Audio and acoustics

Publication

Constrained Convolutional-recurrent Networks to Improve Speech Quality with Low Impact on Recognition Accuracy

Rasool Fakoor, Xiaodong He, Ivan Tashev, Shuayb Zarar

IEEE Int. Conf. Acoustics Speech and Signal Processing (ICASSP) | April 2018

Project

Publication

A Hybrid Approach to Combining Conventional and Deep Learning Techniques for Single-channel Speech Enhancement and Recognition

Yan-Hui Tu, Ivan Tashev, Shuayb Zarar, Chin-Hui Lee

IEEE Int. Conf. Acoustics Speech and Signal Processing (ICASSP) | April 2018

Project

Publication

Speech enhancement for cochlear implant recipients

The Journal of the Acoustical Society of America | April 2018, Vol 143(4): pp. 2244-2254

Video

Live 360 Audio and Video Streaming

March 27, 2018 | Hannes Gamper, David Johnston, Ivan Tashev

Demonstration of Live 360 degrees Audio and Video Streaming during Microsoft Research TechFest, as well as at ICASSP and Interspeech conferences. Designed by members of the Audio and Acoustics Research Group and Microsoft Research Hardware…

03:49

Video

Microsoft Hands-Free Music

March 9, 2018 | Tambie Angel

Our mission is to restore critical expressive & creative channels for people severely affected by disabling conditions, such as ALS, spinal cord injury, and related conditions with potential to isolate and erect innumerable, formidable barriers…

0:01:47

Video

Microsoft Soundscape: A Map Delivered in 3D Sound

February 28, 2018

“Soundscape fills in a lot of the mental map as you move, making it effortless and seamless to know what’s around you,” highlights Erin Lauridsen of Lighthouse for the Blind in San Francisco. Microsoft Soundscape…

Microsoft Soundscape - A Map Delivered in 3D Sound

0:02:44

Publication

Cracking the cocktail party problem by multi-beam deep attractor network

Zhuo Chen, Jinyu Li, Xiong Xiao, Takuya Yoshioka, Huaming Wang, Zhenghao Wang, Yifan Gong

ASRU 2018 | December 2017

Publication

Precision Scaling of Neural Networks for Audio Processing

Jong Hwan Ko, Josh Fromm, Matthai Philipose, Ivan Tashev, Shuayb Zarar

Neural Information Processing Systems (NIPS) | December 2017

Wkshp. on Machine Learning for Audio Signal Processing

Project

Publication

Reinforcement Learning To Adapt Speech Enhancement to Instantaneous Input Signal Quality

Rasool Fakoor, Xiaodong He, Ivan Tashev, Shuayb Zarar

Neural Information Processing Systems (NIPS) | December 2017

Wkshp. on Machine Learning for Audio Signal Processing

Project

Microsoft Expressive Pixels

Expressive Pixels introduces an authoring app combined with open-source firmware, peripherals, documentation, and APIs that allow users and makers to create animations and then display them on a range of colorful LED display devices.