Joseph Keshet

Joseph ‘Yossi’ Keshet

Speech, Language, and Artificial Intelligence.

I am an Associate Professor at the Viterbi Faculty of Electrical and Computer Engineering at the Technion – Israel Institute of Technology, where I direct the Speech, Language, and AI Lab, affiliated with the Signal and Image Processing Lab (SIPL).

 

I am also Chief Scientist at aiOla. aiOla helps enterprises integrate Conversational AI through APIs or apps. aiOla’s technology adapts to any language, jargon, or accent, unlocking spoken data, streamlining workflows, and improving the user experience.

Full CV

My Research

I am passionate about human speech—one of the most fundamental yet intricately complex signals we know. Speech carries not only the information a speaker intends to convey but also reveals their identity, emotional state, and even medical condition. My drive to understand and quantify speech shapes my research interests, which span both machine learning and the computational study of human speech and language.

Blog

News

Workshop
iSpeech 2025
On July 23, 2025, we will hold the second Israeli conference on Speech & AI at the Technion. The program and registration can be found here.  
Interview
The New Supercomputer “Israel-1” by NVIDIA
An interview in YNet (Yedioth Ahronoth) was published with me on Friday in “7 Days” by Dror Feuer on the topic of the new supercomputer “Israel-1” by NVIDIA.
Interview
Why Amazon Scholar Yossi Keshet remains ‘excited about speech’
A blog post at Amazon Science by Larry Hardesty.
Committee
IEEE/ACM Transactions on Audio, Speech, and Language Processing
I was nominated as an Associated Editor for the journal IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Publications

Transformer architectures, similar to those behind ChatGPT, are the foundation of today’s most successful speech recognition systems. Likewise, diffusion-based models have become key to state-of-the-art speech synthesis and generation. My recent publications focus on improving the performance and conceptual understanding of these architectures within the speech domain.
Sound

All publications

A Front-End Adaptation Network for Improving Speech Recognition Performance in Packet Loss and Noisy Environments

Yehoshua Dissen, Shiry Yonash, Israel Cohen, and Joseph Keshet

IEEE Transactions on Audio, Speech and Language Processing, Volume 33, pp. 2175-2188, 2025
Spectral Analysis of Diffusion Models with Application to Schedule Design

Roi Benita, Michael Elad, Joseph Keshet

Preprint, 2025
FlowTSE: Target Speaker Extraction with Flow Matching

Aviv Navon, Aviv Shamsian, Yael Segal-Feldman, Neta Glazer, Gil Hetz, Joseph Keshet

The 26th Annual Conference of the International Speech Communication Association (Interspeech), 2025.
Whisper in Medusa’s Ear: Multi-head Efficient Decoding for Transformer-based ASR

Yael Segal-Feldman, Aviv Shamsian, Aviv Navon, Gill Hetz, Joseph Keshet

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Enhancing analysis of diadochokinetic speech using deep neural networks

Yael Segal-Feldman, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts, Joseph Keshet

Computer Speech & Language, Volume 90, 101715, March 2025
Predicting relative intelligibility from inter-talker distances in a perceptual similarity space for speech

Seung-Eun Kim, Bronya R Chernyak, Joseph Keshet, Matthew Goldrick, Ann R Bradlow

Psychonomic Bulletin & Review, 2025

Courses

Speech Processing with Deep Learning

Speech recognition and synthesis have become foundational components in the development of modern artificial intelligence, bridging the gap between human communication and machine interaction. This course aims to provide a comprehensive introduction to the core principles of speech signal processing and modeling, essential for understanding how machines perceive and generate human language.

Read More

Deep Learning

This course covers key theoretical and practical tools for deep learning, with an emphasis on supervised learning. Topics include gradient descent, fully-connected and convolutional networks, training methods, and architectures for sequential data like transformers. We also explore techniques to improve data and resource efficiency, such as pre-training, self-supervised learning, quantization, and pruning.

Read More

Transformers and Large Language Models

Transformers are powerful deep learning architectures that have revolutionized how machines understand and generate sequential data. From enabling breakthroughs in language models like ChatGPT to powering cutting-edge systems in speech recognition and computer vision, Transformers have become a cornerstone of modern AI. This course explores their design, capabilities, and impact across a range of domains.

Read More
|ECE 460747|ECE 460217|ECE 0480011