Earticle

초록

영어

The predominant language model for speech recognition is n-gram language model, which is locally learned and usually lacks global linguistic information such as long-distance syntactic constraints. We first explore two n-best re-scoring approaches for Mandarin speech recognition to overcome this problem. The first approach is linear re-scoring that can combine several language models from various perspectives. The weights of these models are optimized using minimum error rate learning method. Discriminative approach can also be used for re-scoring with rich syntactic features. To overcome the speech text insufficiency problem for discriminative model, we propose a domain adaptation method that trains the model using Chinese pinyin-to-character conversion dataset. Then we present a cascaded approach to combine the two re-scoring models in pipeline that takes the probability output of linear re-scoring model as the initial weight of the discriminative model. Experimental results show that both re-scoring approaches outperform the baseline system, and the cascaded approach achieves the best performance.

목차

Abstract
 1. Introduction
 2. Background
  2.1. Enhanced language models
  2.2. N-best Re-scoring approaches
 3. Baseline Speech Recognition System
  3.1. Word n-gram Language Model
 4. Re-scoring Approaches
  4.1. Linear re-scoring approach
  4.2. Domain adaptation discriminative re-scoring approach
  4.3. Cascaded re-scoring approach
 5. Sub Models
  5.1. Character N-gram Language Model
  5.2. Character-Based Discriminative Model
  5.3. Pinyin-Word Co-occurrence Model
  5.4. POS Models
  5.5. Dependency model
 6. Experiments
  6.1. Baseline System
  6.2. Linear re-scoring approach
  6.3. Domain adaptation discriminative re-scoring approach
  6.4. Cascaded re-scoring approach
 7. Conclusion
 References

키워드

저자

• Xinxin Li [ Harbin Institute of Technology Shenzhen Graduate School Shenzhen, China, 518055 ]
• Xuan Wang [ Harbin Institute of Technology Shenzhen Graduate School Shenzhen, China, 518055 ]
• Jian Guan [ Harbin Institute of Technology Shenzhen Graduate School Shenzhen, China, 518055 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605