Multilingual Acoustic Model Splitting and Merging by Latent Dirichlet Allocation
碩士 === 國立嘉義大學 === 資訊工程學系研究所 === 101 === To avoid the confusion of phonetic acoustic models between different languages are one of the most challenges in multilingual speech recognition. We proposed the method based on Latent Dirichlet Allocation to avoid the confusion of phonetic acoustic models...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Online Access: | http://ndltd.ncl.edu.tw/handle/76623452382998891560 |