发音语声学

词组短语

articulatory phonetics

与发音语声学相关的网络例句 [注：此内容来源于网络，仅供参考]

In order to decrease the error rate of speech recognition, speaker adaptation techniques are often used to adjust speaker-dependent acoustic models. MLLR (Maximum Likelihood Linear Regression) and MAP are two of the most popular techniques in recent years. MLLR uses the technique of regression trees. It calculates the transform matrix for each leaf node of the tree. This makes it possible to use fewer sentences to decrease the error rate of HMM-based speech recognition. However, while we examined the recognition result, we found that although the overall error rate decreased, but the error rate of certain confusable phones was higher. In order to solve this problem, we propose the use MPE (Minimum Phone Error Discriminative Training) to solve this problem.

在语音辨识技术的实际应用上，语者调适技术常被用做调整语者无关之声学模型，使其对於特定语者之辨识率有所提升，常见的语者调适技术有最大化相似度线性回归（Maximum Likelihood Linear Regression），其精神在於透过对语音辨识模型相近的mixture做群聚，再对各个群聚做调整，以期能达到利用少量语料，提升辨识率的目的，但其缺点为，在发音上相近的模型，其mixture原本就极为近似，若再分类为同一群聚做调整，容易因为使用者的发音习惯，而使模型偏向ㄓ或ㄗ，因此虽然整体的辨识率获得提升，但却造成混淆音的错误率上升。

According to the degrees of PSC they have,Shanghai-accented Mandarin interlanguage are classified into four stages as elementary ,intermediate ,intermediate-advanced and advanced.Then the phonologies of Standard Mandarin and Shanghai-accented Mandarin interlanguage are compared in order to find out the phonological differences between these two dialects. Based on the statistical results, the writer chooses ten typical kinds of pronunciation errors of finals according to the rates of pronunciation errors of finals on stages.Then, the phonetic level analysis is made on them for the four stages respectively. Furthermore, acoustic features of vowels, diphthongs, triphthongs and vowels with nasal endings are analysized and compared by plotting vowel charts and formant patterns for them. Finally, the writer gets some preliminary results of the typical pronunciation errors of finals during the whole process of Shanghai-accented Mandarin interlanguage and on the stages of it respectively.

本文结合当前这种实际研究和应用的需要，以上海地区普通话过渡语为考察对象，从韵母发音偏误入手，借鉴第二语言习得研究中偏误分析和中介语研究的相关理论，采用实验语音学的方法，随机选取了80位上海地区不同普通话水平等级的应试人的应试录音和试卷作为本研究使用的语料，并将其分别对应于上海地区普通话过渡语的四个阶段，重点考察这80位处于不同阶段的应试人在测试的读单字部分的韵母发音偏误现象，通过对各阶段所有应试人的各类韵母发音偏误出现率的统计分析，展示出上海地区普通话学习者在韵母习得方面产生的偏误在过渡语各个阶段上的分布特点及趋势；再根据各阶段各韵母发音偏误率的统计结果，选取各阶段共同具有的十类主要的韵母发音偏误，分别绘制过渡语各阶段的偏误音声学元音舌位图或共振峰模式图，并与标准普通话中相应韵母的声学元音舌位图或共振峰模式图进行比较，从而展示出上海地区普通话学习者的主要韵母偏误类型在过渡语不同阶段上各自的声学特征、偏离标准音的程度和相关趋势，并从一定程度上反映了这一地区普通话学习者在韵母习得方面的能力发展轨迹，为普通话教学及培训中如何提高教学效率问题提供一定的参考依据，也为普通话水平测试各等级标准声学特征的建立，乃至为将来测试的计算机化提供了可靠的声学参数。