To solve the problem of mismatching features in an experimental database, which is a key technique in the field of cross-corpus speech emotion recognition, an auditory attention model based on Chirplet is proposed for...To solve the problem of mismatching features in an experimental database, which is a key technique in the field of cross-corpus speech emotion recognition, an auditory attention model based on Chirplet is proposed for feature extraction.First, in order to extract the spectra features, the auditory attention model is employed for variational emotion features detection. Then, the selective attention mechanism model is proposed to extract the salient gist features which showtheir relation to the expected performance in cross-corpus testing.Furthermore, the Chirplet time-frequency atoms are introduced to the model. By forming a complete atom database, the Chirplet can improve the spectrum feature extraction including the amount of information. Samples from multiple databases have the characteristics of multiple components. Hereby, the Chirplet expands the scale of the feature vector in the timefrequency domain. Experimental results show that, compared to the traditional feature model, the proposed feature extraction approach with the prototypical classifier has significant improvement in cross-corpus speech recognition. In addition, the proposed method has better robustness to the inconsistent sources of the training set and the testing set.展开更多
Because of the excellent performance of Transformer in sequence learning tasks,such as natural language processing,an improved Transformer-like model is proposed that is suitable for speech emotion recognition tasks.T...Because of the excellent performance of Transformer in sequence learning tasks,such as natural language processing,an improved Transformer-like model is proposed that is suitable for speech emotion recognition tasks.To alleviate the prohibitive time consumption and memory footprint caused by softmax inside the multihead attention unit in Transformer,a new linear self-attention algorithm is proposed.The original exponential function is replaced by a Taylor series expansion formula.On the basis of the associative property of matrix products,the time and space complexity of softmax operation regarding the input's length is reduced from O(N2)to O(N),where N is the sequence length.Experimental results on the emotional corpora of two languages show that the proposed linear attention algorithm can achieve similar performance to the original scaled dot product attention,while the training time and memory cost are reduced by half.Furthermore,the improved model obtains more robust performance on speech emotion recognition compared with the original Transformer.展开更多
Persian Passion Play （Ta＇ziya）, the most important Shiite religious ritual, performed by non-professional actors and musicians, is based on the martyrdom of the third Shiite Imam, Husein, and his companions at Karb...Persian Passion Play （Ta＇ziya）, the most important Shiite religious ritual, performed by non-professional actors and musicians, is based on the martyrdom of the third Shiite Imam, Husein, and his companions at Karbala （in 680）. This paper aims to introduce a wide range of sources, both books and articles, on the history, music, actors, and arrangements of ta＇ziya performance in Iran from 1971 onwards. It includes a number of titles of ta＇ziya manuscripts, and the place of performance. The article contains traveler accounts from sixteen century onwards and the translations of ta＇ziya texts in European languages.展开更多
In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language proc...In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language processing. The speaker independently continuous speech recognition experiments and the part-of-speech tagging experiments show that Markov family model has higher performance than hidden Markov model. The precision is enhanced from 94.642% to 96.214% in the part-of-speech tagging experiments, and the work rate is reduced by 11.9% in the speech recognition experiments with respect to HMM baseline system.展开更多
Nowadays, film is essential to our recreational life.Most people always focus on the plots.If we turn our attention to the film scores,we could find that every rhythm is full of your deep feelings.With the research of...Nowadays, film is essential to our recreational life.Most people always focus on the plots.If we turn our attention to the film scores,we could find that every rhythm is full of your deep feelings.With the research of the art of sound, we could see with our eyes, and hear with our heart.展开更多
Musical analysis enables us to study the various elements of a musical work, for example texture, m dynamics, or harmony （including tonality）. Thanks to musical analysis we are able to trace the compos technique, or...Musical analysis enables us to study the various elements of a musical work, for example texture, m dynamics, or harmony （including tonality）. Thanks to musical analysis we are able to trace the compos technique, or assess the artistic value of given work. In addition to traditional, descriptive methods of e it ody, onal music analysis, we can observe in 20th century the development of methods based on science （mathematics, otherwise statistics）. Such methodologies allow us to obtain a strict understanding of the structure of musical pieces Applying mathematical methods for musical analysis seems very reasonable in relation to the output of Frederic Chopin, due to large originality of the elements of musical pieces of this composer. Present paper was written as a result of research related to the applying of numerical method of analysis for exploring the tonal structure of Chopin＇s works. The author＇s research method enables a strict analysis of the chord＇s domination that can be classified under given key （range）--taking into consideration the harmonic functions. By the method of analysis we can get charts that depict whole diatonic vertical music material of the given piece. The main objective of the present study is to describe observations on the high uniqueness in the tonal construction of selected Chopin＇s mazurkas, especially, when compared to the miniatures of other composers of the first half of the 19th century and previously analyzed Chopin＇s pieces： etudes, preludes, and songs.展开更多
Chinese Angelica is sweet and pungent in flavour and warm in property. It has the effect of tonifying blood and activating blood circulation and is frequently applied for such gynecological diseases as irregular menst...Chinese Angelica is sweet and pungent in flavour and warm in property. It has the effect of tonifying blood and activating blood circulation and is frequently applied for such gynecological diseases as irregular menstruation and weak constitution after delivery. Therefore, Chinese Angelica has also the name of 'sacred medicament in gynecology'.展开更多
基金The National Natural Science Foundation of China(No.61273266,61231002,61301219,61375028)the Specialized Research Fund for the Doctoral Program of Higher Education(No.20110092130004)the Natural Science Foundation of Shandong Province(No.ZR2014FQ016)
文摘To solve the problem of mismatching features in an experimental database, which is a key technique in the field of cross-corpus speech emotion recognition, an auditory attention model based on Chirplet is proposed for feature extraction.First, in order to extract the spectra features, the auditory attention model is employed for variational emotion features detection. Then, the selective attention mechanism model is proposed to extract the salient gist features which showtheir relation to the expected performance in cross-corpus testing.Furthermore, the Chirplet time-frequency atoms are introduced to the model. By forming a complete atom database, the Chirplet can improve the spectrum feature extraction including the amount of information. Samples from multiple databases have the characteristics of multiple components. Hereby, the Chirplet expands the scale of the feature vector in the timefrequency domain. Experimental results show that, compared to the traditional feature model, the proposed feature extraction approach with the prototypical classifier has significant improvement in cross-corpus speech recognition. In addition, the proposed method has better robustness to the inconsistent sources of the training set and the testing set.
基金The National Key Research and Development Program of China(No.2020YFC2004002,2020YFC2004003)the National Natural Science Foundation of China(No.61871213,61673108,61571106).
文摘Because of the excellent performance of Transformer in sequence learning tasks,such as natural language processing,an improved Transformer-like model is proposed that is suitable for speech emotion recognition tasks.To alleviate the prohibitive time consumption and memory footprint caused by softmax inside the multihead attention unit in Transformer,a new linear self-attention algorithm is proposed.The original exponential function is replaced by a Taylor series expansion formula.On the basis of the associative property of matrix products,the time and space complexity of softmax operation regarding the input's length is reduced from O(N2)to O(N),where N is the sequence length.Experimental results on the emotional corpora of two languages show that the proposed linear attention algorithm can achieve similar performance to the original scaled dot product attention,while the training time and memory cost are reduced by half.Furthermore,the improved model obtains more robust performance on speech emotion recognition compared with the original Transformer.
文摘Persian Passion Play （Ta＇ziya）, the most important Shiite religious ritual, performed by non-professional actors and musicians, is based on the martyrdom of the third Shiite Imam, Husein, and his companions at Karbala （in 680）. This paper aims to introduce a wide range of sources, both books and articles, on the history, music, actors, and arrangements of ta＇ziya performance in Iran from 1971 onwards. It includes a number of titles of ta＇ziya manuscripts, and the place of performance. The article contains traveler accounts from sixteen century onwards and the translations of ta＇ziya texts in European languages.
基金Project(60763001)supported by the National Natural Science Foundation of ChinaProjects(2009GZS0027,2010GZS0072)supported by the Natural Science Foundation of Jiangxi Province,China
文摘In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language processing. The speaker independently continuous speech recognition experiments and the part-of-speech tagging experiments show that Markov family model has higher performance than hidden Markov model. The precision is enhanced from 94.642% to 96.214% in the part-of-speech tagging experiments, and the work rate is reduced by 11.9% in the speech recognition experiments with respect to HMM baseline system.
文摘Nowadays, film is essential to our recreational life.Most people always focus on the plots.If we turn our attention to the film scores,we could find that every rhythm is full of your deep feelings.With the research of the art of sound, we could see with our eyes, and hear with our heart.
文摘Musical analysis enables us to study the various elements of a musical work, for example texture, m dynamics, or harmony （including tonality）. Thanks to musical analysis we are able to trace the compos technique, or assess the artistic value of given work. In addition to traditional, descriptive methods of e it ody, onal music analysis, we can observe in 20th century the development of methods based on science （mathematics, otherwise statistics）. Such methodologies allow us to obtain a strict understanding of the structure of musical pieces Applying mathematical methods for musical analysis seems very reasonable in relation to the output of Frederic Chopin, due to large originality of the elements of musical pieces of this composer. Present paper was written as a result of research related to the applying of numerical method of analysis for exploring the tonal structure of Chopin＇s works. The author＇s research method enables a strict analysis of the chord＇s domination that can be classified under given key （range）--taking into consideration the harmonic functions. By the method of analysis we can get charts that depict whole diatonic vertical music material of the given piece. The main objective of the present study is to describe observations on the high uniqueness in the tonal construction of selected Chopin＇s mazurkas, especially, when compared to the miniatures of other composers of the first half of the 19th century and previously analyzed Chopin＇s pieces： etudes, preludes, and songs.
文摘Chinese Angelica is sweet and pungent in flavour and warm in property. It has the effect of tonifying blood and activating blood circulation and is frequently applied for such gynecological diseases as irregular menstruation and weak constitution after delivery. Therefore, Chinese Angelica has also the name of 'sacred medicament in gynecology'.
