Tied-state multi-path HMnet model using three-domain successive state splitting
暂无分享,去创建一个
[1] Tomoki Toda,et al. Improving Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient Statistics in Noisy Environments Using Multi-Template Models , 2006, IEICE Trans. Inf. Syst..
[2] Akinori Ito,et al. Construction method of acoustic models dealing with various background noises based on combination of HMMs , 2005, INTERSPEECH.
[3] Akinori Ito,et al. An optimized multi-duration HMM for spontaneous speech recognition , 2003, INTERSPEECH.
[4] Arnon D. Cohen,et al. Multi-path, context dependent SC-HMM architectures for improved connected word recognition , 2000, INTERSPEECH.
[5] Kiyohiro Shikano,et al. Selective multi-path acoustic model based on database likelihoods , 2002, INTERSPEECH.
[6] H. Takaki. A Study on HM-Nets using Decision Tree-based Successive Splitting , 1997 .
[7] Louis ten Bosch,et al. Pronunciation variant-based multi-path HMMs for syllables , 2006, INTERSPEECH.