Junjie Yang , Liu Yang , Yi Guo , Yuan Xie , Shengli Xie
{"title":"利用卷积窄带近似和灵活的正则化器分离欠定音频源","authors":"Junjie Yang , Liu Yang , Yi Guo , Yuan Xie , Shengli Xie","doi":"10.1016/j.apacoust.2025.110874","DOIUrl":null,"url":null,"abstract":"<div><div>Convolutive narrowband approximation (CNA) model is widely utilized in audio source separation, particularly in strongly reverberant scenarios. However, in under-determined audio source separation, the CNA model often faces a serious ill-conditioned inverse filtering problem due to its mixing matrices containing columns that approach zero. To mitigate this issue, a <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mi>p</mi></mrow></msub></math></span> regularizer-based approach is proposed in this paper, assuming mixing filters of CNA model are known or pre-estimated. First, the STFT mixture components of all frames at each frequency bin are concatenated into a long vector, and the CNA system is accordingly expanded to a block-circulant structured linear mixing model. Next, a maximum likelihood estimation, constrained by the proposed mixing model, is introduced to exploit the sparsity of STFT source components with the <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mi>p</mi></mrow></msub></math></span> regularizer, where these components are assumed to independently follow super-Gaussian distributions. Finally, an augmented Lagrange multiplier with efficient iterative strategy is developed to search for the suitable sparse solution. The proposed strategy with regularizer <em>p</em> can be flexibly selected in a range of <span><math><mo>(</mo><mn>0</mn><mo>,</mo><mn>1</mn><mo>]</mo></math></span> to achieve robustness and accuracy in performance. Experimental results in various under-determined cases demonstrate the superior performance of the proposed algorithm over state-of-the-art approaches.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"240 ","pages":"Article 110874"},"PeriodicalIF":3.4000,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Under-determined audio source separation using the convolutive narrowband approximation and flexible ℓp regularizer\",\"authors\":\"Junjie Yang , Liu Yang , Yi Guo , Yuan Xie , Shengli Xie\",\"doi\":\"10.1016/j.apacoust.2025.110874\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Convolutive narrowband approximation (CNA) model is widely utilized in audio source separation, particularly in strongly reverberant scenarios. However, in under-determined audio source separation, the CNA model often faces a serious ill-conditioned inverse filtering problem due to its mixing matrices containing columns that approach zero. To mitigate this issue, a <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mi>p</mi></mrow></msub></math></span> regularizer-based approach is proposed in this paper, assuming mixing filters of CNA model are known or pre-estimated. First, the STFT mixture components of all frames at each frequency bin are concatenated into a long vector, and the CNA system is accordingly expanded to a block-circulant structured linear mixing model. Next, a maximum likelihood estimation, constrained by the proposed mixing model, is introduced to exploit the sparsity of STFT source components with the <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mi>p</mi></mrow></msub></math></span> regularizer, where these components are assumed to independently follow super-Gaussian distributions. Finally, an augmented Lagrange multiplier with efficient iterative strategy is developed to search for the suitable sparse solution. The proposed strategy with regularizer <em>p</em> can be flexibly selected in a range of <span><math><mo>(</mo><mn>0</mn><mo>,</mo><mn>1</mn><mo>]</mo></math></span> to achieve robustness and accuracy in performance. Experimental results in various under-determined cases demonstrate the superior performance of the proposed algorithm over state-of-the-art approaches.</div></div>\",\"PeriodicalId\":55506,\"journal\":{\"name\":\"Applied Acoustics\",\"volume\":\"240 \",\"pages\":\"Article 110874\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-06-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Applied Acoustics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0003682X25003469\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ACOUSTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Acoustics","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0003682X25003469","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ACOUSTICS","Score":null,"Total":0}
Under-determined audio source separation using the convolutive narrowband approximation and flexible ℓp regularizer
Convolutive narrowband approximation (CNA) model is widely utilized in audio source separation, particularly in strongly reverberant scenarios. However, in under-determined audio source separation, the CNA model often faces a serious ill-conditioned inverse filtering problem due to its mixing matrices containing columns that approach zero. To mitigate this issue, a regularizer-based approach is proposed in this paper, assuming mixing filters of CNA model are known or pre-estimated. First, the STFT mixture components of all frames at each frequency bin are concatenated into a long vector, and the CNA system is accordingly expanded to a block-circulant structured linear mixing model. Next, a maximum likelihood estimation, constrained by the proposed mixing model, is introduced to exploit the sparsity of STFT source components with the regularizer, where these components are assumed to independently follow super-Gaussian distributions. Finally, an augmented Lagrange multiplier with efficient iterative strategy is developed to search for the suitable sparse solution. The proposed strategy with regularizer p can be flexibly selected in a range of to achieve robustness and accuracy in performance. Experimental results in various under-determined cases demonstrate the superior performance of the proposed algorithm over state-of-the-art approaches.
期刊介绍:
Since its launch in 1968, Applied Acoustics has been publishing high quality research papers providing state-of-the-art coverage of research findings for engineers and scientists involved in applications of acoustics in the widest sense.
Applied Acoustics looks not only at recent developments in the understanding of acoustics but also at ways of exploiting that understanding. The Journal aims to encourage the exchange of practical experience through publication and in so doing creates a fund of technological information that can be used for solving related problems. The presentation of information in graphical or tabular form is especially encouraged. If a report of a mathematical development is a necessary part of a paper it is important to ensure that it is there only as an integral part of a practical solution to a problem and is supported by data. Applied Acoustics encourages the exchange of practical experience in the following ways: • Complete Papers • Short Technical Notes • Review Articles; and thereby provides a wealth of technological information that can be used to solve related problems.
Manuscripts that address all fields of applications of acoustics ranging from medicine and NDT to the environment and buildings are welcome.