Amir Ivry | Diffusion Nets for Voice Activity Detection
Details
Join Zoom Meeting
https://zoom.us/j/6043600514?pwd=VTFuU2VSTTNhTE1RRFJTZjhZNTN1Zz09
Meeting ID: 604 360 0514
Password: 703769
Abstract:
We address voice activity detection in acoustic environments of transients and stationary noises, which often occur in real life scenarios. We exploit unique spatial patterns of speech and non- speech audio frames by independently learning their underlying geometric structure. This process is done through a deep encoder-decoder based neural network architecture. This structure involves an encoder that maps spectral features with temporal information to their low-dimensional representations, which are generated by applying the diffusion maps method. The encoder feeds a decoder that maps the embedded data back into the high-dimensional space. A deep neural network, which is trained to separate speech from non-speech frames, is obtained by concatenating the decoder to the encoder, resembling the known Diffusion nets architecture. Experimental results show enhanced performance compared to competing voice activity detection methods. The improvement is achieved in both accuracy, robustness, and generalization ability. Our model performs in a real-time manner and can be integrated into audio-based communication systems. We also present a batch algorithm which obtains an even higher accuracy for online applications
Bio:
Amir Ivry is an artificial intelligence researcher and systems developer. Amir is a PhD candidate in the Electrical Engineering Faculty in the Technion, under the supervision of Prof. Israel Cohen and Dr. Baruch Berdugo. His research deals with audio-based applications using advanced deep learning architectures in challenging acoustic environments of noises, interferences, reverberations, and audio frauds. Amir is an IDF Captain serving in an elite technological unit, with 5 years of experience in developing real-time AI-based systems for various applications. His passion for all-AI related has brought Amir to publish 8 academic papers so far in IEEE, the world’s largest professional organization. Also, Amir is the co-author and chief editor of a novel deep learning book, to be published in Amazon during this year. Amir has delivered dozens of lectures for technological audiences in both the defense, private, and academic sectors about his developed deep learning algorithms. Amir is a technological and strategic consultant for corporates, startups, and hedge funds in both Israel, NYC, and Silicon Valley. Amir is the laurate of the Technion’s graduate school Jacobs award for excellent research students (19’&20’) and won multiple awards for his service in the defense sector. Amir is 27 years old and lives near Tel-Aviv.