Name
Abstract | ||
|---|---|---|
We propose a novel utterance comparison model based on probability theory and factor analysis that computes the likelihood of two speech utterances originating from die same speaker. The model depends only on a set of statistics extracted from each utterance and can efficiently compare utterances using these statistics without requiring die indefinite storage of speech features. We apply the model as a distance metric for speaker clustering in die CALLHOME telephone conversation corpus to achieve competitive results compared to three other known similarity measures: the Generalized Likelihood Ratio, Cross-Likelihood Ratio, and eigenvoice distance. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICASSP.2011.5947361 | ICASSP |
Keywords | Field | DocType |
pattern clustering,eigenvoice distance,statistical analysis,utterance comparison model,cross-likelihood ratio,probability theory,speech utterances,speaker recognition,speaker clustering,speaker diarization,generalized likelihood ratio,factor analysis,callhome telephone conversation corpus,computer model,speech,accuracy,tv,mathematical model,likelihood ratio,computational modeling,distance metric | Conversation,Pattern recognition,Computer science,Utterance,Metric (mathematics),Speech recognition,Speaker recognition,Generalized likelihood ratio,Speaker diarisation,Artificial intelligence,Probability theory,Cluster analysis | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4577-0537-3 | 978-1-4577-0537-3 | 4 |
PageRank | References | Authors |
0.44 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Woojay Jeon | 1 | 29 | 3.90 |
| Changxue Ma | 2 | 114 | 15.95 |
| Dusan Macho | 3 | 47 | 6.58 |