Publications

3,804 major publications by members of the MERL staff.


  •  Zhang, J., Cherian, A., Liu, Y., Shabat, I.B., Rodriguez, C., Gould, S., "Aligning Step-by-Step Instructional Diagrams to Video Demonstrations", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), May 2023, pp. 2483-2492.
    BibTeX TR2023-034 PDF
    • @inproceedings{Zhang2023may,
    • author = {Zhang, Jiahao and Cherian, Anoop and Liu, Yanbin and Shabat, Itzik Ben and Rodriguez, Cristian and Gould, Stephen},
    • title = {{Aligning Step-by-Step Instructional Diagrams to Video Demonstrations}},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2023,
    • pages = {2483--2492},
    • month = may,
    • publisher = {CVF},
    • url = {https://www.merl.com/publications/TR2023-034}
    • }
  •  Chen, K., Wichern, G., Germain, F., Le Roux, J., "Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT", IEEE ICASSP Satellite Workshop on Self-supervision in Audio, Speech and Beyond (SASB), DOI: 10.1109/​ICASSPW59220.2023.10193575, May 2023.
    BibTeX TR2023-030 PDF
    • @inproceedings{Chen2023may,
    • author = {Chen, Ke and Wichern, Gordon and Germain, Francois and {Le Roux}, Jonathan},
    • title = {{Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT}},
    • booktitle = {IEEE ICASSP Satellite Workshop on Self-supervision in Audio, Speech and Beyond (SASB)},
    • year = 2023,
    • month = may,
    • doi = {10.1109/ICASSPW59220.2023.10193575},
    • isbn = {979-8-3503-0261-5},
    • url = {https://www.merl.com/publications/TR2023-030}
    • }
  •  Aralikatti, R., Boeddeker, C., Wichern, G., Subramanian, A.S., Le Roux, J., "Reverberation as Supervision for Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095022, May 2023, pp. 1-5.
    BibTeX TR2023-016 PDF
    • @inproceedings{Aralikatti2023may,
    • author = {Aralikatti, Rohith and Boeddeker, Christoph and Wichern, Gordon and Subramanian, Aswin Shanmugam and {Le Roux}, Jonathan},
    • title = {{Reverberation as Supervision for Speech Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095022},
    • url = {https://www.merl.com/publications/TR2023-016}
    • }
  •  Berk, A., Ma, Y., Boufounos, P.T., Wang, P., Mansour, H., "Deep Proximal Gradient Method for Learned Convex Regularizers", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10094632, May 2023, pp. 1-5.
    BibTeX TR2023-032 PDF Video
    • @inproceedings{Berk2023may,
    • author = {Berk, Aaron and Ma, Yanting and Boufounos, Petros T. and Wang, Pu and Mansour, Hassan},
    • title = {{Deep Proximal Gradient Method for Learned Convex Regularizers}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10094632},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-032}
    • }
  •  Bralios, D., Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Latent Iterative Refinement for Modular Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096897, May 2023, pp. 1-5.
    BibTeX TR2023-019 PDF
    • @inproceedings{Bralios2023may,
    • author = {Bralios, Dimitrios and Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and {Le Roux}, Jonathan},
    • title = {{Latent Iterative Refinement for Modular Source Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096897},
    • url = {https://www.merl.com/publications/TR2023-019}
    • }
  •  Fujihashi, T., Koike-Akino, T., Watanabe, T., "Soft 2D-to-3D Delivery Using Deep Graph Neural Networks for Holographic-Type Communication", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095882, May 2023.
    BibTeX TR2023-031 PDF
    • @inproceedings{Fujihashi2023may,
    • author = {Fujihashi, Takuya and Koike-Akino, Toshiaki and Watanabe, Takashi},
    • title = {{Soft 2D-to-3D Delivery Using Deep Graph Neural Networks for Holographic-Type Communication}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095882},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-031}
    • }
  •  Jeon, E.S., Lohit, S., Anirudh, R., Turaga, P., "Robust Time Series Recovery and Classification Using Test-time Noise Simulator Networks", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096888, May 2023.
    BibTeX TR2023-021 PDF Presentation
    • @inproceedings{Jeon2023may,
    • author = {Jeon, Eun Som and Lohit, Suhas and Anirudh, Rushil and Turaga, Pavan},
    • title = {{Robust Time Series Recovery and Classification Using Test-time Noise Simulator Networks}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096888},
    • url = {https://www.merl.com/publications/TR2023-021}
    • }
  •  Jin, S., Wang, P., Boufounos, P.T., Takahashi, R., Roy, S., "Spatial-Domain Object Detection Under MIMO-FMCW Automotive Radar Interference", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095409, May 2023, pp. 1-5.
    BibTeX TR2023-027 PDF
    • @inproceedings{Jin2023may,
    • author = {Jin, Sian and Wang, Pu and Boufounos, Petros T. and Takahashi, Ryuhei and Roy, Sumit},
    • title = {{Spatial-Domain Object Detection Under MIMO-FMCW Automotive Radar Interference}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095409},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-027}
    • }
  •  Kelkar, V.A., Liu, D., Inoue, H., Kanemaru, M., "Sparsity-driven Joint Blind Deconvolution-demodulation with Application to Motor Fault Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10094590, May 2023.
    BibTeX TR2023-026 PDF
    • @inproceedings{Kelkar2023may,
    • author = {Kelkar, Varun A. and Liu, Dehong and Inoue, Hiroshi and Kanemaru, Makoto},
    • title = {{Sparsity-driven Joint Blind Deconvolution-demodulation with Application to Motor Fault Detection}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • month = may,
    • doi = {10.1109/ICASSP49357.2023.10094590},
    • isbn = {978-1-7281-6328-4},
    • url = {https://www.merl.com/publications/TR2023-026}
    • }
  •  Petermann, D., Wichern, G., Subramanian, A.S., Le Roux, J., "Hyperbolic Audio Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10094943, May 2023, pp. 1-5.
    BibTeX TR2023-017 PDF Video Software
    • @inproceedings{Petermann2023may,
    • author = {Petermann, Darius and Wichern, Gordon and Subramanian, Aswin Shanmugam and {Le Roux}, Jonathan},
    • title = {{Hyperbolic Audio Source Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10094943},
    • url = {https://www.merl.com/publications/TR2023-017}
    • }
  •  Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Optimal Condition Training for Target Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095128, May 2023, pp. 1-5.
    BibTeX TR2023-018 PDF
    • @inproceedings{Tzinis2023may,
    • author = {Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and {Le Roux}, Jonathan},
    • title = {{Optimal Condition Training for Target Source Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095128},
    • url = {https://www.merl.com/publications/TR2023-018}
    • }
  •  Ulvog, A., Rapp, J., Koike-Akino, T., Mansour, H., Boufounos, P.T., Parsons, K., "Phase Unwrapping in Correlated Noise for FMCW LIDAR Depth Estimation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095456, May 2023, pp. 1-5.
    BibTeX TR2023-028 PDF Video Presentation
    • @inproceedings{Ulvog2023may,
    • author = {Ulvog, Alfred and Rapp, Joshua and Koike-Akino, Toshiaki and Mansour, Hassan and Boufounos, Petros T. and Parsons, Kieran},
    • title = {{Phase Unwrapping in Correlated Noise for FMCW LIDAR Depth Estimation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • doi = {10.1109/ICASSP49357.2023.10095456},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-028}
    • }
  •  Vaca-Rubio, C., Wang, P., Koike-Akino, T., Wang, Y., Boufounos, P.T., Popovski, P., "mmWave Wi-Fi Trajectory Estimation with Continuous-Time Neural Dynamic Learning", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096474, May 2023, pp. 1-5.
    BibTeX TR2023-033 PDF Video
    • @inproceedings{Vaca-Rubio2023may,
    • author = {Vaca-Rubio, Cristian and Wang, Pu and Koike-Akino, Toshiaki and Wang, Ye and Boufounos, Petros T. and Popovski, Petar},
    • title = {{mmWave Wi-Fi Trajectory Estimation with Continuous-Time Neural Dynamic Learning}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096474},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-033}
    • }
  •  Yen, H., Germain, F., Wichern, G., Le Roux, J., "Cold Diffusion for Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096064, May 2023, pp. 1-5.
    BibTeX TR2023-020 PDF
    • @inproceedings{Yen2023may,
    • author = {Yen, Hao and Germain, Francois and Wichern, Gordon and {Le Roux}, Jonathan},
    • title = {{Cold Diffusion for Speech Enhancement}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096064},
    • url = {https://www.merl.com/publications/TR2023-020}
    • }
  •  Zhao, Q., Ma, Y., Boufounos, P.T., Nabi, S., Mansour, H., "Deep Born Operator Learning for Reflection Tomographic Imaging", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095494, May 2023, pp. 1-5.
    BibTeX TR2023-029 PDF Video
    • @inproceedings{Zhao2023may,
    • author = {Zhao, Qingqing and Ma, Yanting and Boufounos, Petros T. and Nabi, Saleh and Mansour, Hassan},
    • title = {{Deep Born Operator Learning for Reflection Tomographic Imaging}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095494},
    • url = {https://www.merl.com/publications/TR2023-029}
    • }
  •  Menner, M., Berntorp, K., Di Cairano, S., "Automated Controller Calibration by Kalman Filtering", IEEE Transactions on Control Systems Technology, DOI: 10.1109/​TCST.2023.3254213, Vol. 31, No. 6, pp. 2350-2364, April 2023.
    BibTeX TR2023-022 PDF
    • @article{Menner2023apr,
    • author = {Menner, Marcel and Berntorp, Karl and {Di Cairano}, Stefano},
    • title = {{Automated Controller Calibration by Kalman Filtering}},
    • journal = {IEEE Transactions on Control Systems Technology},
    • year = 2023,
    • volume = 31,
    • number = 6,
    • pages = {2350--2364},
    • month = apr,
    • doi = {10.1109/TCST.2023.3254213},
    • url = {https://www.merl.com/publications/TR2023-022}
    • }
  •  Jin, S., Wang, P., Boufounos, P.T., Orlik, P.V., Takahashi, R., Roy, S., "Mutual Interference Mitigation for MIMO-FMCW Automotive Radar", arXiv, April 2023.
    BibTeX arXiv
    • @article{Jin2023apr,
    • author = {Jin, Sian and Wang, Pu and Boufounos, Petros T. and Orlik, Philip V. and Takahashi, Ryuhei and Roy, Sumit},
    • title = {{Mutual Interference Mitigation for MIMO-FMCW Automotive Radar}},
    • journal = {arXiv},
    • year = 2023,
    • month = apr,
    • url = {https://arxiv.org/abs/2304.03177}
    • }
  •  Lin, C., "Analytical Parametrization for Magnetization of Gadolinium based on Scaling Hypothesis", Physica A, DOI: 10.1016/​j.physa.2023.128686, Vol. 617, pp. 128686, April 2023.
    BibTeX TR2023-015 PDF
    • @article{Lin2023apr,
    • author = {Lin, Chungwei},
    • title = {{Analytical Parametrization for Magnetization of Gadolinium based on Scaling Hypothesis}},
    • journal = {Physica A},
    • year = 2023,
    • volume = 617,
    • pages = 128686,
    • month = apr,
    • doi = {10.1016/j.physa.2023.128686},
    • issn = {0378-4371},
    • url = {https://www.merl.com/publications/TR2023-015}
    • }
  •  Cherian, A., Peng, K.-C., Lohit, S., Smith, K., Tenenbaum, J.B., "Are Deep Neural Networks SMARTer than Second Graders?", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March 2023, pp. 10834-10844.
    BibTeX TR2023-014 PDF Video Data Software Presentation
    • @inproceedings{Cherian2023mar,
    • author = {Cherian, Anoop and Peng, Kuan-Chuan and Lohit, Suhas and Smith, Kevin and Tenenbaum, Joshua B.},
    • title = {{Are Deep Neural Networks SMARTer than Second Graders?}},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2023,
    • pages = {10834--10844},
    • month = mar,
    • publisher = {CVF},
    • url = {https://www.merl.com/publications/TR2023-014}
    • }
  •  Sharma, A., Zhang, J., Nikovski, D., Doshi-Velez, F., "Travel-time prediction using neural-network-based mixture models", International Workshop on Statistical Methods and Artificial Intelligence, DOI: 10.1016/​j.procs.2023.03.144, March 2023.
    BibTeX TR2023-012 PDF
    • @inproceedings{Sharma2023mar,
    • author = {Sharma, Abhishek and Zhang, Jing and Nikovski, Daniel and Doshi-Velez, Finale},
    • title = {{Travel-time prediction using neural-network-based mixture models}},
    • booktitle = {International Workshop on Statistical Methods and Artificial Intelligence},
    • year = 2023,
    • month = mar,
    • doi = {10.1016/j.procs.2023.03.144},
    • url = {https://www.merl.com/publications/TR2023-012}
    • }
  •  Wang, Y., Zhang, J., Nikovski, D., Kojima, T., "Estimating Traffic Density Using Transformer Decoders", International Workshop on Statistical Methods and Artificial Intelligence, DOI: 10.1016/​j.procs.2023.03.143, March 2023.
    BibTeX TR2023-011 PDF
    • @inproceedings{Wang2023mar,
    • author = {Wang, Yinsong and Zhang, Jing and Nikovski, Daniel and Kojima, Takuro},
    • title = {{Estimating Traffic Density Using Transformer Decoders}},
    • booktitle = {International Workshop on Statistical Methods and Artificial Intelligence},
    • year = 2023,
    • month = mar,
    • doi = {10.1016/j.procs.2023.03.143},
    • url = {https://www.merl.com/publications/TR2023-011}
    • }
  •  Teo, K.H., "Summary Report of International Electron Device Meeting (IEDM) 2022," Tech. Rep. TR2023-013, Mitsubishi Electric Research Laboratories, March 2023.
    BibTeX TR2023-013 PDF
    • @techreport{Teo2023mar,
    • author = {Teo, Koon Hoo},
    • title = {{Summary Report of International Electron Device Meeting (IEDM) 2022}},
    • institution = {MERL website},
    • year = 2023,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2023-013}
    • }
  •  Yoshino, K., Chen, Y.-N., Crook, P., Kottur, S., Li, J., Hedayatnia, B., Moon, S., Fei, Z., Li, Z., Zhang, J., Feng, Y., Zhou, J., Kim, S., Liu, Y., Jin, D., Papangelis, A., Gopalakrishnan, K., Hakkani-Tur, D., Damavandi, B., Geramifard, A., Hori, C., Shah, A., Zhang, C., Li, H., Sedoc, J., D'Haro, L.F., Banchs, R., Rudnicky, A., "Overview of the Tenth Dialog System Technology Challenge: DSTC10", IEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TCSVT.2002.808437, Vol. 13, No. 2, pp. 121-130, February 2023.
    BibTeX TR2023-109 PDF
    • @article{Yoshino2023feb,
    • author = {{{Yoshino, Koichiro and Chen, Yun-Nung and Crook, Paul and Kottur, Satwik and Li, Jinchao and Hedayatnia, Behnam and Moon, Seungwhan and Fei, Zhengcong and Li, Zekang and Zhang, Jinchao and Feng, Yang and Zhou, Jie and Kim, Seokhwan and Liu, Yang and Jin, Di and Papangelis, Alexandros and Gopalakrishnan, Karthik and Hakkani-Tur, Dilek and Damavandi, Babak and Geramifard, Alborz and Hori, Chiori and Shah, Ankit and Zhang, Chen and Li, Haizhou and Sedoc, João and D'Haro, Luis F. and Banchs, Rafael and Rudnicky, Alexander}}},
    • title = {{{Overview of the Tenth Dialog System Technology Challenge: DSTC10}}},
    • journal = {IEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2023,
    • volume = 13,
    • number = 2,
    • pages = {121--130},
    • month = feb,
    • doi = {10.1109/TCSVT.2002.808437},
    • url = {https://www.merl.com/publications/TR2023-109}
    • }
  •  Kantana, C., Benosman, M., Ma, R., Komatsuzaki, Y., "A System Approach for Efficiency Enhancement and Linearization Technique of Dual-Input Doherty Power Amplifier", IEEE Journal of Microwaves, February 2023.
    BibTeX TR2023-008 PDF
    • @article{Kantana2023feb,
    • author = {Kantana, Chouabi and Benosman, Mouhacine and Ma, Rui and Komatsuzaki, Y.},
    • title = {{A System Approach for Efficiency Enhancement and Linearization Technique of Dual-Input Doherty Power Amplifier}},
    • journal = {IEEE Journal of Microwaves},
    • year = 2023,
    • month = feb,
    • url = {https://www.merl.com/publications/TR2023-008}
    • }
  •  Mateus, A., Ranade, S., Ramalingam, S., Miraldo, P., "Fast and Accurate 3D Registration from Line Intersection Constraints", International Journal of Computer Vision, DOI: 10.1007/​s11263-023-01774-1, Vol. 131, pp. 2044-2069, February 2023.
    BibTeX TR2023-007 PDF
    • @article{Mateus2023feb,
    • author = {Mateus, Andre and Ranade, Siddhant and Ramalingam, Srikumar and Miraldo, Pedro},
    • title = {{Fast and Accurate 3D Registration from Line Intersection Constraints}},
    • journal = {International Journal of Computer Vision},
    • year = 2023,
    • volume = 131,
    • pages = {2044--2069},
    • month = feb,
    • doi = {10.1007/s11263-023-01774-1},
    • url = {https://www.merl.com/publications/TR2023-007}
    • }