Abstract | ||
---|---|---|
For a spoken dialog system to make good use of a speech recognition N-Best list, it is essential to know how much trust to place in each entry. This paper presents a method for assigning a probability of correctness to each of the items on the N-Best list, and to the hypothesis that the correct answer is not on the list. We find that both multinomial logistic regression and support vector machine models yields meaningful, useful probabilities across different tasks and operating conditions. |
Year | Venue | Keywords |
---|---|---|
2009 | SIGDIAL Conference | speech recognition n-best list,estimating probability,dialog system,good use,n-best list,asr n-best list,useful probability,multinomial logistic regression,different task,correct answer,support vector machine model,support vector machine,speech recognition |
Field | DocType | Citations |
Know-how,Spoken dialog,Computer science,Multinomial logistic regression,Correctness,Support vector machine,Natural language processing,Artificial intelligence,Machine learning | Conference | 7 |
PageRank | References | Authors |
0.88 | 6 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jason D. Williams | 1 | 1319 | 76.49 |
Suhrid Balakrishnan | 2 | 238 | 14.60 |