EE Seminar: OrCam Hear: Listening Redefined – Sound Source Separation and Speech Enhancement on the Edge
הרישום לסמינר יבוצע באמצעות סריקת הברקוד למודל (יש להיכנס לפני כן למודל, לא באמצעות האפליקציה) - )- הרישום מסתיים ב- 13:10
Registration to the seminar will be done by scanning the barcode for the Moodle (Please enter ahead to the Moodle, NOT by application)- Registration ends at 13:10
(The talk will be given in English)
Speaker: Tal Rosenwein, CEO and Chief of AI at OrCam Hear
|
011 hall, Electrical Engineering-Kitot Building |
Monday, June 30th, 2025
13:00 - 14:00
|
|
OrCam Hear: Listening Redefined – Sound Source Separation and Speech Enhancement on the Edge
Abstract
In this talk, I will present the challenge and solution behind OrCam Hear's selective hearing technology, a system recently named one of TIME’s Best Inventions of 2024. We will begin with a high-level overview of the product and its impact, and then dive into the technical foundations, focusing on problem formulation and three core tasks in speech enhancement: noise reduction, blind source separation, and target speech enhancement. The talk will also touch on key trade-offs and innovations that enabled us to run complex AI pipelines in real time on the edge.
Short Bio
Tal Rosenwein is the CEO and Chief of AI at OrCam Hear, and an adjunct lecturer in Tel Aviv University’s Computer Science faculty. Over the past 10.5 years, Tal has specialized in speech enhancement and conversational AI, leading the development of 8 product lines used in over 35 countries. His work has resulted in dozens of patents and multiple research papers published in top AI/ML conferences. Tal has given tutorials at international conferences and organized the Israeli conference for audio and speech technologies (iSpeech).
