The end-to-end separation algorithm with superior performance in the field of speech separation has not been effectively used in music separation.Moreover,since music signals are often dual channel data with a high sa...The end-to-end separation algorithm with superior performance in the field of speech separation has not been effectively used in music separation.Moreover,since music signals are often dual channel data with a high sampling rate,how to model longsequence data and make rational use of the relevant information between channels is also an urgent problem to be solved.In order to solve the above problems,the performance of the end-to-end music separation algorithm is enhanced by improving the network structure.Our main contributions include the following:(1)A more reasonable densely connected U-Net is designed to capture the long-term characteristics of music,such as main melody,tone and so on.(2)On this basis,the multi-head attention and dualpath transformer are introduced in the separation module.Channel attention units are applied recursively on the feature map of each layer of the network,enabling the network to perform long-sequence separation.Experimental results show that after the introduction of the channel attention,the performance of the proposed algorithm has a stable improvement compared with the baseline system.On the MUSDB18 dataset,the average score of the separated audio exceeds that of the current best-performing music separation algorithm based on the time-frequency domain(T-F domain).展开更多
For the poor adaptability of the original repeating pattern, an improved music separation method of multi-repeating structure of Mel cepstrum coefficient （MFCC） is proposed. Firstly, the MFCC coefficient matrix （39...For the poor adaptability of the original repeating pattern, an improved music separation method of multi-repeating structure of Mel cepstrum coefficient （MFCC） is proposed. Firstly, the MFCC coefficient matrix （39-dimensional data） of the music signal was extracted. Then the cosine characteristic was applied to the count of similarity matrix of MFCC, and the fragments with consistent similarity are putted together. Next different repeating patterns are built for different groups. Thereby the spectrums of the background music and vocal were separated combined with ideal binary masking （IBM）, and the corresponding time domain signals were obtained by inverse Fourier transform. Fnally, the improved method was tested on the music database of different types and length, and the separation results were compared with repeating method of Rafii and the non-negative matrix factorization based on flexible framework method of Ozerov. The experimental results showed that the separation performance of improved method was improved about 3 dB, and the performance of music with melody changed larger was significantly improved. Experiments verified that the improved method was an effective music separation algorithm and more stability.展开更多
This paper presents experimental results of cocracking of straight-run gasoline (SRG) and light gaS oil (LGO) in an improved pulsed-micro-pyrolyzer. It is shown that there are negative opergistic effect on the yields ...This paper presents experimental results of cocracking of straight-run gasoline (SRG) and light gaS oil (LGO) in an improved pulsed-micro-pyrolyzer. It is shown that there are negative opergistic effect on the yields and selectivities of ethylene and propylene in cocracking. The difference in coking tendencies betWeen the cocracking and the separate cracking is compared as well.展开更多
The move towards international harmonization of accounting standards has dominated the work program of International Accounting Standards Board （IASB） in the past years. This paper aims to verify the compliance of t...The move towards international harmonization of accounting standards has dominated the work program of International Accounting Standards Board （IASB） in the past years. This paper aims to verify the compliance of the comprehensive income （CI） statement format with International Accounting Standard （IAS） 1-presentation of financial statements, which was revised in 2007. The changes introduced by the 2011 revision are also taken into account. For this purpose, this study analyzes the final annual financial statements approved in 2011 by the Italian companies whose shares belonged to the Italia Star segment of Financial Times and Stock Exchange （FTSE）. Given that IAS 1 provides little specific guidance about the presentation of line items and permits many alternative types of format, this paper focuses on information organization in the statement of CI in order to analyze the degree of heterogeneity of financial information. For achieving this goal, this study considers the following issues： （1） presentation of all items of income and expense in an overall statement or in two separate statements; （2） a detailed level of the content in terms of number of items between revenue and net income （NI）; （3） classification of expenses either by nature or by function; （4） number and type of intermediate margins; and （5） presentation of items of other comprehensive income （OCI） either before tax or net of tax. The results show some clear evidences. On the one hand, there is a high diversity in accounting practices, which makes it difficult for users to compare financial information across entities, highlighting the need to complete the joint project of the standards setters （IASB and Financial Accounting Standards Board （FASB）） on financial statement presentation. On the other hand, some alternative types of presentation （e.g., the tendency to split the CI statement into two statements rather than using an integrated solution, the prevalence to disaggregate the expenses by nature, etc.） are used by most of the entities of the sample possibly because of the influence of Italian accounting culture.展开更多
基金National Natural Science Foundation of China,Grant/Award Number:62071039Beijing Natural Science Foundation,Grant/Award Number:L223033。
文摘The end-to-end separation algorithm with superior performance in the field of speech separation has not been effectively used in music separation.Moreover,since music signals are often dual channel data with a high sampling rate,how to model longsequence data and make rational use of the relevant information between channels is also an urgent problem to be solved.In order to solve the above problems,the performance of the end-to-end music separation algorithm is enhanced by improving the network structure.Our main contributions include the following:(1)A more reasonable densely connected U-Net is designed to capture the long-term characteristics of music,such as main melody,tone and so on.(2)On this basis,the multi-head attention and dualpath transformer are introduced in the separation module.Channel attention units are applied recursively on the feature map of each layer of the network,enabling the network to perform long-sequence separation.Experimental results show that after the introduction of the channel attention,the performance of the proposed algorithm has a stable improvement compared with the baseline system.On the MUSDB18 dataset,the average score of the separated audio exceeds that of the current best-performing music separation algorithm based on the time-frequency domain(T-F domain).
基金supported by the National Natural Science Foundation of China(61371164,61275099,61102131)the Project of Key Laboratory of Signal and Information Processing of Chongqing(CSTC2009CA2003)+3 种基金the Chongqing Distinguished Youth Fundation(CSTC2011jjjq40002)the Natural Science Foundation of Chongqing(CSTC2012JJA40008)the Research Project of Chongqing Educational Commission(KJ120525,KJ130524)Graduate Research and Innovation Projects of Chongqing(CYS14140)
文摘For the poor adaptability of the original repeating pattern, an improved music separation method of multi-repeating structure of Mel cepstrum coefficient （MFCC） is proposed. Firstly, the MFCC coefficient matrix （39-dimensional data） of the music signal was extracted. Then the cosine characteristic was applied to the count of similarity matrix of MFCC, and the fragments with consistent similarity are putted together. Next different repeating patterns are built for different groups. Thereby the spectrums of the background music and vocal were separated combined with ideal binary masking （IBM）, and the corresponding time domain signals were obtained by inverse Fourier transform. Fnally, the improved method was tested on the music database of different types and length, and the separation results were compared with repeating method of Rafii and the non-negative matrix factorization based on flexible framework method of Ozerov. The experimental results showed that the separation performance of improved method was improved about 3 dB, and the performance of music with melody changed larger was significantly improved. Experiments verified that the improved method was an effective music separation algorithm and more stability.
文摘This paper presents experimental results of cocracking of straight-run gasoline (SRG) and light gaS oil (LGO) in an improved pulsed-micro-pyrolyzer. It is shown that there are negative opergistic effect on the yields and selectivities of ethylene and propylene in cocracking. The difference in coking tendencies betWeen the cocracking and the separate cracking is compared as well.
文摘The move towards international harmonization of accounting standards has dominated the work program of International Accounting Standards Board （IASB） in the past years. This paper aims to verify the compliance of the comprehensive income （CI） statement format with International Accounting Standard （IAS） 1-presentation of financial statements, which was revised in 2007. The changes introduced by the 2011 revision are also taken into account. For this purpose, this study analyzes the final annual financial statements approved in 2011 by the Italian companies whose shares belonged to the Italia Star segment of Financial Times and Stock Exchange （FTSE）. Given that IAS 1 provides little specific guidance about the presentation of line items and permits many alternative types of format, this paper focuses on information organization in the statement of CI in order to analyze the degree of heterogeneity of financial information. For achieving this goal, this study considers the following issues： （1） presentation of all items of income and expense in an overall statement or in two separate statements; （2） a detailed level of the content in terms of number of items between revenue and net income （NI）; （3） classification of expenses either by nature or by function; （4） number and type of intermediate margins; and （5） presentation of items of other comprehensive income （OCI） either before tax or net of tax. The results show some clear evidences. On the one hand, there is a high diversity in accounting practices, which makes it difficult for users to compare financial information across entities, highlighting the need to complete the joint project of the standards setters （IASB and Financial Accounting Standards Board （FASB）） on financial statement presentation. On the other hand, some alternative types of presentation （e.g., the tendency to split the CI statement into two statements rather than using an integrated solution, the prevalence to disaggregate the expenses by nature, etc.） are used by most of the entities of the sample possibly because of the influence of Italian accounting culture.
