Hagai Aronowitz's homepage

I am leading the speech analysis research team in IBM Research - Haifa, focusing on language recognition, emotion recognition, self-supervised learning, and speaker analysis.

I used to work on speech recognition, speaker recognition, speaker diarization, face recognition, audiovisual processing, and recognition.

I am an elected member of the Speech and Language Technical Committee (SLTC), which is part of the IEEE Signal Processing Society.

I am chairing sessions in Interspeech, ICASSP, and Speaker Odyssey. I am a program committee member in Interspeech and a scientific committee member in Speaker Odyssey. I gave a tutorial in Interspeech 2014 on speaker diarization and organized and chaired special sessions in Interspeech 2014 and 2016 on text-dependent speaker verification.

1. My publication list

2. A talk I gave at Google (Mountain View) and SRI International (Menlo Park) in September 2016.

3. I gave a 3 hour tutorial on speaker diarization in Interspeech, 2014

4. A talk I gave at the Technion (TCE 2014) on Voice Biometrics for Mobile Authentication

5. A seminar on Speaker Diarization I gave in Tel Aviv University in 30/4/2013

68. My patent list

My most frequently checked email address is currently my work email,

hagaia@com.ibm.il, reverse the domain name so that a.b.c becomes c.b.a .

Keywords people might search for me by: speech recognition, speaker recognition, speaker verification, speaker identification, language identification, speaker diarization, speaker segmentation, speaker clustering, emotion recognition, voice activity detection, GALE, HERMES, intersession variability modeling, text-dependent speaker recognition, domain adaptation, domain robustness, inter dataset variability compensation (IDVC), small development set, face recognition, multi-modal biometrics, spoofing and spoofing detection, lipreading. audiovisual processing, score fusion, policy management, self supervised learning, HuBERT, wav2vec 2.0.