8 papers
AmbiDrop: Ambisonics-Based Array-Agnostic Neural Speech Enhancement
Michael Tatarjitzky, Vladimir Tourbabin, Boaz Rafaely
Multichannel Deep Neural Networks (DNNs) have significantly improved speech enhancement performance; however, they typically remain constrained by reliance on fixed microphone arra…
Array-Aware Ambisonics and HRTF Encoding for Binaural Reproduction With Wearable Arrays
Yhonatan Gayer, Vladimir Tourbabin, Zamir Ben Hur +2
This work introduces a novel method for binaural reproduction from arbitrary microphone arrays, based on array-aware optimization of Ambisonics encoding through Head-Related Transf…
SRP-PHAT-NET: A Reliability-Driven DNN for Reverberant Speaker Localization
Bar Shaybet, Vladimir Tourbabin, Boaz Rafaely
Accurate Direction-of-Arrival (DOA) estimation in reverberant environments remains a fundamental challenge for spatial audio applications. While deep learning methods have shown st…
Microphone Occlusion Mitigation for Own-Voice Enhancement in Head-Worn Microphone Arrays Using Switching-Adaptive Beamforming
Wiebke Middelberg, Jung-Suk Lee, Saeed Bagheri Sereshki +3
Enhancing the user's own-voice for head-worn microphone arrays is an important task in noisy environments to allow for easier speech communication and user-device interaction. Howe…
Ambisonics Encoder for Wearable Array with Improved Binaural Reproduction
Yhonatan Gayer, Vladimir Tourbabin, Zamir Ben-Hur +2
Ambisonics Signal Matching (ASM) is a recently proposed signal-independent approach to encoding Ambisonic signal from wearable microphone arrays, enabling efficient and standardize…
Design and Analysis of Binaural Signal Matching with Arbitrary Microphone Arrays and Listener Head Rotations
Lior Madmoni, Zamir Ben-Hur, Jacob Donley +2
Binaural reproduction is rapidly becoming a topic of great interest in the research community, especially with the surge of new and popular devices, such as virtual reality headset…