Improving the recognition of names by document-level clustering

Named entities are of great importance in spoken document processing, but speech recognizers often get them wrong because they are infrequent. A name correction method based on document-level name clustering is proposed in this paper, consisting of three components: named entity detection, name clustering, and name hypothesis selection. We compare the performance of this method to oracle conditions and show that the oracle gain is a 23% reduction in name character error for Mandarin and the automatic approach achieves about 20% of that.

[1]  Mari Ostendorf,et al.  Improving out-of-vocabulary name resolution , 2005, Comput. Speech Lang..

[2]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[3]  Wei Wu,et al.  Development of the 2008 SRI Mandarin speech-to-text system for broadcast news and conversation , 2009, INTERSPEECH.

[4]  Gökhan Tür,et al.  Name-aware speech recognition for interactive question answering , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Feifan Liu,et al.  Unsupervised language model adaptation via topic modeling based on named entity hypotheses , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Wen Wang,et al.  Building a highly accurate Mandarin speech recognizer , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

[7]  Heng Ji,et al.  Phonetic name matching for cross-lingual Spoken Sentence Retrieval , 2008, 2008 IEEE Spoken Language Technology Workshop.

[8]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[9]  Heng Ji,et al.  NYU's Chinese ACE 2005 EDR System Description Can Global Re-Ranking and Semantic Role Labeling help Chinese EDR? , 2005 .

[10]  Dragutin Petkovic,et al.  Phonetic confusion matrix based spoken document retrieval , 2000, SIGIR '00.