登录

双语推荐：phoneme

进入期刊文章
提出了一种基于音素后验概率和层次凝聚聚类算法的音素边界检测方法。该方法首先利用改进的TRAP结构提取语音信号的帧级音素后验概率;然后,运用层次凝聚聚类算法将提取的音素后验概率进行聚类分析;最后根据其全部的最小损失函数值获取阈值,并通过此阈值决定聚类数目和音素边界。实验证明:该方法具有较好的检测性能,且相对于梅尔倒谱参数(MFCC),音素后验概率更为适合音素边界的检测。
A method of phoneme boundary detection based on phoneme posterior probability and Hierarchical Agglomerative Clustering(HAC) is presented. According to this method, phoneme posterior probabilities should first of all be got by Temporal Pattern(TRAP), and then HAC algorithm is chosen to cluster the phoneme posterior probability. Finally, a reasonable threshold can be obtained by all loss function values, and the number of clusters and the phoneme boundaries can be determined by the threshold. The experimental results show that this method is efficient and bears a good detection performance; and the phoneme posterior probabilities are more suitable for phoneme boundary detection than the Mel-Scale Frequency Cepstral Coefficients(MFCC).

[ 可能符合您检索需要的词汇 ]

进入期刊文章
探讨Broca失语的语音障碍、错误特点和原因。方法:选取2011年6月至2013年6月期间我院收治的文化程度为初中以上的Broca失语患者84例。根据《黄昭鸣-韩知娟词表》中的33个词和患者接受失语症检查时的现场录音材料对患者的单个声母音位发音和韵母音位发音错误进行分析,并根据分析结果和系统有序的音位治疗框架分析Broca失语语音障碍的原因和治疗策略。结果:患者单个声母音位发音错误以t、l、k、j、q、c、s、zh、ch以及sh为主,亦有部分患者发生除m外的其他声母音位发音错误,单个韵母音位发音错误的发生率均较低,其中发生率超过5%的有e、i、ü、ei、ian和er,发生率超过10%只有i,差异有统计学意义(P0.01)。患者音位发音错误类型以替换错误为主(80.95%),亦有部分患者发生省略错误(10.71%)和增加错误(13.10%),差异有统计学意义(P0.01)。结论:Broca失语患者的语音障碍主要表现在声母上,部分患者亦可出现韵母发音错误。患者的发音错误以类似替换为主。因此可根据患者的个体情况通过口型、舌位等的纠正实现音位矫正、辅助患者获得正确发音。
[ABSTRACT]Objective: To explore the voice disorders and their error characteristics and the reason of patients with Broca aphasia. Methods:84 patients with Broca aphasia and junior high school or above school education in our hospital from June,2011 to June, 2013 culture for the above were selected. single phoneme pronunciation and pronunciation phoneme pronunciation errors of the patients was analyzed according to 33 words of"Zhao-ming huang-Han Zhijuan glossary"and aphasia examination results taken in recording material, and the reasons and treatment strategies for voice disorders was analyzed according to the results of analysis and treatment system and orderly phoneme framework.Results:Single consonant phoneme pronunciation errors mainly occurs on t, l, k, j, q, c, s, zh, ch, sh, and some patients also have error occurred on other initials phonemes. The incidence of single final phoneme pronunciation errors is low. The phoneme pronunciation error incidence under 5% are e,

[ 可能符合您检索需要的词汇 ]

进入期刊文章
基于注意理论、记忆理论、词块音位重复理论,针对音位重复对词块记忆的影响进行探索,旨在为中国英语学习者提供词块的补充性学习策略。研究发现:音位重复的词块和无音位重复的词块的助记效果有显著性差异;单词重复和押尾韵(双韵)的助记效果最好,押元音韵的助记效果最差,押头韵的助记效果居中。
The effects of phonemic repetition on retention of English lexical chunks are explored based on noticing hy-pothesis, memory theory and theory of phonemic repetition of lexical chunks aiming to enrich the lexis-learning and lex-ical chunks-learning strategies The findings prove that there is a significant difference between phonemic repetition and non-phonemic repetition on retention of English lexical chunks. Among the four types, the effects of word repetition and rhyme have the highest mnemonic level whereas assonance has the lowest with alliteration ranked as the medium level.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
以建立维吾尔语连续音素识别基础平台为目标,在HTK(基于隐马尔可夫模型的工具箱)的基础上,首次研究了其语言相关环节的几项关键技术;结合维吾尔语的语言特征,完成了用于语言模型建立和语音语料库建设的维吾尔语基础文本设计;根据具体技术指标,录制了较大规模语音语料库;确定音素作为基元,训练了维吾尔语声学模型;在基于字母的N-gram语言模型下,得出了从语音句子向字母序列句子的识别结果;统计了维吾尔语32个音素的识别率,给出了容易混淆的音素及其根源分析,为进一步提高识别率奠定了基础。
In this paper, HTK(Hidden Markov model-based Toolkit)based Uyghur continuous phoneme recognition baseline system is presented, and its several language-depended key technologies are addressed. According to the characteristics of Uyghur language, it designs the text corpus for language modeling and speech corpus construction, and records a large-scale speech data for training the phoneme based Uyghur acoustic model. The different recognition rates with different N-gram language models are also given. The statistics of the recognition rates of 32 Uyghur phonemes, the list of the confused phonemes and their possible reasons are analyzed. And then it gives some research directions for further improvements to the baseline system.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
依据异类文种之间、同类文种不同语音之间存在音素数据关联的特性，提出多文种语音数据融合编码方法。将不同文种存在的相同音素数据段块按段块模板截取语音样本序列，小波变换，提取特征矢量，生成共享模板集；任意字音或语句音串均按共享模板集提供的元素进行编码与解码；以模板音素串构成的语音记录库按（音节、音素）索引。实验结果表明，单字语音数据压缩比、语音数据存储量、语音还原分段信噪比、主观评价得分等参数均明显优于已有方法，语音还原质量良好。
Multilingual speech data fusion coding method is proposed according to the phoneme data correlation properties, which exist among heterogeneous languages and different words in the same language. Voice sample sequences of the same phoneme data segment in different languages are intercepted according to the segment templates, wavelet transform is done to those sequences, then feature vectors is extracted to generate shared template sets. Speech data of any word or sentence are coded or decoded according to the template sets. The speech record database made up of template phoneme sets is indexed according to (syllable, phoneme)structure. The single word compression ratio, speech data size, segmental signal-to-noise ratio(SNRS)and score of subjective evaluation(MOS)are significantly better than existing methods, also the voice restoration is of good quality.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
母语语音迁移现象的出现在日语教学过程中是不可避免的一个环节。正确利用正迁移，避免负迁移对于学习者的语音学习效果和效率会产生巨大影响。从发音系统上来看，粤语的音位相对复杂，而日语相对简单。灵活利用粤语音位较多的发音特点，将其引入日语语音的教学过程的同时，辨清粤语中缺乏而日语中却包含的特殊音位，进行有针对性的教学，必将对日语学习者发音错误的预防和纠正起到有效作用。
Migration phenomenon occurs native speech is an inevitable part of the process of teaching in Japanese. Correct use of regular migration;avoid negative transfer for speech learning effectiveness and efficiency of learners will have a huge impact. From the sound system, the Cantonese phoneme is relatively complex, but Japanese is relatively simple. More flex-ible use of Cantonese pronunciation of phonemes features will be introduced into the teaching process, while the Japanese voice, discern the lack of Cantonese and Japanese in particular phonemes but included targeted education, is bound to Japa-nese learners pronunciation errors play an effective role in the prevention and correction.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
音素教学是对韩汉语语音教学的重要环节，直接决定学生能否建立起正确的汉语语音系统，形成良好的汉语发音习惯。如何提高音素教学的效果，改善韩国学习者的“韩腔怪调”和“哑巴汉语”的状况，一直是对韩汉语教学研究的课题。笔者根据在韩国高校一年的授课情况，从音素教学的教学顺序和教学方法两方面，梳理、总结和推广对韩汉语语音教学的实践经验，以期对韩汉语教学提供新的视角和经验。
Phoneme teaching plays an important role in phonetic teaching for Korean learners of the Chinese language. It is crucial in establishing a proper Chinese phonetic system among learners,which is fundamental in good pronunciation habits. Researchers in the past have investigated into related topics such as how to enhance better results in phonic teaching,ways to tackle with the“Mute Chinese Language”phenomenon etc.. Based on her one-year teaching experience in Korea and departing from the perspectives of teaching order and methodology in phoneme teaching,the author analyses and summarises her personal experience in Chinese phoneme teaching to Korean learners. It is hoped that the study would provide insights and reference to the field of teaching-Chinese-to-Korean-learners.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
言语感知遵循音不离词，词不离句的原则。除了语音特征、音位和单词三个感知单元外，句子单元也参与了言语感知的过程。在这一感知过程中，句子语境分别从句法和语义两方面对词汇的识别发生影响。在句法方面，句子层依据句法规则对词汇层产生自上而下的反馈作用，通过词类限制和曲折形态特征核查等方式实现对词汇层上备选单词的筛选；在语义方面，句子层根据语义限制条件对备选单词产生激活或抑制作用。
Phonemes, words and sentences are interconnected in speech perception. Besides phonetic features, phonemes and words, sentences are also engaged in speech perception. In speech perception, sentimental contexts exert influence on word recog-nition both syntactically and semantically. Syntactically, sentence levels exert top-down feedback effect on world levels according to syntactic rules, screening the candidates on word levels by constraining their part of speech or checking their inflectional fea-tures. Semantically, sentence levels activate pr inhibit the candidates by exerting semantic constraints.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
英语专业的语音教学对于提高学生整体水平至关重要,但在实际的教学中很难取得理想的效果。通过对中国教师班级和外籍教师班级语音课教学效果调查,从英语语音音段音位、超音段音位和非语言因素等方面进行分项研究,采取学生自评的方法获得对比数据,得出应该结合中国教师和外籍教师语音教学的优势进行英语语音教学的结论。
English pronunciation teaching, which is of great importance to improve the overall level of English majors, can hardly achieve the ideal effect. This article makes an empirical study of English pronunciation teaching in the classes of a Chinese teacher and a native English teacher in terms of segmental phonemes, suprasegmental phonemes and non-verbal factors. By analyzing the students’self-evaluation, we can find the advantages of Chinese teachers and native English teachers in English pronunciation teaching and combine them together accordingly in classes to get better results.

[ 可能符合您检索需要的词汇 ]

进入期刊文章
提出一种基于话者无关模型的说话人转换方法.考虑到音素信息共同存在于所有说话人的语音中,假设存在一个可以用高斯混合模型来描述的话者无关空间,且可用分段线性变换来描述该空间到各说话人相关空间之间的映射关系.在一个多说话人的数据库上,用话者自适应训练算法来训练模型,并在转换阶段使用源目标说话人空间到话者无关空间的变换关系来构造源与目标之间的特征变换关系,快速、灵活的构造说话人转换系统.通过主观测听实验来验证该算法相对于传统的基于话者相关模型方法的优点.
@@@@A voice conversion method based on speaker independent (SI) model is proposed. Considering the phoneme information that commonly exists in every speaker's speech, an SI space described only by the phoneme information is assumed to exist. Gaussian mixture model ( GMM) is adopted to model the distribution of the SI space, and the mapping relations from speaker dependent (SD) space to SI space are described by linear transformations. The SI model is trained by using speaker adaptive training (SAT) algorithm on a multi-speaker database. In the conversion phase, the conversion function from source space to target space is quickly and flexibly built by joining the transformations from source space to SI space and SI space to target space. The advantage of the proposed method is proved by the results of some listening tests compared with two representative conventional methods.

[ 可能符合您检索需要的词汇 ]