Loizou P, Dorman M, Spanias A
Department of Electrical Engineering, Arizona State University, Tempe 85287-7206.
J Acoust Soc Am. 1995 Mar;97(3):1925-8. doi: 10.1121/1.412065.
In this paper, it is shown how an automatic recognition algorithm, based on hidden Markov models (HMM), can benefit by properly utilizing findings from perceptual experiments on nasals. Perceptual studies on nasal consonants have shown that both nasal murmurs and formant transitions are important in the identification of place of articulation. Thus both acoustic segments bordering the nasal release were incorporated into this HMM-based system. A 7% improvement in alveolar recognition was obtained by explicitly modeling the vowel-nasal transition segments. Further overall improvement (6%) was realized by making the HMM recognizer "focus" more on the vowel-nasal transition segments bordering the nasal release, and less on the nasal murmur and vowel portion of the /epsilon m/ and /epsilon n/ syllables. An overall average [m]-[n] recognition of 95% was obtained when testing this technique on 60 speakers outside the training set.
本文展示了一种基于隐马尔可夫模型（HMM）的自动识别算法如何通过合理利用关于鼻音的感知实验结果而受益。对鼻辅音的感知研究表明，鼻杂音和共振峰过渡在发音部位识别中都很重要。因此，与鼻除阻相邻的两个声学片段都被纳入了这个基于HMM的系统。通过对元音 - 鼻音过渡段进行显式建模，齿龈音识别率提高了7%。通过使HMM识别器更多地“关注”与鼻除阻相邻的元音 - 鼻音过渡段，而减少对/εm/和/εn/音节的鼻杂音和元音部分的关注，进一步实现了整体6%的提升。在训练集之外的60名说话者上测试该技术时，[m]-[n]的整体平均识别率达到了95%。
