目前流行的计算机辅助发音教学系统(CAPT)的比较分析研究

目前国外流行的计算机辅助发音教学系统(CAPT)有很多,本文通过对6种CAPT系统分析了它们的相同点及不同点,并对每一种系统的优、缺点做了详细的介绍,在此分析基础上,得出未来需要的计算机辅助发音教学系统的特点。     

计算机辅助汉语教学系统中语音评价体系初探

本文探讨和研究计算机辅助汉语教学系统中语音评价体系的组成与实现方法。采用标准普通话语音示教数据库和非特定人大词汇量标准普通话汉语语料数据库,建立标准普通话示教语句特征模板库。采用Kohonen自组织神经网络进行学习者语音信号的分类与识别,经过汉语语音教学效果评价系统的处理,获得相应的量化评价结果。初步给出了计算机辅助汉语教学系统中语音评价体系的总体框架及其实现方法。通过实验验证了本语音评价体系的设计方案是合理的、可行的。它基本上能够满足计算机辅助汉语教学系统在线评价学生语音学习效果的需要。     

用于汉语语音信号端点检测与切分的有效方法

文章给出了计算机辅助汉语教学系统中语音端点信号的检测和清浊音信号的切分方法：采用短时相对能频积对汉语语音信号的端点进行检测;采用短时相对能频比的方法对语音信号的清浊音进行切分。这两种方法的使用与现有方法相比可以有效地提高汉语语音信号切分的成功率,实验结果表明正确率可达到９５％以上。文中通过实验验证了所提出的汉语语音信号切分方法是有效的和可行的。它基本上能够满足计算机辅助汉语教学系统在线切分汉语语音信号的需要,比已有的语音信号切分方法的切分效果有显著提高,为下一步提高语音信号的识别率奠定了基础。     

基于TTS汉语发音动态时间弯曲评测法

汉语学习日趋广泛,如何快速有效地实现标准汉语语料库供学习者参考并对汉语学习者的发音标准水平做出评测受到了很大程度的关注。该文介绍微软提供的TTS语音引擎,阐述其编程实现过程,利用TTS生成的汉语音频作为标准语料库。采集汉语学习者发音,对TTS生成的汉语音频和汉语学习者的发音作预处理并提取特征值,最后采用DTW(动态时间弯曲)算法实时地进行发音标准水平评测。     

汉语语音同步的三维口型动画研究

针对汉语的发音习惯以及语音可视化技术中对口型动画自然、连续的要求,提出了一种基于肌肉模型与协同发音模型的与语音保持同步的口型动画的方法.首先,根据汉语发音时的口型视位特征将声、韵母音素归类,并用数据映射的方式合成与之对应的口型关键帧.通过分析输入的文本信息,合成与语音保持同步的三维人脸口型动画.为了解决汉语发音习惯的问题,设计了一种基于微分几何学描述的协同发音建模的方法,该方法通过分析相邻音子间视素的影响权重,可以产生符合汉语发音习惯的口型动画.最后,通过实验对比和分析,该方法产生的口型动画更为逼真,且符合汉语发音的习惯.     

汉语文本-可视语音转换的研究

本文通过对发音者可见器官动作的研究 ,从视觉方面抽取汉语发音的 2 6个基本口形 ,并利用 MPEG- 4所规定的面部动画参数 (FAP)来描述这些口形 ,从而获得了符合国际标准的描述汉语发音的视觉参数 .另外 ,我们研究了这些参数在连续语流中的变化及协同发音对口形的影响 ,基于已有的汉语文语转换系统 (Sonic)和二维网格人脸模型(Plane Face)实现了一个汉语文本 -可视语音转换系统 (TTVS)     

新疆非母语汉语语音识别中的字典自适应技术

将标准普通话语音数据训练得到的声学模型应用于新疆维吾尔族说话人非母语汉语语音识别时,由于说话人的普通话发音存在较大偏误,将导致识别率急剧下降。针对这一问题,将多发音字典技术应用于新疆维吾尔族说话人汉语语音识别中,通过统计分析识别器的识别错误,建立音素混淆矩阵,获取音素的发音候选项。利用剪枝策略对发音候选项进行剪枝整合,扩展出符合维吾尔族说话人汉语发音规律的替代字典。对三种剪枝方法产生的发音字典的识别结果进行了对比。实验结果表明,使用相对最大剪枝策略产生的发音字典可以显著提高系统识别率。     

具有语音评价功能的计算机辅助汉语教学实验系统

本文探讨和研究计算机辅助汉语教学系统中语音评价体系的组成与实现方法。即建立标准普通话示教语句特征模板库,采用Kohonen自组织神经网络进行学习者语音信号的分类与识别,经过汉语语音教学效果评价系统的处理,获得相应的量化评价结果。     

智能型计算机辅助汉语教学系统

本文提出了智能型计算机辅助汉语教学系统的设计与实现方法。讨论了该系统中的领域知识表示、教学知识表示、学生模型的建造以及教学决策等问题。提出了新领的适合于汉语领域知识表示的“ 网络关系给构” 表示法, 根据模糊教学理论建立了可用于对学生能力作出综合评价和进行教学决策的“ 模糊逻辑”的模型。     

人工智能在智能教学系统中的应用

智能教学系统(ITS)是人工智能与教育结合的主要形式。本文在总结国际上相关研究成果的基础上，结合我们在开发智能多媒体汉德语言教学系统《二十一世纪汉语》的过程中累积的实践经验，介绍了ITS的历史、结构和主要技术，着重讨论了人工智能技术与方法在其中的应用，并指出了当今这个领域上存在的一些问题，在文章最后，提出了今后研究工作的努力方向。     

基于语音识别的汉语发音自动评分系统的设计与实现

语音识别技术的发展使得人与计算机的交互成为可能,针对目前对外汉语中发音教学的不足,在结合了语音识别的相关原理,提出了在对外汉语教学领域中汉语自动发音水平评价系统的设计,详细地描述了系统的结构、功能及流程.介绍了系统实现中的关键技术和步骤:动态时间弯折算法、语料库的建立、声韵分割技术以及评价分级标准.通过小范围的试验,表明该系统对留学生汉语发音水平的测试有一定的参考价值.     

Research on automatic evaluation method of Mandarin Chinese pronunciation based on 5G network and FPGA

In the automatic evaluation system, need to learn the standard mandarin of scoring method for teaching in native Chinese pronunciation. The most pronounced goal protocols focus on the context in which native speakers are unnatural. The new Hidden Markov Model (HMM) algorithm based on the traditional algorithm likely algorithm for Chinese syllables, whose final initial period is found in the area where evidence for the measurement of weight control has been found. Experiments have also shown that this algorithm is more effective than the traditional posterior recording algorithm of the Mandarin learning method. Force Hidden Markov Model- HMM Align alignment identification for each syllable and associated recording probability for speech evaluation via race-based reliability system applications. These processes could then be formalized as a linear combination after the overall assessment functions: phonics, tone, intensity, and rhythm. Because both linear and non-linear parameters are involved in the overall evaluation functions. Incorporates variation in pronunciation to generate structure through a novel approach that incorporates tons of sub-tones that represent the missing automatic sound models. The word level assessment achieved through the pronunciation is similar to that which in the future showed the singing ability being realized by the evaluation system in full-length pronunciation as a method.     

学习型中文语音识别系统研究及实现

由于中文存在多音多义字,所以相同的发音可能代表不同的含义。而每个人的发音又会有一定的差异。又因为地方方言等原因,导致中文语音控制的正确性或者成功正确地识别变得很困难。采用逆向思维,通过系统记录使用人的发音,并把使用人自己设定的发音绑定到相应的功能或功能命令,以实现学习型的中文语音识别。     

普通话发音评估性能改进

为减少噪声环境对评估性能的影响,该文将PNCC参数引入普通话发音评估。结果表明,其评分相关性在普通话测试实录音数据库上较传统MFCC参数提高了6.6%。在此基础上,对汉语声学模型拆分方法进行了研究,提出将声母介音+韵母模型拆分方法应用到发音评估中。使用这种拆分方式的评估系统总错误率降低5.6%,专家打分相关性则提高了0.056。该文还对模型最佳状态数的选取进行讨论,并提出模型状态数混合和不同配置综合评分两种混合评分方案,在相关性上较同等条件下3状态模型分别提高了0.021和0.017。     

不完全匹配的语音和文本语句级对齐

语音文本自动对齐技术广泛应用于语音识别与合成、内容制作等领域,其主要目的是将语音和相应的参考文本在语句、单词、音素等级别的单元进行对齐,并获得语音与参考文本之间的时间对位信息.最新的先进对齐方法大多基于语音识别,一方面,准确率受限于语音识别效果,识别字错误率高时文语对齐精度明显下降,识别字错误率对对齐精度影响较大;另一方面,这种对齐方法不能有效处理不完全匹配的长篇幅语音和文本的对齐.该文提出一种基于锚点和韵律信息的文语对齐方法,通过基于边界锚点加权的片段标注将语料划分为对齐段和未对齐段,针对未对齐段使用双门限端点检测方法提取韵律信息,并检测语句边界,降低了基于语音识别的对齐方法对语音识别效果的依赖程度.实验结果表明,与目前先进的基于语音识别的文语对齐方法比较,即使在识别字错误率为0.52时,该文所提方法的对齐准确率仍能提升45%以上;在音频文本不匹配程度为0.5时,该文所提方法能提高3%.     

A Multimedia, Multilingual Teaching and Training System for Children with Speech Disorders

The development of an audiovisual pronunciation teaching and training method and software system is discussed in this article. The method is designed to help children with speech and hearing disorders gain better control over their speech production. The teaching method is drawn up for progression from individual sound preparation to practice of sounds in sentences for four languages: English, Swedish, Slovenian, and Hungarian. The system is a general language-independent measuring tool and database editor. This database editor makes it possible to construct modules for all participant languages and for different sound groups. Two modules are under development for the system in all languages: one for teaching and training vowels to hearing-impaired children and the other for correction of misarticulated fricative sounds. In the article we present the measuring methods, the used distance score calculations of the visualized speech spectra, and problems in the evaluation of the new multimedia tool.     

英语句子朗读发音中的音素自动检错系统

为探索智能语音技术在英语发音学习中的作用,开展了面向中国人朗读英语句子的音素发音自动检错技术研究.首先收集了45个人录制的900句英文朗读发音,并由两位专家对音素发音中的错误进行详细的标注,然后基于语音识别技术建立的句子朗读发音中音素自动检错系统,并针对中国人英语发音时最为常见的错读和漏读两大问题,分别提出音素独立检错阈值和限定音素对齐识别网络的方法,对音素检错系统进行了优化,显著地提高了系统的性能,最终系统的召回率和正确率分别达到49%和52%,接近人工专家间的69%召回率下59%的正确率的性能.     

基于韵律特征辅助的端到端语音识别方法

针对传统的语音识别系统采用数据驱动并利用语言模型来决策最优的解码路径,导致在部分场景下的解码结果存在明显的音对字错的问题,提出一种基于韵律特征辅助的端到端语音识别方法,利用语音中的韵律信息辅助增强正确汉字组合在语言模型中的概率。在基于注意力机制的编码-解码语音识别框架的基础上,首先利用注意力机制的系数分布提取发音间隔、发音能量等韵律特征;然后将韵律特征与解码端结合,从而显著提升了发音相同或相近、语义歧义情况下的语音识别准确率。实验结果表明,该方法在1 000 h及10 000 h级别的语音识别任务上分别较端到端语音识别基线方法在准确率上相对提升了5.2%和5.0%,进一步改善了语音识别结果的可懂度。     

Within-word pronunciation variation modeling for Arabic ASRs: a direct data-driven approach

Pronunciation variation is a major obstacle in improving the performance of Arabic automatic continuous speech recognition systems. This phenomenon alters the pronunciation spelling of words beyond their listed forms in the pronunciation dictionary, leading to a number of out of vocabulary word forms. This paper presents a direct data-driven approach to model within-word pronunciation variations, in which the pronunciation variants are distilled from the training speech corpus. The proposed method consists of performing phoneme recognition, followed by a sequence alignment between the observation phonemes generated by the phoneme recognizer and the reference phonemes obtained from the pronunciation dictionary. The unique collected variants are then added to dictionary as well as to the language model. We started with a Baseline Arabic speech recognition system based on Sphinx3 engine. The Baseline system is based on a 5.4 hours speech corpus of modern standard Arabic broadcast news, with a pronunciation dictionary of 14,234 canonical pronunciations. The Baseline system achieves a word error rate of 13.39%. Our results show that while the expanded dictionary alone did not add appreciable improvements, the word error rate is significantly reduced by 2.22% when the variants are represented within the language model.     

Speak-Correct: A Computerized Interface for the Analysis of Mispronounced Errors

Any natural language may have dozens of accents. Even though the equivalent phonemic formation of the word, if it is properly called in different accents, humans do have audio signals that are distinct from one another. Among the most common issues with speech, the processing is discrepancies in pronunciation, accent, and enunciation. This research study examines the issues of detecting, fixing, and summarising accent defects of average Arabic individuals in English-speaking speech. The article then discusses the key approaches and structure that will be utilized to address both accent flaws and pronunciation issues. The proposed SpeakCorrect computerized interface employs a cutting-edge speech recognition system and analyses pronunciation errors with a speech decoder. As a result, some of the most essential types of changes in pronunciation that are significant for speech recognition are performed, and accent defects defining such differences are presented. Consequently, the suggested technique increases the Speaker’s accuracy. SpeakCorrect uses 100 h of phonetically prepared individuals to construct a pronunciation instruction repository. These prerecorded sets are used to train Hidden Markov Models (HMM) as well as weighted graph systems. Their speeches are quite clear and might be considered natural. The proposed interface is optimized for use with an integrated phonetic pronounced dataset, as well as for analyzing and identifying speech faults in Saudi and Egyptian dialects. The proposed interface detects, analyses, and assists English learners in correcting utterance faults, overcoming problems, and improving their pronunciations.