{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:10:05Z","timestamp":1750212605750,"version":"3.41.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2018,4,30]],"date-time":"2018-04-30T00:00:00Z","timestamp":1525046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100007245","name":"MARCO","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007245","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]},{"name":"six SRC STARnet Centers"},{"name":"Systems on Nanoscale Information fabriCs"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1302641"],"award-info":[{"award-number":["CCF-1302641"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2018,4,30]]},"abstract":"<jats:p>Machine learning (ML) has revolutionized a wide range of recognition tasks, ranging from text analysis to speech to vision, most notably in cloud deployments. However, mobile deployment of these ideas involves a very different category of design problems. In this article, we develop a hardware architecture for a sound source separation task, intended for deployment on a mobile phone. We focus on a novel Markov random field (MRF) sound source separation algorithm that uses expectation-maximization and Gibbs sampling to learn MRF parameters on the fly and infer the best separation of sources. The intrinsically iterative algorithm suggests challenges for both speed and power. A real-time streaming FPGA implementation runs at 150MHz with 207KB RAM, achieves a speed-up of 22\u00d7 over a software reference, performs with an SDR of up to 7.021dB with 1.601ms latency, and exhibits excellent perceived audio quality. A 45nm CMOS ASIC virtual prototype simulated at 20MHz shows that this architecture is small (&lt;10 million gates) and consumes only 70mW, which is less than 2% of the power of an ARM Cortex-A9 software version. To the best of our knowledge, this is the first Gibbs sampling inference accelerator designed in conventional FPGA\/ASIC technology that targets a realistic mobile perceptual application.<\/jats:p>","DOI":"10.1145\/3183351","type":"journal-article","created":{"date-parts":[[2018,5,23]],"date-time":"2018-05-23T15:08:42Z","timestamp":1527088122000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Real-Time and Low-Power Streaming Source Separation Using Markov Random Field"],"prefix":"10.1145","volume":"14","author":[{"given":"Glenn G.","family":"Ko","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rob A.","family":"Rutenbar","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,5,22]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.135"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201905)","volume":"4","author":"Birchfield S. T.","unstructured":"S. T. Birchfield and R. Gangishetty . 2005. Acoustic localization by interaural level difference . In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201905) , Vol. 4 . 1109--1112. S. T. Birchfield and R. Gangishetty. 2005. Acoustic localization by interaural level difference. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201905), Vol. 4. 1109--1112."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the E8th IEEE International Conference on Computer Vision (ICCV\u201901)","volume":"1","author":"Boykov Y. Y.","unstructured":"Y. Y. Boykov and M. P. Jolly . 2001. Interactive graph cuts for optimal boundary 8 region segmentation of objects in N-D images . In Proceedings of the E8th IEEE International Conference on Computer Vision (ICCV\u201901) , Vol. 1 . 105--112. Y. Y. Boykov and M. P. Jolly. 2001. Interactive graph cuts for optimal boundary 8 region segmentation of objects in N-D images. In Proceedings of the E8th IEEE International Conference on Computer Vision (ICCV\u201901), Vol. 1. 105--112."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.36"},{"key":"e_1_2_1_6_1","first-page":"48","article-title":"A Matlab simulation of \u201cshoebox\u201d room acoustics for use in research and teaching","volume":"9","author":"Campbell D.","year":"2005","unstructured":"D. Campbell , K. Palomaki , and G. Brown . 2005 . A Matlab simulation of \u201cshoebox\u201d room acoustics for use in research and teaching . Comput. Inf. Syst. 9 , 3 (2005), 48 . D. Campbell, K. Palomaki, and G. Brown. 2005. A Matlab simulation of \u201cshoebox\u201d room acoustics for use in research and teaching. Comput. Inf. Syst. 9, 3 (2005), 48.","journal-title":"Comput. Inf. Syst."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.720250"},{"volume-title":"Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201905)","author":"Charoensak C.","key":"e_1_2_1_8_1","unstructured":"C. Charoensak and F. Sattar . 2005. A single-chip FPGA design for real-time ICA-based blind source separation algorithm . In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201905) . 5822--5825. C. Charoensak and F. Sattar. 2005. A single-chip FPGA design for real-time ICA-based blind source separation algorithm. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201905). 5822--5825."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/17814.17824"},{"volume-title":"Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS\u201915)","author":"Das S.","key":"e_1_2_1_11_1","unstructured":"S. Das , B. U. Pedroni , P. Merolla , J. Arthur , A. S. Cassidy , B. L. Jackson , D. Modha , G. Cauwenberghs , and K. Kreutz-Delgado . 2015. Gibbs sampling with low-power spiking digital neurons . In Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS\u201915) . 2704--2707. S. Das, B. U. Pedroni, P. Merolla, J. Arthur, A. S. Cassidy, B. L. Jackson, D. Modha, G. Cauwenberghs, and K. Kreutz-Delgado. 2015. Gibbs sampling with low-power spiking digital neurons. In Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS\u201915). 2704--2707."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/641675.642111"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2006.02.008"},{"volume-title":"Proceedings of the Linguistic Data Consortium.","author":"Garofolo J. S.","key":"e_1_2_1_16_1","unstructured":"J. S. Garofolo , L. F. Lamel , W. M. Fisher , J. G. Fiscus , D. S. Pallett , N. L. Dahlgren , and V. Zue . 1993. TIMIT acoustic-phonetic continuous speech corpus . In Proceedings of the Linguistic Data Consortium. J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, D. S. Pallett, N. L. Dahlgren, and V. Zue. 1993. TIMIT acoustic-phonetic continuous speech corpus. In Proceedings of the Linguistic Data Consortium."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767596"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465.2468"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2010.2081387"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"volume-title":"LTE for UMTS: Evolution to LTE-Advanced","author":"Holma Harri","key":"e_1_2_1_22_1","unstructured":"Harri Holma and Antti Toskala . 2011. LTE for UMTS: Evolution to LTE-Advanced . John Wiley 8 Sons. Harri Holma and Antti Toskala. 2011. LTE for UMTS: Evolution to LTE-Advanced. John Wiley 8 Sons."},{"volume-title":"Independent Component Analysis","author":"Hyv\u00e4rinen Aapo","key":"e_1_2_1_23_1","unstructured":"Aapo Hyv\u00e4rinen , Juha Karhunen , and Erkki Oja . 2004. Independent Component Analysis . Vol. 46 . John Wiley 8 Sons. Aapo Hyv\u00e4rinen, Juha Karhunen, and Erkki Oja. 2004. Independent Component Analysis. Vol. 46. John Wiley 8 Sons."},{"key":"e_1_2_1_24_1","unstructured":"Telecommunication Standardization Sector ITU. 2003. International telephone connections and circuits\u2014general recommendations on the transmission quality for an entire international telephone connection. ITU-T Recommendation G.114. ITU-T.  Telecommunication Standardization Sector ITU. 2003. International telephone connections and circuits\u2014general recommendations on the transmission quality for an entire international telephone connection. ITU-T Recommendation G.114. ITU-T."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.175"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.818381"},{"volume-title":"Proceedings of the 2012 IEEE International Workshop on Machine Learning for Signal Processing. 1--6.","author":"Kim M.","key":"e_1_2_1_27_1","unstructured":"M. Kim , P. Smaragdis , G. G. Ko , and R. A. Rutenbar . 2012. Stereophonic spectrogram segmentation using Markov random fields . In Proceedings of the 2012 IEEE International Workshop on Machine Learning for Signal Processing. 1--6. M. Kim, P. Smaragdis, G. G. Ko, and R. A. Rutenbar. 2012. Stereophonic spectrogram segmentation using Markov random fields. In Proceedings of the 2012 IEEE International Workshop on Machine Learning for Signal Processing. 1--6."},{"volume-title":"Proceedings of the 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201917)","author":"Ko G. G.","key":"e_1_2_1_28_1","unstructured":"G. G. Ko and R. A. Rutenbar . 2017. A case study of machine learning hardware: Real-time source separation using Markov random fields via sampling-based inference . In Proceedings of the 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201917) . 2477--2481. G. G. Ko and R. A. Rutenbar. 2017. A case study of machine learning hardware: Real-time source separation using Markov random fields via sampling-based inference. In Proceedings of the 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201917). 2477--2481."},{"volume-title":"Probabilistic Graphical Models: Principles and Techniques","author":"Koller Daphne","key":"e_1_2_1_29_1","unstructured":"Daphne Koller and Nir Friedman . 2009. Probabilistic Graphical Models: Principles and Techniques . MIT Press . Daphne Koller and Nir Friedman. 2009. Probabilistic Graphical Models: Principles and Techniques. MIT Press."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.200"},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems","volume":"1","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E. Hinton . 2012. ImageNet classification with deep convolutional neural networks . In Proceedings of the 25th International Conference on Neural Information Processing Systems , Volume 1 (NIPS\u201912). 1097--1105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Volume 1 (NIPS\u201912). 1097--1105."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"volume-title":"Introduction to Monte Carlo Methods","author":"Mackay D. J. C.","key":"e_1_2_1_33_1","unstructured":"D. J. C. Mackay . 1998. Introduction to Monte Carlo Methods . Springer , Dordrecht, Netherlands , 175--204. D. J. C. Mackay. 1998. Introduction to Monte Carlo Methods. Springer, Dordrecht, Netherlands, 175--204."},{"key":"e_1_2_1_34_1","volume-title":"Tenenbaum","author":"Mansinghka Vikash K.","year":"2008","unstructured":"Vikash K. Mansinghka , Eric M. Jonas , and Joshua B . Tenenbaum . 2008 . Stochastic Digital Circuits for Probabilistic Inference. Technical Report MITCSAIL-TR 2069. MIT, Cambridge, MA. Vikash K. Mansinghka, Eric M. Jonas, and Joshua B. Tenenbaum. 2008. Stochastic Digital Circuits for Probabilistic Inference. Technical Report MITCSAIL-TR 2069. MIT, Cambridge, MA."},{"key":"e_1_2_1_35_1","unstructured":"Thomas Minka. 1998. Expectation-Maximization as Lower Bound Maximization. Retrieved from http:\/\/www.cse.psu.edu\/&sim;rtc12\/CSE598G\/papers\/minka98expectationmaximization.pdf.  Thomas Minka. 1998. Expectation-Maximization as Lower Bound Maximization. Retrieved from http:\/\/www.cse.psu.edu\/&sim;rtc12\/CSE598G\/papers\/minka98expectationmaximization.pdf."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1962.5219391"},{"key":"e_1_2_1_37_1","volume-title":"Hinton","author":"Neal Radford M.","year":"1998","unstructured":"Radford M. Neal and Geoffrey E . Hinton . 1998 . A view of the EM algorithm that justifies incremental, sparse, and other variants. In Learning in Graphical Models. Springer , 355--368. Radford M. Neal and Geoffrey E. Hinton. 1998. A view of the EM algorithm that justifies incremental, sparse, and other variants. In Learning in Graphical Models. Springer, 355--368."},{"volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann","author":"Pearl Judea","key":"e_1_2_1_38_1","unstructured":"Judea Pearl . 1988. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann , San Francisco, CA . Judea Pearl. 1988. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco, CA."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1610463"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014573219977"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.915115"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70844"},{"volume-title":"A Hardware Random Number Generator","author":"Tkacik Thomas E.","key":"e_1_2_1_44_1","unstructured":"Thomas E. Tkacik . 2003. A Hardware Random Number Generator . Springer , 450--453. Thomas E. Tkacik. 2003. A Hardware Random Number Generator. Springer, 450--453."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.07.004"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.55"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3183351","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3183351","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3183351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:13Z","timestamp":1750210753000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3183351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,30]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,4,30]]}},"alternative-id":["10.1145\/3183351"],"URL":"https:\/\/doi.org\/10.1145\/3183351","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"type":"print","value":"1550-4832"},{"type":"electronic","value":"1550-4840"}],"subject":[],"published":{"date-parts":[[2018,4,30]]},"assertion":[{"value":"2017-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-01-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-05-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}