Abstract | ||
---|---|---|
Building a stochastic language model (LM) for speech recog- nition requires a large corpus of target tasks. For some tasks no enough large corpus is available and this is an obstacle to achieving high recognition accuracy. In this paper, we propose a methodforbuildinganLMwithahigherpredictionpowerusing large corpora from different tasks rather than an LM estimated from a small corpus for a specific target task. In our experiment, weusedtranscriptionsofairuniversitylecturesandarticlesfrom Nikkei newspaper and compared an existing interpolation-based method and our new method. The results show that our new method reduces perplexity by 9.71%. |
Year | Venue | Keywords |
---|---|---|
2003 | INTERSPEECH | language model |
Field | DocType | Citations |
Perplexity,Obstacle,Computer science,Interpolation,Speech recognition,Natural language processing,Artificial intelligence,Cluster analysis,Language model | Conference | 1 |
PageRank | References | Authors |
0.35 | 7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shinsuke Mori | 1 | 474 | 47.78 |
Masafumi Nishimura | 2 | 112 | 22.77 |
Nobuyasu Itoh | 3 | 65 | 13.19 |