检索结果-南通市图书馆

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2012年第2期27卷 443-450页

作者：李亚丽徐为群颜永红 Key Laboratory of Speech Acoustics and Content Understanding Chinese Academy of Sciences

In this paper,we propose a novel co-occurrence probabilities based similarity measure for inducing semantic *** with the new similarity measure outperforms the widely used distance based on Kullback-Leibler divergence in precision,recall and F1 *** our experiments,we induced semantic classes from unannotated in-domain corpus and then used the induced classes and structures to generate large in-domain corpus which was then used for language model *** recognition rate was improved from 85.2% to 91%.We imply a new measure to solve the lack of domain data problem by first induction then generation for a dialogue system.

关键词： semantic class induction lack of domain data language model adaptation

A General Bayesian Model for Speaker Verification

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第6期25卷 1045-1051页

作者： XU Yunfei YANG Hai YANG Lin ZHOU Ruohua YAN Yonghong Key Laboratory of Speech Acoustics and Content Understanding Institute of AcousticsChinese Academy of Sciences

This paper presents a general Bayesian model for speaker verification tasks. It is a generative probability model. Due to its simple analytical property, a computationally efficient expectation-maximization algorithm can be derived to obtain the model parameters. A closedform solution, which allows the scalable size of enrollment set, is given in a full Bayesian way for making speaker verification decisions. Factor analysis technique is employed to model the speaker-specific components, then the redundant information in this model will be dropped. Experimental results are evaluated by both equal error rate and minimum detection cost function. The proposed approach shows promising results on the National institute of standards and technology(NIST) Speaker recognition evaluation(SRE) 2010 extended and 2012 core tasks. Significant improvement is obtained when comparing with Gaussian probabilistic linear discriminant analysis, especially under phone-call conditions and mismatched train-test channel conditions. Contrast experimental results with other popular generative probability models are also presented in this paper.

关键词： Bayesian model Speaker verification I-Vector

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

波场合成与波场分析的有源房间补偿方法

声学学报 2014年第1期39卷 137-144页

作者：李娟付强颜永红中国科学院语言声学与内容理解重点实验室北京100190

波场合成是一种空间声重放技术,利用扬声器阵列在宽阔的听音区域内重建声场。为消除或者消减听音房间的反射对重建波场的影响,利用测量环绕听音区域的闭合曲线上声压和声压梯度来分析波场,推导了基于圆形阵列进行波域分解的公式,利用多... 详细信息

波场合成是一种空间声重放技术,利用扬声器阵列在宽阔的听音区域内重建声场。为消除或者消减听音房间的反射对重建波场的影响,利用测量环绕听音区域的闭合曲线上声压和声压梯度来分析波场,推导了基于圆形阵列进行波域分解的公式,利用多通道逆滤波进行了平面波域的房间补偿,实验结果显示该算法在整个听音区域内都是有效的。与传统补偿方法相比,边界元法所需的测量传声器数目少计算复杂度低,而波域分解具有更充分的波场分析能力,因此是一种更有效的有源房间补偿方法.

关键词：补偿方法波场分析听音房间波场合成有源测量传声器听音区域声压梯度

在线全文

学校读者我要写书评

暂无评论

波场合成中声像感知距离重建

声学学报 2013年第6期38卷 743-748页

作者：李娟李军锋颜永红中国科学院语言声学与内容理解重点实验室北京100190

声像距离是声像位置的重要信息,为了完整地描述重建声场中感知声像位置,需在虚拟声场中重建出声像距离。本文基于人耳对距离的感知机理,将镜像法引入波场合成技术中,通过模拟反射声来控制感知声像距离。基于"比较判断律"的主观测听实验... 详细信息

声像距离是声像位置的重要信息,为了完整地描述重建声场中感知声像位置,需在虚拟声场中重建出声像距离。本文基于人耳对距离的感知机理,将镜像法引入波场合成技术中,通过模拟反射声来控制感知声像距离。基于"比较判断律"的主观测听实验表明:通过模拟房间反射声受试者更明显地感受到声像距离的变化,并且变化规律与人耳对距离的感知机理相符合。因此在基于波场合成的声重放系统中,通过模拟反射声和有效地控制反射声能量可以准确地重建出声像距离。

关键词：波场合成距离声像感知反射声合成技术变化规律重放系统

A Robust Step-Size Control Technique Based on Proportionate Constraints on Filter Update for Acoustic Echo Cancellation

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第4期25卷 692-699页

作者： WU Chao JIANG Kaiyu WANG Xiaofei GUO Yanmeng FU Qiang YAN Yonghong Institute of Acoustics Chinese Academy of Sciences

One of the main difficulties in Acoustic echo cancellation(AEC) is that the filter adaptation needs to vary according to different situations such as near-end interferences and echo path *** this paper,we propose a robust step-size control algorithm in frequency *** proposed method is based on the optimization of the square of the bin-wise a posteriori *** on the filter update is applied,which contributes to robustness to near-end interferences of the *** learning rate formula is derived first and then the relationship between the proposed algorithm and a robust statistics based approach is *** method is extended to the Multidelay block frequency domain adaptive filter(MDF) so as to meet the demand of low delay in practical ***,the values of the constraints are designed to be updated proportionately to improve the convergence *** results demonstrate the superiority of the proposed algorithm.

关键词： Acoustic echo cancellation(AEC) Stepsize control Proportionate constraints Robust filtering

Speech Enhancement Using Multi-channel Post-Filtering with Modified Signal Presence Probability in Reverberant Environment

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第03期25卷 512-519页

作者： WANG Xiaofei GUO Yanmeng FU Qiang YAN Yonghong Key Laboratory of Speech Acoustics and Content Understanding Institute of AcousticsChinese Academy of Sciences

In this paper, a multi-channel post-filtering approach in reverberant environment based on detection and estimation scheme is presented. A modified Signal presence probability(SPP), which is in consideration of reverberation, is proposed with a novel estimator Direct-toreverberate ratio(DRR) to adapt to distant-talking *** is known a key estimator to instruct the updating of transient noise or residual directional interference and form gain function in the time-frequency domain, consequently a new desired signal detection scheme is proposed to improve its accuracy. Appropriate spectral enhancement technique is applied to the noisy speech signal taking advantage of the modified SPP estimator. The proposed multi-channel post-filtering is tested in different nonstationary noisy and reverberant environments. Experimental results show that it achieves considerable improvement on signal preservation of the desired speech with more noise reduction over the comparative algorithms.

关键词： Speech enhancement Multi-channel post-filtering Reverberation robust Signal detection

嵌入式中文语音合成系统非周期成分音节层建模方法

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

清华大学学报（自然科学版） 2013年第6期53卷 767-770,780页

作者：王朝民谢湘匡镜明北京理工大学信息与电子学院北京100081

当前主流参数化语音合成系统大多采用混合激励的源-滤波器模型,而非周期成分是影响合成音音质的重要参数。该文探讨了如何更有效地对非周期成分建模以及在嵌入式语音合成系统中非周期成分的模型规模如何尽可能压缩。该文通过分析得到非... 详细信息

当前主流参数化语音合成系统大多采用混合激励的源-滤波器模型,而非周期成分是影响合成音音质的重要参数。该文探讨了如何更有效地对非周期成分建模以及在嵌入式语音合成系统中非周期成分的模型规模如何尽可能压缩。该文通过分析得到非周期成分在中文音节中前后帧存在较强相关性,因此在一个音节内一段固定频段上,可以对非周期成分形成的一条连续轨迹通过离散余弦变换(dis-crete cosine transformation,DCT)来拟合。实验证明,该方法在保持合成音音质与基线系统相当的情况下,可以将分带非周期成分(band aperiodicity,BAP)模型的大小压缩到原来的6.64%。

关键词：非周期成分音节层建模语音合成

PLF Optimization for Target Language Detection

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2017年第1期26卷 118-121页

作者： ZHANG Jian YUAN Qingsheng BAO Xiuguo ZHOU Ruohua YAN Yonghong Institute of Information Engineering Chinese Academy of Sciences Institute of Acoustics Chinese Academy of Sciences National Computer Network Emergency Response Technical Team/Coordination Center of China

The objective of traditional feature studies in Spoken language recognition(SLR) is extracting the linguistic discrimination between each language. However,applications of security area always interested in a particular language, which requires the features should be the best reflection of the differences between target language and the other languages. To address this problems, the frame level Phone log-posteriors feature(PLF), which has been recently introduced as a novel and effective feature in SLR, is optimized to get a better performance on Target language detection(TLD) task. The F-Ratio analysis method is used to analyze the contribution of each dimension in feature vector for TLD. In this work, frame level phone posterior probabilities are estimated by a phone recognizer, and processed through taking logarithm. Then the feature is optimized through weighting each dimension according to the F-Ratio values. Finally, Principal component analysis(PCA) is used to decorrelate the feature and reduce vector size. Experiments carried out on the NIST LRE 2007 dataset show that the effectiveness of the optimized feature, which yields significant relative improvements in term of Equal error rate(EER) with regard to the Gaussian mixture models-Support vector machines(GMM-SVM) system based on the original feature.

关键词： Spoken language recognition Target language detection Weighted phone log-posteriors F-Ratio

多特征融合的英语口语考试自动评分系统的研究

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

电子与信息学报 2012年第9期34卷 2097-2102页

作者：李艳玲颜永红中国科学院声学研究所语言声学与内容理解实验室北京100190 内蒙古师范大学计算机与信息工程学院呼和浩特010022

该文主要针对大规模英语口语考试自动评分系统的问答题型,采用多特征融合的方法进行评分。以语音识别文本作为研究对象,提取了3类特征进行评分。这3类特征分别是:相似度特征、句法特征和语音特征。总共9个特征从不同方面描述了考生回答... 详细信息

该文主要针对大规模英语口语考试自动评分系统的问答题型,采用多特征融合的方法进行评分。以语音识别文本作为研究对象,提取了3类特征进行评分。这3类特征分别是:相似度特征、句法特征和语音特征。总共9个特征从不同方面描述了考生回答与专家评分之间的关系。在相似度特征中,改进了Manhattan距离作为相似度。同时提出了基于编辑距离的关键词覆盖率的特征,充分考虑了识别文本中存在的单词变异现象,为给考生一个客观公平的分数提供依据。所有提取的特征利用多元线性回归模型进行融合,得到机器评分。实验结果表明,提取的特征对机器评分是十分有效的,并且在以考生为单位的系统评分性能达到了专家评分性能的98.4%。

关键词：自动语音识别自动评分特征选择相似度句法树