| N13-1074 | results ending with a comparison to | mixture modeling | . Proceedings of NAACL-HLT 2013 |
| N13-1074 | Fi - nally , we experiment with | mixture modeling | based adaptation . We compare |
| H92-1079 | in the description of our tied | mixture modeling | has only recently been fully |
| N13-1074 | Finally , we experimented with | mixture modeling | where improvements are observed |
| N13-1074 | tables ( 0.5 ) . The results of | mixture modeling | are summarized in Table 3 . In |
| H93-1020 | concerning tied mixtures . First , | mixture modeling | does not require the use of Gaussian |
| J00-3003 | scoring formulas for the two DA | mixture modeling | approaches for ASR . The mixture-of-posteriors |
| N13-1074 | and apply our method within a | mixture modeling | framework . In Section 2 , we |
| D13-1107 | method to set model weights in | mixture modeling | . In ad - dition , inspired by |
| N13-1074 | adaptation , in addition to applying | mixture modeling | on top of our method . We focus |
| N13-1074 | section , we compare our method to | mixture modeling | based adaptation , in addition |
| N13-1074 | weights and are then combined using | mixture modeling | . A finer grained weighting is |
| H92-1079 | we expect that the use of tied | mixture modeling | will allow us to develop a high-performance |
| J00-3003 | 6.2 Computational Structure of | Mixture Modeling | It is instructive to compare |
| D11-1130 | take a similar approach using | mixture modeling | combined with a background variation |
| D14-1156 | by introducing query-specific | mixture modeling | ; the utilities of the deduced |
| N13-1074 | Additionally , we compare our results to | mixture modeling | , where we report gains when |
| N13-1074 | based adaptation . We compare | mixture modeling | to our adaptation method , and |
| N13-1074 | heuristically extracted tables . 4.1 | Mixture Modeling | In this section , we compare |
| D15-1147 | al. ( 2015a ) applied EM-based | mixture modeling | to OSM and NNJM models to perform |
