Comparison of Frame Margin Probability Training to other Discriminative Methods for Multi-condition Speech Recognition
Our earlier frame margin probability discriminative training (FMPDT) algorithm has shown its advantage over maximum likelihood estimation (MLE) on multi-condition speech recognition 1. This paper reports our recent improvement on FMPDT and compares it with minimum classification error (MCE) and inimum phone error (MPE). We rewrite the re-estimation formulae of MCE, MPE in a unified linear interpolation way which facilitates this comparison. We compare the recognition results for MCE and MPE, FMPDT using the Aurora2 standard database and HTK3.4, and find the proposed method can give more balanced improvements under different conditions than other discriminative training algorithms.
Haozheng Li Xiaobing Li Douglas OShaughnessy
INRS-EMT University of Quebec
国际会议
2008 International Conference on Audio，Language and Image Processing(2008国际声音、语言、图像过程大会)
镇江
英文
1754-1758
2008-07-07（万方平台首次上网日期，不代表论文的发表时间）