{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T11:29:25Z","timestamp":1762514965618,"version":"build-2065373602"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s13042-025-02542-y","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T05:12:39Z","timestamp":1743743559000},"page":"8603-8616","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based efficient audio production separation method"],"prefix":"10.1007","volume":"16","author":[{"given":"Wenzhu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Byung-Gyu","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,2]]},"reference":[{"key":"2542_CR1","doi-asserted-by":"publisher","first-page":"8129","DOI":"10.1007\/s11042-023-15891-z","volume":"83","author":"A Prashanth","year":"2024","unstructured":"Prashanth A, Jayalakshmi SL, Vedhapriyavadhana R (2024) A review of deep learning techniques in audio event recognition (AER) applications. Multimed Tools Appl 83:8129\u20138143","journal-title":"Multimed Tools Appl"},{"key":"2542_CR2","doi-asserted-by":"crossref","unstructured":"Reghunath L, Rajan R (2023) Predominant audio source separation in polyphonic music. Audio Speech Music Proc. 49 (2023)","DOI":"10.1186\/s13636-023-00316-4"},{"key":"2542_CR3","doi-asserted-by":"crossref","unstructured":"Ostermann F, Vatolkin I, Ebeling M (2023) AAM: a dataset of Artificial Audio Multitracks for diverse music information retrieval tasks. Audio Speech Music Proc. 13 (2023)","DOI":"10.1186\/s13636-023-00278-7"},{"key":"2542_CR4","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/s10772-023-10045-w","volume":"26","author":"J Agrawal","year":"2023","unstructured":"Agrawal J, Gupta M, Garg H (2023) Monaural speech separation using WT-Conv-TasNet for hearing aids. Int J Speech Technol 26:707\u2013720","journal-title":"Int J Speech Technol"},{"key":"2542_CR5","doi-asserted-by":"publisher","first-page":"15919","DOI":"10.1007\/s11042-022-12421-1","volume":"81","author":"R Abdelmalek","year":"2022","unstructured":"Abdelmalek R, Mnasri Z, Benzarti F (2022) Audio signal reconstruction using phase retrieval: implementation and evaluation. Multimed Tools Appl 81:15919\u201315946","journal-title":"Multimed Tools Appl"},{"key":"2542_CR6","doi-asserted-by":"crossref","unstructured":"Cobos M, Ahrens J, Kowalczyk K et al (2022) An overview of machine learning and other data-based methods for spatial audio capture, processing, and reproduction. J Audio Speech Music Proc. 10 (2022)","DOI":"10.1186\/s13636-022-00242-x"},{"key":"2542_CR7","doi-asserted-by":"publisher","first-page":"4174","DOI":"10.1007\/s00034-022-01979-8","volume":"41","author":"JPL Escola","year":"2022","unstructured":"Escola JPL, de Souza UB, Guido RC et al (2022) The Haar Wavelet transform in IoT Digital Audio Signal Processing. Circuits Syst Signal Process 41:4174\u20134184","journal-title":"Circuits Syst Signal Process"},{"key":"2542_CR8","doi-asserted-by":"publisher","first-page":"360","DOI":"10.26599\/TST.2022.9010007","volume":"28","author":"R Zeng","year":"2023","unstructured":"Zeng R (2023) CNN-Based broad learning for cross-domain emotion classification. Tsinghua Sci Technol 28:360\u2013369","journal-title":"Tsinghua Sci Technol"},{"key":"2542_CR9","doi-asserted-by":"publisher","first-page":"258","DOI":"10.26599\/TST.2021.9010099","volume":"28","author":"P Wang","year":"2023","unstructured":"Wang P, Wang SA, Fairness-Enhanced Intelligent (2023) MAC Scheme using Q-Learning-based bidirectional backoff for distributed Vehicular Communication Networks. Tsinghua Sci Technol 28:258\u2013268","journal-title":"Tsinghua Sci Technol"},{"key":"2542_CR10","doi-asserted-by":"publisher","first-page":"27044","DOI":"10.1007\/s10489-023-04973-y","volume":"53","author":"K Presannakumar","year":"2023","unstructured":"Presannakumar K, Mohamed A (2023) Source identification of weak audio signals using attention based convolutional neural network. Appl Intell 53:27044\u201327059","journal-title":"Appl Intell"},{"key":"2542_CR11","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.26599\/TST.2023.9010076","volume":"29","author":"F Wang","year":"2024","unstructured":"Wang F, He Q, Li S (2024) Solving Combinatorial optimization problems with deep neural network: a Survey. Tsinghua Sci Technol 29:1266\u20131282","journal-title":"Tsinghua Sci Technol"},{"issue":"Suppl 3","key":"2542_CR12","doi-asserted-by":"publisher","first-page":"3651","DOI":"10.1007\/s10462-023-10612-2","volume":"56","author":"P Ochieng","year":"2023","unstructured":"Ochieng P (2023) Deep neural network techniques for monaural speech enhancement and separation: state of the art analysis. Artif Intell Rev 56(Suppl 3):3651\u20133703","journal-title":"Artif Intell Rev"},{"key":"2542_CR13","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1007\/s00034-022-02178-1","volume":"42","author":"S Joseph","year":"2023","unstructured":"Joseph S, Rajan R, Cycle (2023) GAN-Based Audio source separation using time\u2013frequency masking. Circuits Syst Signal Process 42:1163\u20131180","journal-title":"Circuits Syst Signal Process"},{"key":"2542_CR14","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1007\/s12555-022-0616-4","volume":"22","author":"Z Wang","year":"2024","unstructured":"Wang Z, Zou W, Zhang W et al (2024) Auditory feature Driven Model Predictive Control for Sound Source Approaching. Int J Control Autom Syst 22:676\u2013689","journal-title":"Int J Control Autom Syst"},{"key":"2542_CR15","doi-asserted-by":"crossref","unstructured":"Grinstein E, Neo VW, Naylor PA (2023) Dual input neural networks for positional sound source localization. J Audio Speech Music Proc. 32 (2023)","DOI":"10.1186\/s13636-023-00301-x"},{"key":"2542_CR16","doi-asserted-by":"crossref","unstructured":"Cobos M, Ahrens J, Kowalczyk K et al (2022) Data-based spatial audio processing. Audio Speech Music Proc. 13 (2022)","DOI":"10.1186\/s13636-022-00248-5"},{"key":"2542_CR17","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1140\/epjst\/e2019-900046-x","volume":"228","author":"K Smagulova","year":"2019","unstructured":"Smagulova K, James AP (2019) A survey on LSTM memristive neural network architectures and applications. Eur Phys J Spec Top 228:2313\u20132324","journal-title":"Eur Phys J Spec Top"},{"key":"2542_CR18","doi-asserted-by":"publisher","first-page":"3425","DOI":"10.1007\/s41870-022-00907-y","volume":"14","author":"R Shashidhar","year":"2022","unstructured":"Shashidhar R, Patilkulkarni S, Puneeth SB (2022) Combining audio and visual speech recognition using LSTM and deep convolutional neural network. Int j inf Tecnol 14:3425\u20133436","journal-title":"Int j inf Tecnol"},{"key":"2542_CR19","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1007\/s11265-022-01770-7","volume":"94","author":"R Liu","year":"2022","unstructured":"Liu R, Zhou Y, Liu H et al (2022) A new neural beamformer for multi-channel Speech separation. J Sign Process Syst 94:977\u2013987","journal-title":"J Sign Process Syst"},{"key":"2542_CR20","doi-asserted-by":"crossref","unstructured":"Luo Y (2021) Spherical harmonic covariance and magnitude function encodings for beamformer design. J Audio Speech Music Proc. 41 (2021)","DOI":"10.1186\/s13636-021-00230-7"},{"key":"2542_CR21","doi-asserted-by":"crossref","unstructured":"Ali R, van Waterschoot T, Moonen M (2021) An integrated MVDR beamformer for speech enhancement using a local microphone array and external microphones. Audio Speech Music Proc. 10 (2021)","DOI":"10.1186\/s13636-020-00192-2"},{"key":"2542_CR22","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1007\/s00034-023-02530-z","volume":"43","author":"Z Saric","year":"2024","unstructured":"Saric Z, Subotic M, Bilibajkic R et al (2024) Mask-based Beamforming Applied to the end-fire microphone array. Circuits Syst Signal Process 43:1661\u20131696","journal-title":"Circuits Syst Signal Process"},{"key":"2542_CR23","doi-asserted-by":"crossref","unstructured":"Sadeghi ME, Sheikhzadeh H, Emadi MJ (2022) Speech improvement in noisy reverberant environments using virtual microphones along with proposed array geometry. EURASIP J. Adv. Signal Process. 120 (2022)","DOI":"10.1186\/s13634-022-00951-7"},{"key":"2542_CR24","doi-asserted-by":"crossref","unstructured":"Luo Y, Mesgarani N (2018) Tasnet: time-domain audio separation network for real-time, single-channel speech separation. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 696\u2013700","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"2542_CR25","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1109\/TASLP.2019.2925450","volume":"27","author":"N Makishima","year":"2019","unstructured":"Makishima N, Mogami S, Takamune N, Kitamura D, Sumino H, Takamichi S (2019) Ono, N. Independent deeply learned matrix analysis for determined audio source separation. IEEE\/ACM Trans Audio Speech Lang Process 27:1601\u20131615","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"2542_CR26","first-page":"1","volume":"12","author":"S Das","year":"2020","unstructured":"Das S, Kolya AK (2020) Detecting generic music features with single layer feedforward network using unsupervised hebbian computation. Int J Artif Intell 12:1\u201320","journal-title":"Int J Artif Intell"},{"key":"2542_CR27","doi-asserted-by":"crossref","unstructured":"Fevotte C, Vincent E, Ozerov A (2018) Single-channel audio source separation with NMF: divergences, constraints and algorithms. In: Audio Source Sep, 1\u201324","DOI":"10.1007\/978-3-319-73031-8_1"},{"key":"2542_CR28","doi-asserted-by":"publisher","first-page":"2154","DOI":"10.21105\/joss.02154","volume":"5","author":"R Hennequin","year":"2020","unstructured":"Hennequin R, Khlif A, Voituret F, Moussallam M (2020) Spleeter: a fast and efficient music source separation tool with pre-trained models. J Open Source Softw 5:2154","journal-title":"J Open Source Softw"},{"key":"2542_CR29","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11868-022-00465-8","volume":"13","author":"S Ghobber","year":"2022","unstructured":"Ghobber S, Mejjaoli H (2022) Time-frequency concentration and localization operators associated with the directional short-time fourier transform. J Pseudo-Differ Oper Appl 13:33","journal-title":"J Pseudo-Differ Oper Appl"},{"key":"2542_CR30","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1007\/s00041-022-09977-9","volume":"28","author":"M Speckbacher","year":"2022","unstructured":"Speckbacher M (2022) Sampling trajectories for the short-time Fourier Transform. J Fourier Anal Appl 28:82","journal-title":"J Fourier Anal Appl"},{"key":"2542_CR31","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11868-021-00432-9","volume":"13","author":"S Ghobber","year":"2022","unstructured":"Ghobber S, Omri S, Oueslati O (2022) Logvinenko-Sereda type theorems for the short time Fourier transform. J Pseudo-Differ Oper Appl 13:2","journal-title":"J Pseudo-Differ Oper Appl"},{"key":"2542_CR32","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1515\/fca-2021-0029","volume":"24","author":"R Kamalakkannan","year":"2021","unstructured":"Kamalakkannan R, Roopkumar R, Zayed A (2021) Short time coupled fractional fourier transform and the uncertainty principle. Fract Calc Appl Anal 24:667\u2013688","journal-title":"Fract Calc Appl Anal"},{"key":"2542_CR33","doi-asserted-by":"publisher","first-page":"16395","DOI":"10.1007\/s11042-022-14192-1","volume":"82","author":"S Mirzaei","year":"2023","unstructured":"Mirzaei S, Jazani IK (2023) Acoustic scene classification with multi-temporal complex modulation spectrogram features and a convolutional LSTM network. Multimed Tools Appl 82:16395\u201316408","journal-title":"Multimed Tools Appl"},{"key":"2542_CR34","doi-asserted-by":"publisher","first-page":"16903","DOI":"10.1007\/s12652-023-04706-6","volume":"14","author":"M Dua","year":"2023","unstructured":"Dua M, Akanksha, Dua S (2023) Cepstral and acoustic ternary pattern based hybrid feature extraction approach for end-to-end bangla speech recognition. J Ambient Intell Hum Comput 14:16903\u201316919","journal-title":"J Ambient Intell Hum Comput"},{"key":"2542_CR35","doi-asserted-by":"publisher","first-page":"5313","DOI":"10.1007\/s00034-023-02340-3","volume":"42","author":"S Balasubramanian","year":"2023","unstructured":"Balasubramanian S, Rajavel R, Kar A (2023) Estimation of Ideal Binary Mask for Audio-Visual Monaural Speech Enhancement. Circuits Syst Signal Process 42:5313\u20135337","journal-title":"Circuits Syst Signal Process"},{"key":"2542_CR36","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1007\/s41066-024-00456-8","volume":"9","author":"HH Gul","year":"2024","unstructured":"Gul HH, Egrioglu E, Bas E (2024) A new statistical training algorithm for a single multiplicative neuron model artificial neural network. Granul Comput 9:28","journal-title":"Granul Comput"},{"key":"2542_CR37","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/s11222-023-10320-5","volume":"34","author":"I Ortega-Fernandez","year":"2024","unstructured":"Ortega-Fernandez I, Sestelo M, Villanueva NM (2024) Explainable generalized additive neural networks with independent neural network training. Stat Comput 34:6","journal-title":"Stat Comput"},{"key":"2542_CR38","doi-asserted-by":"publisher","first-page":"6249","DOI":"10.1007\/s11042-023-15747-6","volume":"83","author":"IH Rather","year":"2024","unstructured":"Rather IH, Kumar S (2024) Generative adversarial network based synthetic data training model for lightweight convolutional neural networks. Multimed Tools Appl 83:6249\u20136271","journal-title":"Multimed Tools Appl"},{"key":"2542_CR39","doi-asserted-by":"publisher","first-page":"26101","DOI":"10.1007\/s11042-022-12850-y","volume":"81","author":"N Kaur","year":"2022","unstructured":"Kaur N, Singh P (2022) Speech waveform reconstruction from speech parameters for an effective text to speech synthesis system using minimum phase harmonic sinusoidal model for Punjabi. Multimed Tools Appl 81:26101\u201326120","journal-title":"Multimed Tools Appl"},{"key":"2542_CR40","doi-asserted-by":"publisher","unstructured":"Diel P, Munoz-Montoro AJ, Carabias-Orti JJ, Ranilla J (2024) Efficient FPGA implementation for sound source separation using direction-informed multichannel non-negative matrix factorization. J. Supercomput., early access https:\/\/doi.org\/10.1007\/s11227-024-05945-w","DOI":"10.1007\/s11227-024-05945-w"},{"key":"2542_CR41","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1109\/TASLP.2024.3356980","volume":"32","author":"Y Oezer","year":"2024","unstructured":"Oezer Y, Mueller M (2024) Source separation of piano concertos using musically motivated augmentation techniques. IEEE\/ACM Trans Audio Speech Lang Process 32:1214\u20131225","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"2542_CR42","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TASLP.2023.3252272","volume":"31","author":"K Schulze-Forster","year":"2023","unstructured":"Schulze-Forster K, Richard G, Kelley L, Doire CSJ, Badeau R (2023) Unsupervised music source separation using Differentiable Parametric Source models. IEEE\/ACM Trans Audio Speech Lang Process 31:1276\u20131285","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"2542_CR43","doi-asserted-by":"publisher","first-page":"5864","DOI":"10.1109\/TMM.2022.3200282","volume":"25","author":"YL Ji","year":"2023","unstructured":"Ji YL, Ma S, Xu X et al (2023) Self-supervised fine-grained cycle-separation network (FSCN) for Visual-Audio separation. IEEE Trans Multimedia 25:5864\u20135876","journal-title":"IEEE Trans Multimedia"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02542-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02542-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02542-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T11:23:24Z","timestamp":1762514604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02542-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,2]]},"references-count":43,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["2542"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02542-y","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2025,4,2]]},"assertion":[{"value":"1 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This declaration is \u201cnot applicable\u201d.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}