Browse > Article

The Optimal and Complete Prompts Lists Generation Algorithm for Connected Spoken Word Speech Corpus  

유하진 (서울시립대학교 컴퓨터과학부)
Abstract
This paper describes an efficient algorithm to generate compact and complete prompts lists for connected spoken words speech corpus. In building a connected spoken digit recognizer, we have to acquire speech data in various contexts. However, in many speech databases the lists are made by using random generators. We provide an efficient algorithm that can generate compact and complete lists of digits in various contexts. This paper includes the proof of optimality and completeness of the algorithm.
Keywords
Speech recognition; Korean; Connected word recognition; Connected digit recognition; Speech corpus;
Citations & Related Records
연도 인용수 순위
  • Reference
1 /
[] / The LDC Corpus Catalog
2 /
[] / The LDC Corpus Catalog
3 Efficient decoding algorithms for Mandarin connected digit speech recognition /
[ Zhu Xuan;Li Husheng;Lin Jia;Liu Runsheng ] / Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing
4 Connected digit recognition experiments with the OGI Toolkit's neural network and HMM-based recognizers /
[ Cosi,P.;Hosom,J.P.;Shalkwyk,J.;Sutton,S.;Cole,R.A. ] / Proceedings of IEEE 4th Workshop on Interactive Voice Technology for Telecommunications Applications, IVTTAETWR-98
5 Context-dependent word duration modeling for Korean connected digit recognition /
[ Kwon,O.W.;Un,C.K. ] / Electronics Letters