusion Networks (WCNs), sequences of bundled words, for both NE modeling and recognition by regarding the word bundles as units instead of the independent words. This is done by clustering similar word bundles that may originate from the same word. We trained the NE models with the maximum entropy principle and evaluated the performance using real-life call-center data. The results showed that by using the WCNs, the error of NE recognition was relatively reduced by up to 33.0%.
Year
DOI
Venue
2011
10.1109/ICASSP.2011.5947622
Acoustics, Speech and Signal Processing
Keywords
Field
DocType
call centres,maximum entropy methods,speech recognition,ASR,NE recognition,WCN,automatic speech recognition,conversational telephone speech leveraging word confusion networks,maximum entropy principle,named entity recognition,real-life call-center data,word confusion network,Conversational Telephone Speech,Maximum Entropy Model,Named Entity Recognition,Word Confusion Network
Confusion,Pattern recognition,Computer science,Speech recognition,Named entity,Artificial intelligence,Natural language processing,Principle of maximum entropy,Cluster analysis,Named-entity recognition
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4577-0537-3
978-1-4577-0537-3
4
PageRank 
References 
Authors
0.42
14
4
Name
Order
Citations
PageRank
Kurata, G.140.42
Nobuyasu Itoh26513.19
Nishimura, M.340.42
Abhinav Sethy436331.16