Applying Discriminative Language Models to Reranking of M-best Speech Recognition Results
碩士 === 國立臺灣師範大學 === 資訊工程研究所 === 97 === A language model (LM) is designed to represent the regularity of a given language. When applied to speech recognition, it can be used to constrain the acoustic analysis, guide the search through multiple candidate word strings, and quantify the acceptability of...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2009
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/3tx7h6 |