实现自动计算汉字对应声母的方法

提出了自动计算汉字对应声母编码的概念,分析了基于汉字ASCII码和汉字字符编码国标GB2312-80规则的具体实现思路及算法,并介绍了实现该算法的主要程序段。     

神经网络方法及其在语音识别中的应用

讨论了神经网络技术用于汉语语音信号的端点检测，声，韵母分离、非线性特征抽取和大字表识别的方法，描述了系统实现框图并给出了应用实例。     

汉语双音节中第一音节的元音共振峰轨迹研究

汉语中,协同发音主要取决于相邻前一音节末尾的元音,以及相邻后一音节首的辅音。主要考察在汉语普通话双音节中,第一音节元音韵母和不同第二音节声母组合时对第一个音节元音共振峰轨迹的影响。元音韵母选用元音三角形的3个顶点的元音,总结了轨迹变化的规律。     

利用拼音特征的深度学习文本分类模型

针对人-机器人语音交互中经过语音识别的文本指令,提出了一种利用汉语拼音中声韵母作为特征的深度学习文本分类模型。首先,以无人驾驶车语音导航控制为人机交互的应用背景,分析其文本指令结构并分别构建单一意图与复杂意图语料库;其次,在以字符作为文本分类特征的基础上,结合汉语拼音与英文单词的区别,提出了一种利用拼音声韵母字符作为中文文本分类的特征表示方法;然后,用门控递归单元(GRU)代替传统递归神经网络单元以解决其难以捕获长时间维度特征的不足,为提取信息的高阶特征、缩短特征序列长度并加快模型收敛速度,建立了一种结合卷积神经网络及GRU递归神经网络的深度学习文本分类模型。最后,为验证模型在处理长、短序列任务上的表现,在上述两个语料库上对提出的模型分别进行十折交叉测试,并与其他分类方法进行比较与分析,结果表明该模型显著地提高了分类准确率。     

林语堂的方言学思想综述

作为语言学家的林语堂精于音韵学,高度重视方言研究,在丰富的古代文献语言资料和深厚的中国传统语言学功底以及西方现代语言学素养的基础上,提出了一系列科学的方言学研究方法,开启了从地理上划分方言区域的先河。其自成一体的方言学思想在中国方言研究领域产生了深远影响。     

Limits on learning phonotactic constraints from recent production experience.

Adults can learn new artificial phonotactic constraints by producing syllables that exhibit the constraints. The experiments presented here tested the limits of phonotactic learning in production using speech errors as an implicit measure of learning. Experiment 1 tested a constraint in which the placement of a consonant as an onset or coda depended on the identity of a nonadjacent consonant. Participant speech errors reflected knowledge of the constraint but not until the 2nd day of testing. Experiment 2 tested a constraint in which consonant placement depended on an extralinguistic factor, the speech rate. Participants were not able to learn this constraint. Together, these experiments suggest that phonotactic-like constraints are acquired when mutually constraining elements reside within the phonological system. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An evaluation of the diagnostic rhyme test

The intelligibility of a speech output device is an important predictor of user acceptability. The Diagnostic Rhyme Test (DRT) is an ANSI standard for measuring speech intelligibility (ANSI S3.2-1989). In the DRT, respondents hear a word and choose its equivalent from two visually presented words. The two words differ only in their initial (e.g., veal-feel), and the two consonants differ only in a single distinctive acousticphonetic feature (e.g., voicing). To define distinctive feature, the DRT uses a minimal distinctive feature system, loosely based on the work of Jakobson et al. (1963) and Miller and Nicely (1955). These studies carefully analyzed natural speech errors in various noise environments. Whether or not these studies can be freely applied to alternative forced-choice tests of coded or synthesized speech is an empirical issue. In the present study, the results of a Consonant Identification (CI) task were compared to a previously conducted DRT using the same coding algorithms. The CI data indicated that the low-bit-rate coded speech yielded significantly more multifeature confusions then the uncoded speech. Moreover, the multifeature confusions could not be easily predicted from the single-feature confusions. A fundamental assumption of the DRT is that speech errors are adequately diagnosed by testing single-feature confusions. The results of the present study contradict that assumption. In conclusion, we argue that the application of the DRT (and more generally, any closed-response choice procedure) to coded or synthesized speech is questionable.     

实现自动计算汉字对应声母的方法

提出了自动计算汉字对应声母编码的概念,分析了基于汉字ASCⅡ码和汉字字符编码国标GB2312-80规则的具体实现思路及算法,并介绍了实现该算法的主要程序段.     

Recognition of Pitman shorthand text using tangent feature values at word level

Recognition of text recorded in Pitman shorthand language (PSL) is an interesting research problem. Automatic reading of PSL and generating equivalent English text is very challenging. The most important task involved here is the accurate recognition of Pitman stroke patterns, which constitute “text” in PSL. The paper describes automatic recognition of the strokes of the PSL at word level. A pen-down to pen-up sequence makes a stroke, which is a composition of primitives. The words are separated based on pen-down and pen-up points. The features that form a word (a stroke) are grouped first. Next, primitives and their sequence are identified and passed to a recognizer which identifies the word. A tangent-based vector through the contour of a stroke identifies the consonant primitives. Any other marks close to the stroke but not associated with the contour of a stroke represent the vowel markers.     

REVERSE ENGINEERING

Four methods of vowel identification are examined. The method of Sukhotin combined with the consonant line appears to be the best. The method of vowel distribution is the worst.