Knowing the geometry of a space is desirable for many applications, e.g. sound source localization, sound field reproduction or auralization. In circumstances where only acoustic signals can be obtained, estimating the geometry of a room is a challenging propostition. Existing methods have been proposed to reconstruct a room from the room impulse responses (RIRs). However, the sound source and microphones must be deployed in a feasible region of the room for it to work, which is impractical when the room is unknown. This work propose to employ a robot equipped with a sound source and four acoustic sensors, to follow a proposed path planning strategy to moves around the room to collect first image sources for room geometry estimation. The strategy can effectively drives the robot from a random initial location through the room so that the room geometry is guaranteed to be revelaed. Effectiveness of the proposed approach is extensively validated in a synthetic environment, where the results obtained are highly promising. Read More
Daily Archives: July 3, 2019
Why Tech Giants Are Pinning Their AI Strategy On Deep Learning Frameworks
There’s one aspect that has affected the growth of deep learning research — the proliferation of deep learning frameworks. Popular Deep Learning frameworks such as TensorFlow (Google), PyTorch (one of the newest frameworks that is rapidly gaining popularity), Caffe, MXNet and Keras among others have helped DL researchers achieve human-level efficiencies on tasks such as facial recognition, image classification, object detection, sentiment detection among other tasks. While multiple frameworks for deep learning is great news for the developer community, it is also a part of the marketing pitch to get them to lock the developer base into other solutions (selling compute capability).
— Each of these frameworks was designed to solve a specific problem
— After reaching a certain maturity, the frameworks were open sourced
Read More
Ten Experts Offer Ten-Year Outlook For China's Artificial Intelligence Sector
Ten leading experts on China’s artificial intelligence sector offer their outlook for the Chinese AI industry over the next ten years in a newly released report. Titled “Next 10 Years: What To Expect In China’s Artificial Intelligence Future,” the report is released today during a press conference at the Annual Meeting of the New Champions in Dalian, China.
The report was compiled by China Money Network, who invited 10 industry leaders to present their predictions for the next 10 years. These industry experts come from a wide range of segments, spanning computer vision, speech recognition, autonomous driving, AI chips, healthcare AI, fintech AI, AI-as-a-Service, and investment.
“There is nothing more exciting than listening to these industry leaders describe what our future holds,” says Nina Xiang, founder of China Money Network, a media platform for tracking China’s smart investments and tech innovations. “For sure, the future of China’s AI sector will be far from smooth sailing in a calm ocean. But it is precisely the challenges that make overcoming them so meaningful and rewarding.” Read More
Rick's Cafe AI 