Bio

My name is Yael Segal-Feldman, I’m an AI researcher with a Ph.D. in Electrical and Computer Engineering from the Technion – Israel Institute of Technology, where I was advised by Prof. Joseph Keshet. My research introduced the concept of the Speech Object and focused on its representation across multiple levels. I’ve developed algorithms for keyword spotting, spoken term detection, diadochokinetic (DDK) tasks, and pitch tracking.

Currently, I work at aiOla, where I build speech and language technologies that turn cutting-edge research into real-world products. My interests include multilingual and low-resource systems, as well as emerging techniques like speculative decoding.

Publications

• FlowTSE: Target Speaker Extraction with Flow Matching. Aviv Navon, Aviv Shamsian, Yael Segal, Neta Glazer, Gil Hetz and Joseph Keshet. (INTERSPEECH 2025). Demo.
• Whisper in Medusa’s Ear: Multi-head Efficient Decoding for Transformer-based ASR. Yael Segal, Aviv Shamsian, Aviv Navon, Gill Hetz and Joseph Keshet. (ICASSP 2025). Code, Blog.
• Enhancing analysis of diadochokinetic speech using deep neural networks. Yael Segal, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts and Joseph Keshet. Computer Speech & Language 90 (2025). Code.
• Hebdb: a weakly supervised dataset for hebrew speech processing. Arnon Turetzky, Or Tal, Yael Segal, Yehoshua Dissen, Ella Zeldes, Amit Roth, Eyal Cohen et al. (INTERSPEECH 2024). Dataset.
• Speech characteristics yield important clues about motor function: Speech variability in individuals at clinical high-risk for psychosis. Kasia Hitczenko,Yael Segal, Joseph Keshet, Matthew Goldrick, Adam Buchwald, Angela Roberts and Vijay A. Mittal. Schizophrenia 9, no. 1 (2023). Code.
• DDKtor: Automatic diadochokinetic speech analysis. Yael Segal, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts and Joseph Keshet. (INTERSPEECH 2022). Code.
• DeepFry: Identifying Vocal Fry Using Deep Neural Networks. Bronya R. Chernyak*, Talia Ben Simon*, Yael Segal*, Jeremy Steffman, Eleanor Chodroff, Jennifer S. Cole, Joseph Keshet. (INTERSPEECH 2022). Code
• Pitch Estimation by Multiple Octave Decoders. Yael Segal, May Arama-Chayoth, Joseph Keshet. IEEE Signal Processing Letters, vol. 28, pp. 1610-1614, 2021, doi: 10.1109/LSP.2021.3100812. Code
• CNN-based Spoken Term Detection and Localization without Dynamic Programming. Tzeviya Sylvia Fuchs*, Yael Segal*, Joseph Keshet. The 46th IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), 2021.
• SpeechYOLO: Detection and Localization of Speech Objects. Yael Segal*, Tzeviya Sylvia Fuchs*, Joseph Keshet. The 20th Annual Conference of the International Speech Communication Association INTERSPEECH 2019, Sep. 2019, pp. 4210–4214, Code.