UPON the establishment of European universities in the Middle Ages,the educational system in Western countries became characterized by an essentially Eurocentric worldview.This was reflected in the study of Latin and ...UPON the establishment of European universities in the Middle Ages,the educational system in Western countries became characterized by an essentially Eurocentric worldview.This was reflected in the study of Latin and Greek in high school,and in basing public life and political systems on philosophies of classical antiquity.The work of the influential Chinese philosopher Confucius(551-479 B.C.),a near-contemporary of the major Greek philosophers Socrates(469-399 B.C.),Plato(428-348 B.C.)and Aristotle(384-322 B.C.),whose ethical and political ideas entered into the constitutions of European states,remained unknown.展开更多
The exhibition presents the life of Confucius and the essence of his thoughts through plates,accompanied by replicas of related cultural objects and cultural creative products,with the purposeof helping local people u...The exhibition presents the life of Confucius and the essence of his thoughts through plates,accompanied by replicas of related cultural objects and cultural creative products,with the purposeof helping local people understand the origin of Confucianism and presenting the modern charm of traditional culture.展开更多
“The Belt and Road”cooperation initiative contains Chinese excellent traditional cultural ideas,and is deeply rooted in Chinese excellent traditional culture.The proposal of“the Belt and Road”cooperation initiativ...“The Belt and Road”cooperation initiative contains Chinese excellent traditional cultural ideas,and is deeply rooted in Chinese excellent traditional culture.The proposal of“the Belt and Road”cooperation initiative is not only the strategic need to implement the“going out”of Chinese culture,but also the need to promote cultural exchanges and mutual learning among countries along“the Belt and Road”,and more importantly,the practical consideration of building a community of shared future for mankind with cultural identity.Confucius classroom,as one of the important platforms to realize the“going out”of Chinese culture,shows the“image of China”and enhances the“soft power”of Chinese culture,integrates and configures Chinese teaching and Chinese cultural resources through cooperation,and plays an important role in telling Chinese stories,spreading Chinese voice,enhancing cultural mutual trust and people-to-people contacts as well as the awareness of a community of shared future for mankind.Taking the Confucius classroom jointly built by Huanggang Normal University in China and Sabaragamuwa University in Sri Lanka as an example,this paper explores some effective transmission ways for spreading Chinese excellent traditional culture in Sri Lankan Confucius classroom under the background of“the Belt and Road”cooperation initiative,aiming to give full play to the role of Confucius classroom in cultural exchanges and enhance inter-school exchanges and cooperation between China and Sri Lanka in terms of cultural mutual trust and respect.展开更多
Lun Yu or The Analects,a masterpiece of ancient Chinese thought,contains Chinese Confucianism and the values and ways of doing things that it represents.This paper focuses on the interpretation and translation of“p...Lun Yu or The Analects,a masterpiece of ancient Chinese thought,contains Chinese Confucianism and the values and ways of doing things that it represents.This paper focuses on the interpretation and translation of“péng(朋)”and“yǒu(友)”in the translations by James Legge,Arthur Waley,Koo Hung-ming,and Xu Yuanchong respectively to explore the similarities and differences between Chinese and Western cultures and the concepts held by different translators in the way of conducting oneself in society.展开更多
Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning...Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.展开更多
Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is ext...Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.展开更多
Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hate...Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hatespeech, but they still suffer from ambiguity when differentiating between hateful and offensive content and theyalso lack accuracy. The work suggested in this paper uses a combination of the Whale Optimization Algorithm(WOA) and Particle Swarm Optimization (PSO) to adjust the weights of two Multi-Layer Perceptron (MLPs)for neutrosophic sets classification. During the training process of the MLP, the WOA is employed to exploreand determine the optimal set of weights. The PSO algorithm adjusts the weights to optimize the performanceof the MLP as fine-tuning. Additionally, in this approach, two separate MLP models are employed. One MLPis dedicated to predicting degrees of truth membership, while the other MLP focuses on predicting degrees offalse membership. The difference between these memberships quantifies uncertainty, indicating the degree ofindeterminacy in predictions. The experimental results indicate the superior performance of our model comparedto previous work when evaluated on the Davidson dataset.展开更多
Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotiona...Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.展开更多
In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a p...In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.展开更多
The teaching of English speeches in universities aims to enhance oral communication ability,improve English communication skills,and expand English knowledge,occupying a core position in English teaching in universiti...The teaching of English speeches in universities aims to enhance oral communication ability,improve English communication skills,and expand English knowledge,occupying a core position in English teaching in universities.This article takes the theory of second language acquisition as the background,analyzes the important role and value of this theory in English speech teaching in universities,and explores how to apply the theory of second language acquisition in English speech teaching in universities.It aims to strengthen the cultivation of English skilled talents and provide a brief reference for improving English speech teaching in universities.展开更多
林语堂的翻译活动前后跨越了半个世纪,历经了中国"五四"新文化运动和美国20世纪50年代"反文化"运动和现代性的冲击。他的译品,就犹如他的创作一样,带有鲜明的中西合璧的文化色彩。林语堂通过通俗的艺术方法为中国...林语堂的翻译活动前后跨越了半个世纪,历经了中国"五四"新文化运动和美国20世纪50年代"反文化"运动和现代性的冲击。他的译品,就犹如他的创作一样,带有鲜明的中西合璧的文化色彩。林语堂通过通俗的艺术方法为中国古典文化的精华在西方文化世界的传播做出了卓越贡献。由林语堂编译的The Wisdom of Confucius(中文名《孔子的智慧)》较为完整地表达了林语堂的孔子观,也系统地向西方介绍了儒家学说,对促进西方读者了解中国传统文化起到了重要作用。林语堂的翻译思想、The Wisdom of Confucius的编译内容、林语堂《论语》的英译本都具有深刻的学术研究价值。展开更多
Along with the rapid globalization and urbanization,primitive ecological environment and cultural life atmosphere of urban streets and lanes have degraded,memories of the city have been lost,and cities have shown the ...Along with the rapid globalization and urbanization,primitive ecological environment and cultural life atmosphere of urban streets and lanes have degraded,memories of the city have been lost,and cities have shown the tendency of convergence and homogenization.Taking the Confucius Temple Block for example,this paper applied cognitive map,oral interview and GIS spatial statistics to study residents' col ective memories of urban street and lane spaces,and found that the locals' collective memories of streets and lanes in the Confucius Temple Block declined gradually in the sequence of "aura area" → "secondary aura area" → "buffer area" → "blind spot area",and "civilian" urban design concept was claimed as the major incentive of the decline.Streets and lanes as important components of urban public spaces have specific historical connotations and genius loci,and they deserve wide concern from the academic circle and the society for their function of protecting collective memories of residents.展开更多
Following Halliday’s view that "if a text is to be described at all,then it should be described properly;and this means by the theories and methods developed in linguistics"(Halliday,2002),we use the theore...Following Halliday’s view that "if a text is to be described at all,then it should be described properly;and this means by the theories and methods developed in linguistics"(Halliday,2002),we use the theoretical framework and methods developed in Systemic-Functional linguistics to explore "the socio-historical and ideological environment" for the "engendering" (ibid.) of the Analects,the particular contextual features of this great work,the hierarchical structure of Confucius’ main teachings,and also the ways of realizing his ideas in this book by the lexico-grammatical choices.We also discuss the implication and relevance of Confucianism to China and the present world.展开更多
Thurstone’s Comparative Judgment Model was applied to measure characteristics of tourists’after-trip perception of landscape preference in the Confucius Temple,a famous historical block in Nanjing City.The results s...Thurstone’s Comparative Judgment Model was applied to measure characteristics of tourists’after-trip perception of landscape preference in the Confucius Temple,a famous historical block in Nanjing City.The results show that(a)as time goes by,the tourists’time perception differentiation has continuously sublimated from the general experience into the peak experience,and gradually evolved into the core experience element in the overall perception.In terms of content,perceptional contents of tourists decrease in sequence of the Confucian culture,the commercial culture and the culture of refined scholars.As a whole,tourists’after-trip perception differentiation has 3 sections:halo zone,sub-halo zone,and gray zone.(b)Because of tourism development,the Confucian culture is influenced by other cultures,and the commercial culture shows the trend of"over-generalization",and the culture of refined scholars has weakening carriers and modes of inheritance.Inheritance of its unique cultural connotations deserves increasing attention.展开更多
Day by day,biometric-based systems play a vital role in our daily lives.This paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect huma...Day by day,biometric-based systems play a vital role in our daily lives.This paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect human emotions based on voice recognition and control a few electronic peripherals for alert actions.This proposed smart assistant aims to provide a support to the people through buzzer and light emitting diodes(LED)alert signals and it also keep track of the places like households,hospitals and remote areas,etc.The proposed approach is able to detect seven emotions:worry,surprise,neutral,sadness,happiness,hate and love.The key elements for the implementation of speech emotion recognition are voice processing,and once the emotion is recognized,the machine interface automatically detects the actions by buzzer and LED.The proposed system is trained and tested on various benchmark datasets,i.e.,Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS)database,Acoustic-Phonetic Continuous Speech Corpus(TIMIT)database,Emotional Speech database(Emo-DB)database and evaluated based on various parameters,i.e.,accuracy,error rate,and time.While comparing with existing technologies,the proposed algorithm gave a better error rate and less time.Error rate and time is decreased by 19.79%,5.13 s.for the RAVDEES dataset,15.77%,0.01 s for the Emo-DB dataset and 14.88%,3.62 for the TIMIT database.The proposed model shows better accuracy of 81.02%for the RAVDEES dataset,84.23%for the TIMIT dataset and 85.12%for the Emo-DB dataset compared to Gaussian Mixture Modeling(GMM)and Support Vector Machine(SVM)Model.展开更多
Chinese cultural communication in Africa has developed quickly under the framework of the Confucius Institutes. The Confucius Institutes in Africa have opened multilevel Chinese classes and held rich and colorful cult...Chinese cultural communication in Africa has developed quickly under the framework of the Confucius Institutes. The Confucius Institutes in Africa have opened multilevel Chinese classes and held rich and colorful cultural activities. At the moment, however, Chinese cultural communication through the Confucius Institutes in Africa is still confronted with problems, such as the difficult communication environment, lack of local high-level Chinese talents, language and cultural differences, and degree of acceptance. This paper puts forward strategies for Chinese cultural communication: Constructing models with multiple Chinese teaching spots supported by individual Confucius Institutes; strengthening the training of high-level talents for Chinese cultural communications; pushing forward localization of Chinese cultural communications; focusing on the interactivity of language in cultural communications; and establishing a Chinese cultural communication model with multiple subject participation.展开更多
From the perspective of urban memory, the paper made empirical analysis of residents' perception after the trip to the historic and cultural block, by selecting Confucius Temple of Nanjing as the typical case, usi...From the perspective of urban memory, the paper made empirical analysis of residents' perception after the trip to the historic and cultural block, by selecting Confucius Temple of Nanjing as the typical case, using questionnaire survey, mathematical statistics and structural equation model. The results indicated that residents had different perceptions after the trip of different elements of the urban memory and some important influential factors were discussed. Moreover, some implications for local governments and planning department were proposed.展开更多
Speech emotion recognition,as an important component of humancomputer interaction technology,has received increasing attention.Recent studies have treated emotion recognition of speech signals as a multimodal task,due...Speech emotion recognition,as an important component of humancomputer interaction technology,has received increasing attention.Recent studies have treated emotion recognition of speech signals as a multimodal task,due to its inclusion of the semantic features of two different modalities,i.e.,audio and text.However,existing methods often fail in effectively represent features and capture correlations.This paper presents a multi-level circulant cross-modal Transformer(MLCCT)formultimodal speech emotion recognition.The proposed model can be divided into three steps,feature extraction,interaction and fusion.Self-supervised embedding models are introduced for feature extraction,which give a more powerful representation of the original data than those using spectrograms or audio features such as Mel-frequency cepstral coefficients(MFCCs)and low-level descriptors(LLDs).In particular,MLCCT contains two types of feature interaction processes,where a bidirectional Long Short-term Memory(Bi-LSTM)with circulant interaction mechanism is proposed for low-level features,while a two-stream residual cross-modal Transformer block is appliedwhen high-level features are involved.Finally,we choose self-attention blocks for fusion and a fully connected layer to make predictions.To evaluate the performance of our proposed model,comprehensive experiments are conducted on three widely used benchmark datasets including IEMOCAP,MELD and CMU-MOSEI.The competitive results verify the effectiveness of our approach.展开更多
Study on the relationship between landscape beauty and ecological beauty is an important scientifi c problem that refl ects the nature of man-land relation, and current academic researches on this topic are most based...Study on the relationship between landscape beauty and ecological beauty is an important scientifi c problem that refl ects the nature of man-land relation, and current academic researches on this topic are most based on a single perspective. Therefore, this paper took the Confucius Temple–Qinhuai River Scenic Area in Nanjing City as a typical case of urban traditional cultural tourism destination, adopted landscape pattern indexes and balanced incomplete block comparison and evaluation method as the evaluation standards of ecological beauty and landscape beauty, and analyzed the coupling characteristics and rules of landscape pattern and landscape aesthetics. The results showed that(a) The overall landscape of the study area had higher fragmentation degree, but different landscape groups were infl uenced by different human interventions, landscape patches showed moderate diversity and heterogeneity, patch area, spatial distribution and spatial aggregation degree showed structural differences.(b) The locals and visitors had aesthetic perception of the study area, but preferred the beautiful natural scenery of the Qinhuai River, as well as the historical buildings and cultural landscapes that contain rich memories of the city.(c) Landscape pattern and landscape aesthetics showed coupled complementation and harmonious coexistence. The Confucius Temple–Qinhuai River Scenic Area has profound historical and cultural background, but it has witnessed gradual loss of cultural characteristics and fast "delocalization" against the background of rapid urbanization. As an urban traditional cultural tourism destination, it carries the responsibility of protecting city memories and inheriting regional cultures.展开更多
文摘UPON the establishment of European universities in the Middle Ages,the educational system in Western countries became characterized by an essentially Eurocentric worldview.This was reflected in the study of Latin and Greek in high school,and in basing public life and political systems on philosophies of classical antiquity.The work of the influential Chinese philosopher Confucius(551-479 B.C.),a near-contemporary of the major Greek philosophers Socrates(469-399 B.C.),Plato(428-348 B.C.)and Aristotle(384-322 B.C.),whose ethical and political ideas entered into the constitutions of European states,remained unknown.
文摘The exhibition presents the life of Confucius and the essence of his thoughts through plates,accompanied by replicas of related cultural objects and cultural creative products,with the purposeof helping local people understand the origin of Confucianism and presenting the modern charm of traditional culture.
基金2021 China-Sri Lanka Cultural Exchange and Economic Development Research Center Project of Huanggang Normal University:“Research on the Dissemination and Translation of Chinese Classical Poetry in Sri Lanka From the Perspective of‘the Belt and Road’”.The research results of the project were funded by the China-Sri Lanka Cultural Exchange and Economic Development Research Center of Huanggang Normal University(Fund Project No.:202126504).
文摘“The Belt and Road”cooperation initiative contains Chinese excellent traditional cultural ideas,and is deeply rooted in Chinese excellent traditional culture.The proposal of“the Belt and Road”cooperation initiative is not only the strategic need to implement the“going out”of Chinese culture,but also the need to promote cultural exchanges and mutual learning among countries along“the Belt and Road”,and more importantly,the practical consideration of building a community of shared future for mankind with cultural identity.Confucius classroom,as one of the important platforms to realize the“going out”of Chinese culture,shows the“image of China”and enhances the“soft power”of Chinese culture,integrates and configures Chinese teaching and Chinese cultural resources through cooperation,and plays an important role in telling Chinese stories,spreading Chinese voice,enhancing cultural mutual trust and people-to-people contacts as well as the awareness of a community of shared future for mankind.Taking the Confucius classroom jointly built by Huanggang Normal University in China and Sabaragamuwa University in Sri Lanka as an example,this paper explores some effective transmission ways for spreading Chinese excellent traditional culture in Sri Lankan Confucius classroom under the background of“the Belt and Road”cooperation initiative,aiming to give full play to the role of Confucius classroom in cultural exchanges and enhance inter-school exchanges and cooperation between China and Sri Lanka in terms of cultural mutual trust and respect.
基金This is part of the achievement of the 2022 USST College Students’Project“《論語》的英譯與儒家文化對外傳播研究”(No.Serial XJ2022231).
文摘Lun Yu or The Analects,a masterpiece of ancient Chinese thought,contains Chinese Confucianism and the values and ways of doing things that it represents.This paper focuses on the interpretation and translation of“péng(朋)”and“yǒu(友)”in the translations by James Legge,Arthur Waley,Koo Hung-ming,and Xu Yuanchong respectively to explore the similarities and differences between Chinese and Western cultures and the concepts held by different translators in the way of conducting oneself in society.
基金This work is part of the research projects LaTe4PoliticES(PID2022-138099OBI00)funded by MICIU/AEI/10.13039/501100011033the European Regional Development Fund(ERDF)-A Way of Making Europe and LT-SWM(TED2021-131167B-I00)funded by MICIU/AEI/10.13039/501100011033the European Union NextGenerationEU/PRTR.Mr.Ronghao Pan is supported by the Programa Investigo grant,funded by the Region of Murcia,the Spanish Ministry of Labour and Social Economy and the European Union-NextGenerationEU under the“Plan de Recuperación,Transformación y Resiliencia(PRTR).”。
文摘Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.
文摘Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.
文摘Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hatespeech, but they still suffer from ambiguity when differentiating between hateful and offensive content and theyalso lack accuracy. The work suggested in this paper uses a combination of the Whale Optimization Algorithm(WOA) and Particle Swarm Optimization (PSO) to adjust the weights of two Multi-Layer Perceptron (MLPs)for neutrosophic sets classification. During the training process of the MLP, the WOA is employed to exploreand determine the optimal set of weights. The PSO algorithm adjusts the weights to optimize the performanceof the MLP as fine-tuning. Additionally, in this approach, two separate MLP models are employed. One MLPis dedicated to predicting degrees of truth membership, while the other MLP focuses on predicting degrees offalse membership. The difference between these memberships quantifies uncertainty, indicating the degree ofindeterminacy in predictions. The experimental results indicate the superior performance of our model comparedto previous work when evaluated on the Davidson dataset.
文摘Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.
基金This research was funded by Shenzhen Science and Technology Program(Grant No.RCBS20221008093121051)the General Higher Education Project of Guangdong Provincial Education Department(Grant No.2020ZDZX3085)+1 种基金China Postdoctoral Science Foundation(Grant No.2021M703371)the Post-Doctoral Foundation Project of Shenzhen Polytechnic(Grant No.6021330002K).
文摘In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.
文摘The teaching of English speeches in universities aims to enhance oral communication ability,improve English communication skills,and expand English knowledge,occupying a core position in English teaching in universities.This article takes the theory of second language acquisition as the background,analyzes the important role and value of this theory in English speech teaching in universities,and explores how to apply the theory of second language acquisition in English speech teaching in universities.It aims to strengthen the cultivation of English skilled talents and provide a brief reference for improving English speech teaching in universities.
文摘林语堂的翻译活动前后跨越了半个世纪,历经了中国"五四"新文化运动和美国20世纪50年代"反文化"运动和现代性的冲击。他的译品,就犹如他的创作一样,带有鲜明的中西合璧的文化色彩。林语堂通过通俗的艺术方法为中国古典文化的精华在西方文化世界的传播做出了卓越贡献。由林语堂编译的The Wisdom of Confucius(中文名《孔子的智慧)》较为完整地表达了林语堂的孔子观,也系统地向西方介绍了儒家学说,对促进西方读者了解中国传统文化起到了重要作用。林语堂的翻译思想、The Wisdom of Confucius的编译内容、林语堂《论语》的英译本都具有深刻的学术研究价值。
基金Sponsored by Youth Program of National Natural Science Foundation of China(41401152)Humanities and Social Science Youth Program of the Ministry of Education(14YJCZH228)+1 种基金"Qing-Lan"Project of Excellent Young Teachers’Training Program of Jiangsu Provincial Colleges and UniversitiesScientific Research Fund for the Fifth Session of Jiangsu Provincial"333"Project(Level 3)
文摘Along with the rapid globalization and urbanization,primitive ecological environment and cultural life atmosphere of urban streets and lanes have degraded,memories of the city have been lost,and cities have shown the tendency of convergence and homogenization.Taking the Confucius Temple Block for example,this paper applied cognitive map,oral interview and GIS spatial statistics to study residents' col ective memories of urban street and lane spaces,and found that the locals' collective memories of streets and lanes in the Confucius Temple Block declined gradually in the sequence of "aura area" → "secondary aura area" → "buffer area" → "blind spot area",and "civilian" urban design concept was claimed as the major incentive of the decline.Streets and lanes as important components of urban public spaces have specific historical connotations and genius loci,and they deserve wide concern from the academic circle and the society for their function of protecting collective memories of residents.
文摘Following Halliday’s view that "if a text is to be described at all,then it should be described properly;and this means by the theories and methods developed in linguistics"(Halliday,2002),we use the theoretical framework and methods developed in Systemic-Functional linguistics to explore "the socio-historical and ideological environment" for the "engendering" (ibid.) of the Analects,the particular contextual features of this great work,the hierarchical structure of Confucius’ main teachings,and also the ways of realizing his ideas in this book by the lexico-grammatical choices.We also discuss the implication and relevance of Confucianism to China and the present world.
基金Sponsored by National Natural Science Foundation(41271149)Colleges and Universities Philosophy,Social Sciences Foundation of Jiangxi Provincial Department of Education(2012SJB790028)2013 Key Program of Nanjing Institute of Industry Technology(YK13-05-03)
文摘Thurstone’s Comparative Judgment Model was applied to measure characteristics of tourists’after-trip perception of landscape preference in the Confucius Temple,a famous historical block in Nanjing City.The results show that(a)as time goes by,the tourists’time perception differentiation has continuously sublimated from the general experience into the peak experience,and gradually evolved into the core experience element in the overall perception.In terms of content,perceptional contents of tourists decrease in sequence of the Confucian culture,the commercial culture and the culture of refined scholars.As a whole,tourists’after-trip perception differentiation has 3 sections:halo zone,sub-halo zone,and gray zone.(b)Because of tourism development,the Confucian culture is influenced by other cultures,and the commercial culture shows the trend of"over-generalization",and the culture of refined scholars has weakening carriers and modes of inheritance.Inheritance of its unique cultural connotations deserves increasing attention.
基金Deanship of Scientific Research at Majmaah University for supporting this work under Project No.R-2022-166.
文摘Day by day,biometric-based systems play a vital role in our daily lives.This paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect human emotions based on voice recognition and control a few electronic peripherals for alert actions.This proposed smart assistant aims to provide a support to the people through buzzer and light emitting diodes(LED)alert signals and it also keep track of the places like households,hospitals and remote areas,etc.The proposed approach is able to detect seven emotions:worry,surprise,neutral,sadness,happiness,hate and love.The key elements for the implementation of speech emotion recognition are voice processing,and once the emotion is recognized,the machine interface automatically detects the actions by buzzer and LED.The proposed system is trained and tested on various benchmark datasets,i.e.,Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS)database,Acoustic-Phonetic Continuous Speech Corpus(TIMIT)database,Emotional Speech database(Emo-DB)database and evaluated based on various parameters,i.e.,accuracy,error rate,and time.While comparing with existing technologies,the proposed algorithm gave a better error rate and less time.Error rate and time is decreased by 19.79%,5.13 s.for the RAVDEES dataset,15.77%,0.01 s for the Emo-DB dataset and 14.88%,3.62 for the TIMIT database.The proposed model shows better accuracy of 81.02%for the RAVDEES dataset,84.23%for the TIMIT dataset and 85.12%for the Emo-DB dataset compared to Gaussian Mixture Modeling(GMM)and Support Vector Machine(SVM)Model.
文摘Chinese cultural communication in Africa has developed quickly under the framework of the Confucius Institutes. The Confucius Institutes in Africa have opened multilevel Chinese classes and held rich and colorful cultural activities. At the moment, however, Chinese cultural communication through the Confucius Institutes in Africa is still confronted with problems, such as the difficult communication environment, lack of local high-level Chinese talents, language and cultural differences, and degree of acceptance. This paper puts forward strategies for Chinese cultural communication: Constructing models with multiple Chinese teaching spots supported by individual Confucius Institutes; strengthening the training of high-level talents for Chinese cultural communications; pushing forward localization of Chinese cultural communications; focusing on the interactivity of language in cultural communications; and establishing a Chinese cultural communication model with multiple subject participation.
基金Sponsored by National Natural Science Foundation of China(41401152)Youth Funds of Humanities and Social Sciences Research of the Ministry of Education(14YJCZH228)+1 种基金Domestic Senior Visiting Scholar Foundation of Jiangsu Provincial Higher Vocational Colleges(2015FX036)Key Project of Humanities and Social Sciences Foundation of Nanjing Institute of Industry Technology(YK13-05-03)
文摘From the perspective of urban memory, the paper made empirical analysis of residents' perception after the trip to the historic and cultural block, by selecting Confucius Temple of Nanjing as the typical case, using questionnaire survey, mathematical statistics and structural equation model. The results indicated that residents had different perceptions after the trip of different elements of the urban memory and some important influential factors were discussed. Moreover, some implications for local governments and planning department were proposed.
基金the National Natural Science Foundation of China(No.61872231)the National Key Research and Development Program of China(No.2021YFC2801000)the Major Research plan of the National Social Science Foundation of China(No.2000&ZD130).
文摘Speech emotion recognition,as an important component of humancomputer interaction technology,has received increasing attention.Recent studies have treated emotion recognition of speech signals as a multimodal task,due to its inclusion of the semantic features of two different modalities,i.e.,audio and text.However,existing methods often fail in effectively represent features and capture correlations.This paper presents a multi-level circulant cross-modal Transformer(MLCCT)formultimodal speech emotion recognition.The proposed model can be divided into three steps,feature extraction,interaction and fusion.Self-supervised embedding models are introduced for feature extraction,which give a more powerful representation of the original data than those using spectrograms or audio features such as Mel-frequency cepstral coefficients(MFCCs)and low-level descriptors(LLDs).In particular,MLCCT contains two types of feature interaction processes,where a bidirectional Long Short-term Memory(Bi-LSTM)with circulant interaction mechanism is proposed for low-level features,while a two-stream residual cross-modal Transformer block is appliedwhen high-level features are involved.Finally,we choose self-attention blocks for fusion and a fully connected layer to make predictions.To evaluate the performance of our proposed model,comprehensive experiments are conducted on three widely used benchmark datasets including IEMOCAP,MELD and CMU-MOSEI.The competitive results verify the effectiveness of our approach.
基金Sponsored by Youth Program of National Natural Science Foundation of China(41401152)Youth Program of Humanities and Social Sciences Foundation of the Ministry of Education(14YJCZH228)+1 种基金Domestic Senior Visiting Scholar Plan of Jiangsu Provincial Higher Vocational Colleges(2015FX036)Outstanding Young Teacher Cultivation Program of Jiangsu Universities and Colleges"Blue Project"
文摘Study on the relationship between landscape beauty and ecological beauty is an important scientifi c problem that refl ects the nature of man-land relation, and current academic researches on this topic are most based on a single perspective. Therefore, this paper took the Confucius Temple–Qinhuai River Scenic Area in Nanjing City as a typical case of urban traditional cultural tourism destination, adopted landscape pattern indexes and balanced incomplete block comparison and evaluation method as the evaluation standards of ecological beauty and landscape beauty, and analyzed the coupling characteristics and rules of landscape pattern and landscape aesthetics. The results showed that(a) The overall landscape of the study area had higher fragmentation degree, but different landscape groups were infl uenced by different human interventions, landscape patches showed moderate diversity and heterogeneity, patch area, spatial distribution and spatial aggregation degree showed structural differences.(b) The locals and visitors had aesthetic perception of the study area, but preferred the beautiful natural scenery of the Qinhuai River, as well as the historical buildings and cultural landscapes that contain rich memories of the city.(c) Landscape pattern and landscape aesthetics showed coupled complementation and harmonious coexistence. The Confucius Temple–Qinhuai River Scenic Area has profound historical and cultural background, but it has witnessed gradual loss of cultural characteristics and fast "delocalization" against the background of rapid urbanization. As an urban traditional cultural tourism destination, it carries the responsibility of protecting city memories and inheriting regional cultures.