A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize...A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.展开更多
Objective:To investigate the neural electrophysiologieal activity underlying Chinese and Eng- lish Stroop tasks for Chinese English bilinguals.Methods:Event-related potentials(ERPs)were recorded in 14 Chinese bilingua...Objective:To investigate the neural electrophysiologieal activity underlying Chinese and Eng- lish Stroop tasks for Chinese English bilinguals.Methods:Event-related potentials(ERPs)were recorded in 14 Chinese bilinguals with a moderate command of English when they performed the Stroop task pre- sented in English words and Chinese characters,respectively.Results:In Chinese task version,it was found an increased positivity over bilateral front-polar regions on incongruent trials compared with congru- ent trials,followed by an increased negativity over fronto-central region and an increased positivity over occipital region.While in English task version,only the increased negativity was observed over fronto-cen- tral region,but with reduced amplitude and anterior distribution.Conclusion:This increased negativity was proposed as an index of the resolution processes of conflicting information in the incongruent situa- tion.The increased positivity over occipital region on Chinese incongruent trials may indicate visually rechecking effect for Chinese character.展开更多
The term ＂Experimental＂ in the title means, that the synthesizer is constructed as tool to conduct experiments, for investigating the influence of environment of unit on sounding of it. Synthesizer as tool for testi...The term ＂Experimental＂ in the title means, that the synthesizer is constructed as tool to conduct experiments, for investigating the influence of environment of unit on sounding of it. Synthesizer as tool for testing of hypotheses and results of experiments, satisfy three conditions： independence from the selection of unit for the synthesis （word or any part of it）; taking into account the environment of unit （left and right hand contexts and position of unit）; independence from the content of base. Such synthesizer is a good tool for studying many aspects of speech and removes the problem of selection. We can vary the unit and other parameters, described in paper, by the same synthesizer, synthesize the same text and listen to the results directly. This paper describes the formal structure of experimental Georgian speech synthesizer.展开更多
Multilingual Education Programs Regulation was adopted and the implementation of bilingual educational reform started in Georgia in 2010. The paper presents research results on readiness of non-Georgian schools to imp...Multilingual Education Programs Regulation was adopted and the implementation of bilingual educational reform started in Georgia in 2010. The paper presents research results on readiness of non-Georgian schools to implement multilingual educational programs effectively. The research studied the important factors influencing the effectiveness of bilingual educational programs, specifically （1） type of program, （2） human resources of schools and teachers professional development, （3） bilingual education as shared vision for all school stakeholders, and （4） community and parental involvement in designing and implementation of bilingual educational programs. The following research methods were used during the research： （1） quantitative and qualitative content analysis of bilingual educational programs of 26 non-Georgian schools of Kvemo Kartli and Samtskhe-Javakheti regions of Georgia, （2） quantitative survey of non-Georgian school principals through questionnaires, and （3） quantitative survey of non-Georgian schools＇ teachers of different subjective groups through questionnaire. The study revealed that schools are implementing mostly ＂weak＂ bilingual educational programs. The schools implementing bilingual educational programs do not have sufficient human resources, bilingual education is not a shared vision for all school stakeholders and parents and community are not actively involved in designing and implementation of the programs.展开更多
The performance of the traditional Voice Activity Detection （VAD） algorithms declines sharply in lower Signal-to-Noise Ratio （SNR） environments. In this paper, a feature weighting likelihood method is proposed for...The performance of the traditional Voice Activity Detection （VAD） algorithms declines sharply in lower Signal-to-Noise Ratio （SNR） environments. In this paper, a feature weighting likelihood method is proposed for noise-robust VAD. The contribution of dynamic features to likelihood score can be increased via the method, which improves consequently the noise robustness of VAD. Divergence based dimension reduction method is proposed for saving computation, which reduces these feature dimensions with smaller divergence value at the cost of degrading the performance a little. Experimental results on Aurora Ⅱ database show that the detection performance in noise environments can remarkably be improved by the proposed method when the model trained in clean data is used to detect speech endpoints. Using weighting likelihood on the dimension-reduced features obtains comparable, even better, performance compared to original full-dimensional feature.展开更多
Software tools are developed for computer realization of syntactic, semantic, and morphological models of natural language texts, using rule based programming. The tools are efficient for a language, which has free or...Software tools are developed for computer realization of syntactic, semantic, and morphological models of natural language texts, using rule based programming. The tools are efficient for a language, which has free order of words and developed morphological structure like Georgian. For instance, a Georgian verb has several thousand verb-forms. It is very difficult to express rules of morphological analysis by finite automaton and it will be inefficient as well. Resolution of some problems of full morphological analysis of Georgian words is impossible by finite automaton. Splitting of some Georgian verb-forms into morphemes requires non-deterministic search algorithm, which needs many backtrackings. To minimize backtrackings, it is necessary to put constraints, which exist among morphemes and verify them as soon as possible to avoid false directions of search. Software tool for syntactic analysis has means to reduce rules, which have the same members in different order. The authors used the tool for semantic analysis as well. Thus, proposed software tools have many means to construct efficient parser, test and correct it. The authors realized morphological and syntactic analysis of Georgian texts by these tools. In the presented paper, the authors describe the software tools and its application for Georgian language.展开更多
In this paper, we applied RobustICA to speech separation and made a comprehensive comparison to FastICA according to the separation results. Through a series of speech signal separation test, RobustICA reduced the sep...In this paper, we applied RobustICA to speech separation and made a comprehensive comparison to FastICA according to the separation results. Through a series of speech signal separation test, RobustICA reduced the separation time consumed by FastICA with higher stability, and speeches separated by RobustICA were proved to having lower separation errors. In the 14 groups of speech separation tests, separation time consumed by RobustICA was 3.185 s less than FastICA by nearly 68%. Separation errors of FastICA had a float between 0.004 and 0.02, while the errors of RobustlCA remained around 0.003. Furthermore, compared to FastICA, RobustlCA showed better separation robustness. Experimental results showed that RohustICA was successful to apply to the speech signal separation, and showed superiority to FastlCA in speech separation.展开更多
In this paper, we introduce and discuss the robustness of contextuality（Ro C） R_C（e） and the contextuality cost C（e） of an empirical model e. The following properties of them are proved.（i） An empirical model ...In this paper, we introduce and discuss the robustness of contextuality（Ro C） R_C（e） and the contextuality cost C（e） of an empirical model e. The following properties of them are proved.（i） An empirical model e is contextual if and only if R_C（e） ＆gt; 0;（ii） the Ro C function R_C is convex, lower semi-continuous and un-increasing under an affine mapping on the set E M of all empirical models;（iii） e is non-contextual if and only if C（e） = 0;（iv） e is contextual if and only if C（e） ＆gt; 0;（v） e is strongly contextual if and only if C（e） = 1. Also, a relationship between RC（e） and C（e） is obtained. Lastly, the Ro C of three empirical models is computed and compared. Especially, the Ro C of the PR boxes is obtained and the supremum 0.5 is found for the Ro C of all no-signaling type（2, 2, 2） empirical models.展开更多
基金The National Natural Science Foundation of China (No.61231002,61273266,51075068,60872073,60975017, 61003131)the Ph.D.Programs Foundation of the Ministry of Education of China(No.20110092130004)+1 种基金the Science Foundation for Young Talents in the Educational Committee of Anhui Province(No. 2010SQRL018)the 211 Project of Anhui University(No.2009QN027B)
文摘A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.
文摘Objective:To investigate the neural electrophysiologieal activity underlying Chinese and Eng- lish Stroop tasks for Chinese English bilinguals.Methods:Event-related potentials(ERPs)were recorded in 14 Chinese bilinguals with a moderate command of English when they performed the Stroop task pre- sented in English words and Chinese characters,respectively.Results:In Chinese task version,it was found an increased positivity over bilateral front-polar regions on incongruent trials compared with congru- ent trials,followed by an increased negativity over fronto-central region and an increased positivity over occipital region.While in English task version,only the increased negativity was observed over fronto-cen- tral region,but with reduced amplitude and anterior distribution.Conclusion:This increased negativity was proposed as an index of the resolution processes of conflicting information in the incongruent situa- tion.The increased positivity over occipital region on Chinese incongruent trials may indicate visually rechecking effect for Chinese character.
文摘The term ＂Experimental＂ in the title means, that the synthesizer is constructed as tool to conduct experiments, for investigating the influence of environment of unit on sounding of it. Synthesizer as tool for testing of hypotheses and results of experiments, satisfy three conditions： independence from the selection of unit for the synthesis （word or any part of it）; taking into account the environment of unit （left and right hand contexts and position of unit）; independence from the content of base. Such synthesizer is a good tool for studying many aspects of speech and removes the problem of selection. We can vary the unit and other parameters, described in paper, by the same synthesizer, synthesize the same text and listen to the results directly. This paper describes the formal structure of experimental Georgian speech synthesizer.
文摘Multilingual Education Programs Regulation was adopted and the implementation of bilingual educational reform started in Georgia in 2010. The paper presents research results on readiness of non-Georgian schools to implement multilingual educational programs effectively. The research studied the important factors influencing the effectiveness of bilingual educational programs, specifically （1） type of program, （2） human resources of schools and teachers professional development, （3） bilingual education as shared vision for all school stakeholders, and （4） community and parental involvement in designing and implementation of bilingual educational programs. The following research methods were used during the research： （1） quantitative and qualitative content analysis of bilingual educational programs of 26 non-Georgian schools of Kvemo Kartli and Samtskhe-Javakheti regions of Georgia, （2） quantitative survey of non-Georgian school principals through questionnaires, and （3） quantitative survey of non-Georgian schools＇ teachers of different subjective groups through questionnaire. The study revealed that schools are implementing mostly ＂weak＂ bilingual educational programs. The schools implementing bilingual educational programs do not have sufficient human resources, bilingual education is not a shared vision for all school stakeholders and parents and community are not actively involved in designing and implementation of the programs.
基金Supported by the National Basic Research Program of China (973 Program) (No.2007CB311104)
文摘The performance of the traditional Voice Activity Detection （VAD） algorithms declines sharply in lower Signal-to-Noise Ratio （SNR） environments. In this paper, a feature weighting likelihood method is proposed for noise-robust VAD. The contribution of dynamic features to likelihood score can be increased via the method, which improves consequently the noise robustness of VAD. Divergence based dimension reduction method is proposed for saving computation, which reduces these feature dimensions with smaller divergence value at the cost of degrading the performance a little. Experimental results on Aurora Ⅱ database show that the detection performance in noise environments can remarkably be improved by the proposed method when the model trained in clean data is used to detect speech endpoints. Using weighting likelihood on the dimension-reduced features obtains comparable, even better, performance compared to original full-dimensional feature.
文摘Software tools are developed for computer realization of syntactic, semantic, and morphological models of natural language texts, using rule based programming. The tools are efficient for a language, which has free order of words and developed morphological structure like Georgian. For instance, a Georgian verb has several thousand verb-forms. It is very difficult to express rules of morphological analysis by finite automaton and it will be inefficient as well. Resolution of some problems of full morphological analysis of Georgian words is impossible by finite automaton. Splitting of some Georgian verb-forms into morphemes requires non-deterministic search algorithm, which needs many backtrackings. To minimize backtrackings, it is necessary to put constraints, which exist among morphemes and verify them as soon as possible to avoid false directions of search. Software tool for syntactic analysis has means to reduce rules, which have the same members in different order. The authors used the tool for semantic analysis as well. Thus, proposed software tools have many means to construct efficient parser, test and correct it. The authors realized morphological and syntactic analysis of Georgian texts by these tools. In the presented paper, the authors describe the software tools and its application for Georgian language.
基金National Natural Science Foundation of Chinagrant number:61271082,61201029,61102094
文摘In this paper, we applied RobustICA to speech separation and made a comprehensive comparison to FastICA according to the separation results. Through a series of speech signal separation test, RobustICA reduced the separation time consumed by FastICA with higher stability, and speeches separated by RobustICA were proved to having lower separation errors. In the 14 groups of speech separation tests, separation time consumed by RobustICA was 3.185 s less than FastICA by nearly 68%. Separation errors of FastICA had a float between 0.004 and 0.02, while the errors of RobustlCA remained around 0.003. Furthermore, compared to FastICA, RobustlCA showed better separation robustness. Experimental results showed that RohustICA was successful to apply to the speech signal separation, and showed superiority to FastlCA in speech separation.
基金supported by the National Natural Science Foundation of China(Grant Nos.1137101211401359+1 种基金11471200 and 11571213)the Fundamental Research Funds for the Central Universities(Grant No.GK201301007)
文摘In this paper, we introduce and discuss the robustness of contextuality（Ro C） R_C（e） and the contextuality cost C（e） of an empirical model e. The following properties of them are proved.（i） An empirical model e is contextual if and only if R_C（e） ＆gt; 0;（ii） the Ro C function R_C is convex, lower semi-continuous and un-increasing under an affine mapping on the set E M of all empirical models;（iii） e is non-contextual if and only if C（e） = 0;（iv） e is contextual if and only if C（e） ＆gt; 0;（v） e is strongly contextual if and only if C（e） = 1. Also, a relationship between RC（e） and C（e） is obtained. Lastly, the Ro C of three empirical models is computed and compared. Especially, the Ro C of the PR boxes is obtained and the supremum 0.5 is found for the Ro C of all no-signaling type（2, 2, 2） empirical models.
