Title | ||
---|---|---|
Latent semantic rational kernels for topic spotting on spontaneous conversational speech |
Abstract | ||
---|---|---|
In this work, we propose latent semantic rational kernels (LSRK) for topic spotting on spontaneous conversational speech. Rather than mapping the input weighted finite-state transducers (WFSTs) onto a high dimensional n-gram feature space as in n-gram rational kernels, the proposed LSRK maps the WFSTs onto a latent semantic space. Moreover, with the LSRK framework, all available external knowledge can be flexibly incorporated to boost the topic spotting performance. The experiments we conducted on a spontaneous conversational task, Switchboard, show that our method can achieve significant performance gain over the baselines from 27.33% to 57.56% accuracy and almost double the classification accuracy over the n-gram rational kernels in all cases. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6639284 | ICASSP |
Keywords | Field | DocType |
finite state machines,latent semantic rational kernels,rational kernels,n-gram rational kernels,lsa,wfsts,weighted finite state transducers,lsrk,n-gram feature space,wfst,speech recognition equipment,spontaneous conversational speech,topic spotting,acoustic transducers,lattices,transducers,semantics,kernel,speech,accuracy,switches | Feature vector,Pattern recognition,Computer science,Speech recognition,Finite-state machine,Artificial intelligence,Natural language processing,Spotting,Semantic space | Conference |
ISSN | Citations | PageRank |
1520-6149 | 2 | 0.37 |
References | Authors | |
6 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chao Weng | 1 | 113 | 19.75 |
Biing-Hwang Juang | 2 | 3388 | 699.72 |