- Date: February 15, 2021
Where: Virtual
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - Diego Romeres, a Principal Research Scientist in MERL's Data Analytics group, gave the invited talk "Reinforcement Learning for Robotics" at the Autonomy Talks organized at ETH, Zurich. In the presentation, some directions to apply Model-based Reinforcement Learning algorithms to real-world applications are presented together with a novel MBRL algorithm called MC-PILCO. The link to the presentation is https://www.youtube.com/watch?v=wYgbgMa4j-s.
-
- Date: February 15, 2021
Where: The 2nd International Symposium on AI Electronics
MERL Contact: Chiori Hori
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
Brief - Chiori Hori, a Senior Principal Researcher in MERL's Speech and Audio Team, will be a keynote speaker at the 2nd International Symposium on AI Electronics, alongside Alex Acero, Senior Director of Apple Siri, Roberto Cipolla, Professor of Information Engineering at the University of Cambridge, and Hiroshi Amano, Professor at Nagoya University and winner of the Nobel prize in Physics for his work on blue light-emitting diodes. The symposium, organized by Tohoku University, will be held online on February 15, 2021, 10am-4pm (JST).
Chiori's talk, titled "Human Perspective Scene Understanding via Multimodal Sensing", will present MERL's work towards the development of scene-aware interaction. One important piece of technology that is still missing for human-machine interaction is natural and context-aware interaction, where machines understand their surrounding scene from the human perspective, and they can share their understanding with humans using natural language. To bridge this communications gap, MERL has been working at the intersection of research fields such as spoken dialog, audio-visual understanding, sensor signal understanding, and robotics technologies in order to build a new AI paradigm, called scene-aware interaction, that enables machines to translate their perception and understanding of a scene and respond to it using natural language to interact more effectively with humans. In this talk, the technologies will be surveyed, and an application for future car navigation will be introduced.
-
- Date: November 16, 2020
MERL Contacts: Devesh K. Jha; Daniel N. Nikovski; Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - MERL researchers, in collaboration with researchers from MELCO and the Department of Brain and Cognitive Science at MIT, have released simulation software Circular Maze Environment (CME). This system could be used as a new benchmark for evaluating different control and robot learning algorithms. The control objective in this system is to tip and the tilt the maze so as to drive one (or multiple) marble(s) to the innermost ring of the circular maze. Although the system is very intuitive for humans to control, it is very challenging for artificial intelligence agents to learn efficiently. It poses several challenges for both model-based as well as model-free methods, due to its non-smooth dynamics, long planning horizon, and non-linear dynamics. The released Python package provides the simulation environment for the circular maze, where movement of multiple marbles could be simulated simultaneously. The package also provides a trajectory optimization algorithm to design a model-based controller in simulation.
-
- Date: October 29, 2020
MERL Contact: Devesh K. Jha
Research Areas: Artificial Intelligence, Machine Learning, Optimization, Robotics
Brief - MERL Researcher Devesh Jha has been appointed to the editorial board of the IEEE Robotics and Automation Letters (RA-L) as an Associate Editor. IEEE RA-L publishes peer-reviewed articles in the areas of robotics and automation which can also be presented at the annual flagship conferences of RAS like ICRA, IROS and CASE.
-
- Date: October 13, 2020
MERL Contact: Siddarth Jain
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Robotics
Brief - Computer vision and robotics researcher, Siddarth Jain, has been appointed to the editorial board of the IEEE Robotics and Automation Letters (RA-L) as an Associate Editor. Siddarth joined MERL in September 2019 after obtaining his Ph.D. in robotics from Northwestern University, where he developed novel robotics systems to help people with motor-impairments in performing activities of daily living tasks.
RA-L publishes peer-reviewed articles in areas of robotics and automation. RA-L also provides a unique feature to the authors with the opportunity to publish a paper in a peer-reviewed journal and present the same paper at the annual flagship robotics conferences of IEEE RAS, including ICRA, IROS, and CASE.
-
- Date: October 15, 2020
Awarded to: Ethan Manilow, Gordon Wichern, Jonathan Le Roux
MERL Contacts: Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - Former MERL intern Ethan Manilow and MERL researchers Gordon Wichern and Jonathan Le Roux won Best Poster Award and Best Video Award at the 2020 International Society for Music Information Retrieval Conference (ISMIR 2020) for the paper "Hierarchical Musical Source Separation". The conference was held October 11-14 in a virtual format. The Best Poster Awards and Best Video Awards were awarded by popular vote among the conference attendees.
The paper proposes a new method for isolating individual sounds in an audio mixture that accounts for the hierarchical relationship between sound sources. Many sounds we are interested in analyzing are hierarchical in nature, e.g., during a music performance, a hi-hat note is one of many such hi-hat notes, which is one of several parts of a drumkit, itself one of many instruments in a band, which might be playing in a bar with other sounds occurring. Inspired by this, the paper re-frames the audio source separation problem as hierarchical, combining similar sounds together at certain levels while separating them at other levels, and shows on a musical instrument separation task that a hierarchical approach outperforms non-hierarchical models while also requiring less training data. The paper, poster, and video can be seen on the paper page on the ISMIR website.
-
- Date: February 4, 2021
Where: N/A
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning
Brief - Dr. Diego Romeres, Principal Research Scientist in the Data Analytics group, will serve on the Programme Committee for the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI), 2021.
-
- Date: August 23, 2020
Where: European Conference on Computer Vision (ECCV), online, 2020
MERL Contact: Anoop Cherian
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
Brief - MERL Principal Research Scientist Anoop Cherian gave an invited talk titled "Sound2Sight: Audio-Conditioned Visual Imagination" at the Multi-modal Video Analysis workshop held in conjunction with the European Conference on Computer Vision (ECCV), 2020. The talk was based on a recent ECCV paper that describes a new multimodal reasoning task called Sound2Sight and a generative adversarial machine learning algorithm for producing plausible video sequences conditioned on sound and visual context.
-
- Date: August 25, 2020
MERL Contact: Ankush Chakrabarty
Research Areas: Artificial Intelligence, Control, Data Analytics, Dynamical Systems, Machine Learning, Optimization, Robotics
Brief - Ankush Chakrabarty co-organized an invited session on “Data-Driven Control For Industrial Applications” at the IEEE Conference on Control Technology and Applications with Shahin Shahrampour (Asst. Prof., Texas A&M). Talks covered topics including reinforcement learning for aerospace systems, constrained reinforcement learning for motors, deep Q learning for traffic systems and participants included speakers from Stanford University, North Carolina State University, Texas A&M, Oklahoma State University, University of Science and Technology at Beijing, and TU Delft.
MERL presented research (Chakrabarty, Danielson, Wang) on constraint-enforcing output-tracking with approximate dynamic programming for servomotor systems.
-
- Date: August 3, 2020
Where: Cambridge, MA
MERL Contact: Abraham P. Vinod
Research Areas: Artificial Intelligence, Control, Optimization, Robotics
Brief - Mitsubishi Electric Research Laboratories is excited to welcome Abraham P. Vinod as the newest member of its research staff, in the Control for Autonomy Team. Abraham joins MERL from the University of Texas, Austin, where he was a Postdoctoral Research Fellow. He obtained his Ph.D. from the University of New Mexico. His PhD research produced scalable algorithms for providing safety guarantees for stochastic, control-constrained, dynamical systems, with applications to motion planning. In his postdoctoral research, Abraham studied theory and algorithms for on-the-fly, data-driven control of unknown systems under severely limited data. His current research interests lie in the intersection of optimization, control, and learning. Abraham won the Best Student Paper Award at the 2017 ACM Hybrid Systems: Computation and Control Conference, was a finalist for the Best Paper Award in the 2018 ACM Hybrid Systems: Computation and Control Conference, and won the best undergraduate student research project award at the Indian Institute of Technology, Madras.
-
- Date: July 22, 2020
Where: Tokyo, Japan
MERL Contacts: Anoop Cherian; Chiori Hori; Jonathan Le Roux; Tim K. Marks; Anthony Vetro
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
Brief - Mitsubishi Electric Corporation announced that the company has developed what it believes to be the world’s first technology capable of highly natural and intuitive interaction with humans based on a scene-aware capability to translate multimodal sensing information into natural language.
The novel technology, Scene-Aware Interaction, incorporates Mitsubishi Electric’s proprietary Maisart® compact AI technology to analyze multimodal sensing information for highly natural and intuitive interaction with humans through context-dependent generation of natural language. The technology recognizes contextual objects and events based on multimodal sensing information, such as images and video captured with cameras, audio information recorded with microphones, and localization information measured with LiDAR.
Scene-Aware Interaction for car navigation, one target application, will provide drivers with intuitive route guidance. The technology is also expected to have applicability to human-machine interfaces for in-vehicle infotainment, interaction with service robots in building and factory automation systems, systems that monitor the health and well-being of people, surveillance systems that interpret complex scenes for humans and encourage social distancing, support for touchless operation of equipment in public areas, and much more. The technology is based on recent research by MERL's Speech & Audio and Computer Vision groups.
-
- Date: July 10, 2020
Where: Virtual Baltimore, MD
MERL Contact: Jonathan Le Roux
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - MERL Senior Principal Research Scientist and Speech and Audio Senior Team Leader Jonathan Le Roux was invited by the Center for Language and Speech Processing at Johns Hopkins University to give a plenary lecture at the 2020 Frederick Jelinek Memorial Summer Workshop on Speech and Language Technology (JSALT). The talk, entitled "Deep Learning for Multifarious Speech Processing: Tackling Multiple Speakers, Microphones, and Languages", presented an overview of deep learning techniques developed at MERL towards the goal of cracking the Tower of Babel version of the cocktail party problem, that is, separating and/or recognizing the speech of multiple unknown speakers speaking simultaneously in multiple languages, in both single-channel and multi-channel scenarios: from deep clustering to chimera networks, phasebook and friends, and from seamless ASR to MIMO-Speech and Transformer-based multi-speaker ASR.
JSALT 2020 is the seventh in a series of six-week-long research workshops on Machine Learning for Speech Language and Computer Vision Technology. A continuation of the well known Johns Hopkins University summer workshops, these workshops bring together diverse "dream teams" of leading professionals, graduate students, and undergraduates, in a truly cooperative, intensive, and substantive effort to advance the state of the science. MERL researchers led such teams in the JSALT 2015 workshop, on "Far-Field Speech Enhancement and Recognition in Mismatched Settings", and the JSALT 2018 workshop, on "Multi-lingual End-to-End Speech Recognition for Incomplete Data".
-
- Date: July 12, 2020 - July 18, 2020
Where: Vienna, Austria (virtual this year)
MERL Contacts: Mouhacine Benosman; Anoop Cherian; Devesh K. Jha; Daniel N. Nikovski
Research Areas: Artificial Intelligence, Computer Vision, Data Analytics, Dynamical Systems, Machine Learning, Optimization, Robotics
Brief - MERL researchers are presenting three papers at the International Conference on Machine Learning (ICML 2020), which is virtually held this year from 12-18th July. ICML is one of the top-tier conferences in machine learning with an acceptance rate of 22%. The MERL papers are:
1) "Finite-time convergence in Continuous-Time Optimization" by Orlando Romero and Mouhacine Benosman.
2) "Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?" by Kei Ota, Tomoaki Oiki, Devesh Jha, Toshisada Mariyama, and Daniel Nikovski.
3) "Representation Learning Using Adversarially-Contrastive Optimal Transport" by Anoop Cherian and Shuchin Aeron.
-
- Date: June 22, 2020
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - We are excited to announce that Dr. Zhong-Qiu Wang, who recently obtained his Ph.D. from The Ohio State University, has joined MERL's Speech and Audio Team as a Visiting Research Scientist. Zhong-Qiu brings strong expertise in microphone array processing, speech enhancement, blind source/speaker separation, and robust automatic speech recognition, for which he has developed some of the most advanced machine learning and deep learning methods.
Prior to joining MERL, Zhong-Qiu received the B.Eng. degree in 2013 from Harbin Institute of Technology, Harbin, China, and the M.Sc. and Ph.D. degree in 2017 and 2020 from The Ohio State University, Columbus, USA, all in Computer Science. He was a summer research intern at Microsoft Research, Mitsubishi Electric Research Laboratories, and Google AI. He received a Best Student Paper Award at ICASSP 2018 for his work as an intern at MERL, and a Graduate Research Award from OSU Department of Computer Science and Engineering in 2020.
-
- Date: June 14, 2020 - June 19, 2020
MERL Contacts: Anoop Cherian; Michael J. Jones; Toshiaki Koike-Akino; Tim K. Marks; Kuan-Chuan Peng; Ye Wang
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Brief - MERL researchers are presenting four papers (two oral papers and two posters) and organizing two workshops at the IEEE/CVF Computer Vision and Pattern Recognition (CVPR 2020) conference.
CVPR 2020 Orals with MERL authors:
1. "Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction," by Maosen Li, Siheng Chen, Yangheng Zhao, Ya Zhang, Yanfeng Wang, Qi Tian
2. "Collaborative Motion Prediction via Neural Motion Message Passing," by Yue Hu, Siheng Chen, Ya Zhang, Xiao Gu
CVPR 2020 Posters with MERL authors:
3. "LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood," by Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Ye Wang, Michael Jones, Anoop Cherian, Toshiaki Koike-Akino, Xiaoming Liu, Chen Feng
4. "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird’s Eye View Maps," by Pengxiang Wu, Siheng Chen, Dimitris N. Metaxas
CVPR 2020 Workshops co-organized by MERL researchers:
1. Fair, Data-Efficient and Trusted Computer Vision
2. Deep Declarative Networks.
-
- Date: June 9, 2020
Where: ICRAxMIT
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, Dynamical Systems, Machine Learning, Robotics
Brief - Diego Romeres, a Principal Research Scientist in MERL's Data Analytics group, gave an invited talk at the workshop ICRAxMIT organized at MIT. The talk briefly described a derivative-free framework that doesn't take in consideration velocities and accelerations to model and control robotic systems. The proposed approach is validated in two real robotic systems.
-
- Date: June 8, 2020 - June 12, 2020
Where: Virtual Hangzhou
MERL Contact: Pu (Perry) Wang
Research Areas: Artificial Intelligence, Computational Sensing, Dynamical Systems, Machine Learning, Signal Processing
Brief - MERL researcher Pu (Perry) Wang organized a special session on June 10, 2020 titled Automotive Radar Sensing. Presentations included topics from deep waveform design, object tracking, mutual interference mitigation with their applications to high-resolution automotive imaging. The session's contributors come from both academia and industry.
In this special session, our previous intern Yuxuan Xia (Chalmers Institute of Technology, Sweden) presented our work on extended object tracking using low-cost automotive radar sensors with a realistic measurement model. Yuxuan was also selected to be one of the six best student paper finalists at IEEE SAM 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, Robotics
Brief - 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).
-
- 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 & Audio
Brief - 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.
-
- Date: November 20, 2019
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning, Robotics
Brief - 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.
-
- Date: November 9, 2019
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - Takaaki Hori has been elected to serve on the Speech and Language Processing Technical Committee (SLTC) of the IEEE Signal Processing Society for a 3-year term.
The SLTC promotes and influences all the technical areas of speech and language processing such as speech recognition, speech synthesis, spoken language understanding, speech to speech translation, spoken dialog management, speech indexing, information extraction from audio, and speaker and language recognition.
-
- Date: October 27, 2019
Awarded to: Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu
MERL Contact: Tim K. Marks
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Brief - 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.
-
- Date: October 10, 2019
Awarded to: Devesh Jha, Nurali Virani, Zhenyuan Yuan, Ishana Shekhawat and Asok Ray
MERL Contact: Devesh K. Jha
Research Areas: Artificial Intelligence, Control, Data Analytics, Machine Learning, Robotics
Brief - 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.
-
- Date: September 22, 2019 - September 26, 2019
MERL Contacts: Devesh K. Jha; Toshiaki Koike-Akino; Kieran Parsons; Ye Wang
Research Areas: Artificial Intelligence, Communications, Electronic and Photonic Devices, Optimization, Signal Processing
Brief - MERL Optical Team scientists will be presenting 5 papers including 2 invited talks at the 45th European Conference on Optical Communication (ECOC) 2019, which is being held in Dublin from September 22-26, 2019. Topics to be presented include recent advances in sophisticated constellation shaping schemes, lattice coding, and deep learning-based turbo equalization to mitigate fiber nonlinearity. Dr. Kojima is giving an invited workshop talk on deep learning-based nano-photonic device optimization. Dr. Tobias Fehenberger, a former Visiting Scientist is giving an invited talk related to our joint paper "Mapping Strategies for Short-Length Probabilistic Shaping"
ECOC is the largest optical communications event in Europe and a key meeting place for more than 1,500 scientists and researchers from institutions and companies across the world. The conference features more than 400 oral and poster presentations from various major telecoms industries and universities. As well as being one of the largest scientific conferences globally, ECOC also features Europe’s largest optical communications exhibition.
-
- Date: September 15, 2019 - September 19, 2019
Where: Graz, Austria
MERL Contacts: Chiori Hori; Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - MERL Speech & Audio Team researchers will be presenting 7 papers at the 20th Annual Conference of the International Speech Communication Association INTERSPEECH 2019, which is being held in Graz, Austria from September 15-19, 2019. Topics to be presented include recent advances in end-to-end speech recognition, speech separation, and audio-visual scene-aware dialog. Takaaki Hori is also co-presenting a tutorial on end-to-end speech processing.
Interspeech is the world's largest and most comprehensive conference on the science and technology of spoken language processing. It gathers around 2000 participants from all over the world.
-