Artificial Intelligence
Making machines smarter for improved safety, efficiency and comfort.
Our AI research encompasses advances in computer vision, speech and audio processing, as well as data analytics. Key research themes include improved perception based on machine learning techniques, learning control policies through model-based reinforcement learning, as well as cognition and reasoning based on learned semantic representations. We apply our work to a broad range of automotive and robotics applications, as well as building and home systems.
Quick Links
-
Researchers
Jonathan
Le Roux
Takaaki
Hori
Daniel
Nikovski
Michael
Jones
Tim
Marks
Chiori
Hori
Devesh
Jha
Anoop
Cherian
Toshiaki
Koike-Akino
Ye
Wang
Alan
Sullivan
Philip
Orlik
Bret
Harsham
Diego
Romeres
Gordon
Wichern
Jeroen
van Baar
William
Yerazunis
Keisuke
Kojima
Niko
Moritz
Kieran
Parsons
Arvind
Raghunathan
Emil
Laftchiev
Saleh
Nabi
Petros
Boufounos
Siheng
Chen
Chungwei
Lin
Hongbo
Sun
Yebin
Wang
Mouhacine
Benosman
Matthew
Brand
Radu
Corcodel
Kyeong Jin
(K.J.)
Kim
Hassan
Mansour
Bingnan
Wang
Jinyun
Zhang
Jianlin
Guo
Hiroyuki
Hashimoto
David
Millar
Anthony
Vetro
Siddarth
Jain
Suhas
Lohit
Kuan-Chuan
Peng
Kazuto
Sugimoto
-
Awards
-
AWARD Best Paper Award at the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2019 Date: December 18, 2019
Awarded to: Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe
MERL Contact: Jonathan Le Roux
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- MERL researcher Jonathan Le Roux and co-authors Xuankai Chang, Shinji Watanabe (Johns Hopkins University), Wangyou Zhang, and Yanmin Qian (Shanghai Jiao Tong University) won the Best Paper Award at the 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019), for the paper "MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition". MIMO-Speech is a fully neural end-to-end framework that can transcribe the text of multiple speakers speaking simultaneously from multi-channel input. The system is comprised of a monaural masking network, a multi-source neural beamformer, and a multi-output speech recognition model, which are jointly optimized only via an automatic speech recognition (ASR) criterion. The award was received by lead author Xuankai Chang during the conference, which was held in Sentosa, Singapore from December 14-18, 2019.
-
AWARD MERL Researchers win Best Paper Award at ICCV 2019 Workshop on Statistical Deep Learning in Computer Vision Date: October 27, 2019
Awarded to: Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu
MERL Contact: Tim Marks
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- MERL researcher Tim Marks, former MERL interns Abhinav Kumar and Wenxuan Mou, and MERL consultants Professor Chen Feng (NYU) and Professor Xiaoming Liu (MSU) received the Best Oral Paper Award at the IEEE/CVF International Conference on Computer Vision (ICCV) 2019 Workshop on Statistical Deep Learning in Computer Vision (SDL-CV) held in Seoul, Korea. Their paper, entitled "UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss," describes a method which, given an image of a face, estimates not only the locations of facial landmarks but also the uncertainty of each landmark location estimate.
-
AWARD MERL Researcher Devesh Jha Wins the Rudolf Kalman Best Paper Award 2019 Date: October 10, 2019
Awarded to: Devesh Jha, Nurali Virani, Zhenyuan Yuan, Ishana Shekhawat and Asok Ray
MERL Contact: Devesh Jha
Research Areas: Artificial Intelligence, Control, Data Analytics, Machine Learning, RoboticsBrief- MERL researcher Devesh Jha has won the Rudolf Kalman Best Paper Award 2019 for the paper entitled "Imitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models". This paper, published in a Special Commemorative Issue for Rudolf E. Kalman in the ASME JDSMC in March 2018, uses Bayesian filtering for imitation learning in Hidden Mode Hybrid Systems. This award is given annually by the Dynamic Systems and Control Division of ASME to the authors of the best paper published in the ASME Journal of Dynamic Systems Measurement and Control during the preceding year.
See All Awards for Artificial Intelligence -
-
News & Events
-
NEWS Diego Romeres appointed as an Associate Editor for IROS 2020 Date: February 14, 2020
Where: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, RoboticsBrief- Diego Romeres, a Research Scientist in MERL's Data Analytics group, will be serving as an Associate Editor (AE) for the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020).
-
NEWS MERL researcher Diego Romeres gave an invited talk at University of Connecticut on Reinforcement Learning for Robotics Date: November 20, 2019
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning, RoboticsBrief- Diego Romeres, a Research Scientist in MERL's Data Analytics group, gave a seminar lecture at the Electrical and Computer Engineering Colloquium of the University of Connecticut. The talk described novel reinforcement algorithms based on combining physical models with non-parametric models of robotic systems derived from data.
See All News & Events for Artificial Intelligence -
-
Research Highlights
-
Internships
-
SP1424: Advanced computational sensing technologies
The Computational Sensing team at MERL is seeking motivated and qualified individuals to develop computational imaging algorithms for a variety of sensing applications. Ideal candidates should be Ph.D. students and have solid background and publication record in any of the following, or related areas: imaging inverse problems, learning for inverse problems, large-scale optimization, blind inverse scattering, radar/lidar/sonar imaging, or wave-based inversion. Experience with experimentally measured data is desirable. Publication of the results produced during our internships is expected. The duration of the internships is anticipated to be 3-6 months. Start date is flexible.
-
MD1441: Advanced Phased Array Transceiver
MERL is looking for a highly motivated, and qualified individual to join our internship program of advanced phased array research. The ideal candidate should be a senior Ph.D. student with rich experience in beam forming technologies. Knowledge of wireless communication, transceiver architecture, and digital signal processing, FPGA and/or Matlab programming skills are required. RF circuits knowledge will be a plus. Duration is 3-6 months with a flexible start date.
-
CV1423: Health Monitoring from Video
MERL is seeking a highly motivated intern to conduct original research in the area of monitoring vital signs, such as heart rate and heart rate variability, from video of a person. The successful candidate will collaborate with MERL researchers to derive and implement new models, collect data, conduct experiments, and prepare results for publication. The candidate should be a PhD student in computer vision with a strong publication record and experience in computer vision, signal processing, machine learning, and health monitoring. Strong programming skills (C/C++, Python, Matlab, etc.) are expected.
See All Internships for Artificial Intelligence -
-
Recent Publications
- , "Multi-Stream End-to-End Speech Recognition", IEEE/ACM Transactions on Audio, Speech and Language Processing, March 2020.BibTeX Download PDFAbout TR2020-030
- @article{Li2020mar,
- author = {Li, Ruizhi and Wang, Xiaofei and Mallidi, Harish and Watanabe, Shinji and Hori, Takaaki and Hermansky, Hynek},
- title = {Multi-Stream End-to-End Speech Recognition},
- journal = {IEEE/ACM Transactions on Audio, Speech and Language Processing},
- year = 2020,
- month = mar,
- url = {https://www.merl.com/publications/TR2020-030}
- }
- , "Overview of the seventh Dialog System Technology Challenge: DSTC7", Computer Speech and Language, March 2020.BibTeX Download PDFAbout TR2020-029
- @article{D’Haro2020mar,
- author = {D’Haro, Luis, Fernando and Yoshino, Koichiro and Hori, Chiori and Marks, Tim and Polymenakos, Lazaros and Kummerfeld, Jonathan, k. and Galley, Michel and Gao, Xiang},
- title = {Overview of the seventh Dialog System Technology Challenge: DSTC7},
- journal = {Computer Speech and Language},
- year = 2020,
- month = mar,
- url = {https://www.merl.com/publications/TR2020-029}
- }
- , "Deep Neural Network Inverse Design of Integrated Nanophotonic Devices", arXiv, March 2020.BibTeX Download PDFAbout TR2020-026
- @article{Tang2020mar2,
- author = {Tang, Yingheng and Kojima, Keisuke and Koike-Akino, Toshiaki and Wang, Ye and Wu, Pengxiang and TaherSima, Mohammad and Jha, Devesh and Parsons, Kieran and Qi, Minghao},
- title = {Deep Neural Network Inverse Design of Integrated Nanophotonic Devices},
- journal = {arXiv},
- year = 2020,
- month = mar,
- url = {https://www.merl.com/publications/TR2020-026}
- }
- , "Generative Deep Learning Model for a Multi-level NanoOptic Broadband Power Splitter", Optical Fiber Communication Conference and Exposition (OFC), DOI: 10.1364/OFC.2020.Th1A.1, ISBN: 978-1-943580-71-2, March 2020, pp. Th1A.1.BibTeX Download PDFAbout TR2020-025
- @inproceedings{Tang2020mar,
- author = {Tang, Yingheng and Kojima, Keisuke and Koike-Akino, Toshiaki and Wang, Ye and Wu, Pengxiang and TaherSima, Mohammad and Jha, Devesh and Parsons, Kieran and Qi, Minghao},
- title = {Generative Deep Learning Model for a Multi-level NanoOptic Broadband Power Splitter},
- booktitle = {Optical Fiber Communication Conference and Exposition (OFC)},
- year = 2020,
- pages = {Th1A.1},
- month = mar,
- publisher = {OSA},
- doi = {10.1364/OFC.2020.Th1A.1},
- isbn = {978-1-943580-71-2},
- url = {https://www.merl.com/publications/TR2020-025}
- }
- , "Spatio-Temporal Ranked-Attention Networks for Video Captioning", IEEE Winter Conference on Applications of Computer Vision (WACV), February 2020.BibTeX Download PDFAbout TR2020-016
- @inproceedings{Cherian2020feb,
- author = {Cherian, Anoop and Wang, Jue and Hori, Chiori and Marks, Tim},
- title = {Spatio-Temporal Ranked-Attention Networks for Video Captioning},
- booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
- year = 2020,
- month = feb,
- url = {https://www.merl.com/publications/TR2020-016}
- }
- , "FX-GAN: Self-Supervised GAN Learning via Feature Exchange", IEEE Winter Conference on Applications of Computer Vision (WACV), February 2020.BibTeX Download PDFAbout TR2020-014
- @inproceedings{Huang2020feb,
- author = {Huang, Rui and Xu, Wenju and Lee, Teng-Yok and Cherian, Anoop and Wang, Ye and Marks, Tim},
- title = {FX-GAN: Self-Supervised GAN Learning via Feature Exchange},
- booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
- year = 2020,
- month = feb,
- url = {https://www.merl.com/publications/TR2020-014}
- }
- , "Learning a distance function with a Siamese network to localize anomalies in videos", IEEE Winter Conference on Applications of Computer Vision (WACV), February 2020.BibTeX Download PDFAbout TR2020-015
- @inproceedings{Jones2020feb,
- author = {Ramachandra, Bharathkumar and Jones, Michael J. and Vatsavai, Ranga},
- title = {Learning a distance function with a Siamese network to localize anomalies in videos},
- booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
- year = 2020,
- month = feb,
- url = {https://www.merl.com/publications/TR2020-015}
- }
- , "UNSUPERVISED SPEAKER ADAPTATION USING ATTENTION-BASED SPEAKER MEMORY FOR END-TO-END ASR", arXiv, February 2020.BibTeX Download PDFAbout TR2020-019
- @article{Sari2020feb,
- author = {Sari, Leda and Moritz, Niko and Hori, Takaaki and Le Roux, Jonathan},
- title = {UNSUPERVISED SPEAKER ADAPTATION USING ATTENTION-BASED SPEAKER MEMORY FOR END-TO-END ASR},
- journal = {arXiv},
- year = 2020,
- month = feb,
- url = {https://www.merl.com/publications/TR2020-019}
- }
- , "Multi-Stream End-to-End Speech Recognition", IEEE/ACM Transactions on Audio, Speech and Language Processing, March 2020.
-
Free Downloads
