[1] 周迅溢,王蓓,杨玉芳,等. 语句中协同发音对音节知觉的影响[J].心理学报,2003,35(3):340-344.[2] SCHULTZ T, WAND M. Modeling coarticulation in EMG-based continuous speech recognition[J].Speech Communication, 2010, 53(4):341-353.[3] GAO S, LEE T, WONG Y W, et al. Acoustic modeling for Chinese speech recognition: a comparative study of Mandarin and Cantonese [C]// Proceedings of the 25th IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway:IEEE, 2000:1261-1264.[4] ZHANG J, ZHENG F, LI J, et al. Improved context-dependent acoustic modeling for continuous Chinese speech recognition[C]// Proceedings of the 7th European Conference on Speech Communication and Technology. Aalborg:ISCA, 2001:1617-1620.[5] 张辉,杜利民. 汉语连续语音识别中不同基元声学模型的复合[J]. 电子与信息学报,2006,28(11):2045-2049.[6] LIU X, GALES M J F, HIERONYMUS J L, et al. Investigation of acoustic units for LVCSR systems [C]// Proceedings of the 36th IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway:IEEE, 2011:4872-4875.[7] 彭荻,刘刚,郭军. 语音识别系统中上下文相关声学模型建模优化[J]. 北京邮电大学学报,2006,29(z2):188-191.[8] 高升.语境相关的声学模型和搜索策略的研究[D]. 北京:中国科学院自动化研究所, 2001.[9] GANAPATHIRAJU A, HAMAKER J, PICONE J, et al. Syllable-based large vocabulary continuous speech recognition[J]. IEEE Transactions on Speech Audio Processing, 2001,9(4):358-366. [10] WU H, WU X H. Context dependent syllable acoustic model for continuous Chinese speech recognition[C]// The 13th European Conference on Speech Communication and Technology. Aalborg:ISCA, 2007:1713-1716.[11] DENG L, AKSMANOVIC M, SUN D, et al. Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states[J]. IEEE Transactions on Speech Audio Processing, 1994, 2(4): 507-520.[12] 唐赟,刘文举,徐波. 基于后验概率解码段模型的汉语语音数字串识别[J]. 计算机学报, 2006, 29(4):635-642.[13] YOUNG S, EVERMANN G, GALES M, et al. Hidden Markov model toolkit [EB/OL]. [2012-10-20]. http://htk.eng.cam.ac.uk/docs/docs.shtml.[14] 唐赟.基于随机段模型的汉语语音识别算法研究[D].北京:中国科学院自动化研究所,2006. |