Improving of Open-Set Language Identification by Using Deep SVM and Thresholding Functions
Citations
20 citations
8 citations
Cites methods from "Improving of Open-Set Language Iden..."
...[29] used deep SVM for detecting out of set languages in the task of language identification and presented 3 formulations for the out of set languages as well....
[...]
7 citations
References
459 citations
"Improving of Open-Set Language Iden..." refers background in this paper
...Several systems have demonstrated the effectiveness of ivector representation over the low-level acoustic features such as Mel-frequency cepstral coefficients (MFCC), and shifteddelta cepstral coefficient (SDC) [2]–[4]....
[...]
...It consistently outperforms its high-level counterparts, including Gaussian mixture models (GMM) [2], [4], [11] and Gaussian Mixture Model-Universal Background Model (GMM-UBM) [2], [12]....
[...]
438 citations
248 citations
190 citations
176 citations
"Improving of Open-Set Language Iden..." refers background or methods in this paper
...This approach is straightforward and fast for application and in contrast to existing works [18], [20], [21], does not rely on the use of additional data from OOS languages which may not be available....
[...]
...For instance, in [20]–[23], non-target languages data are pooled from different resources to build OOS corpus, which can be costly and time-consuming....
[...]
...[20] NIST LRE 1996&2003 OOS modeling GMM, SVM and tokenizer Campbell et al....
[...]