PeopleofSuperintelligence

Researcher

Hynek Hermansky

Also known as Hynek Heřmanský

Hynek Hermansky is a speech scientist whose bio-inspired approaches to speech processing helped make machine speech recognition robust. Born in 1946 in Nové Město na Moravě, he graduated in electrical engineering from Brno University of Technology in 1972, earned a doctorate at Tokyo University and worked in US industrial research in the 1980s. He introduced perceptual linear prediction (PLP), one of the two primary feature sets for speech recognition, in 1987 and the channel-robust RASTA-PLP method in 1991, and he developed the TANDEM technique, which links neural-net features to conventional recognizers. His career took him to a professorship at the Oregon Graduate Institute, the research directorship of IDIAP in Switzerland and 12 years as head of the Center for Language and Speech Processing at Johns Hopkins, with the ISCA Medal for Scientific Achievement in 2013 and the IEEE Flanagan Speech and Audio Processing Award in 2020. Now a professor emeritus at Johns Hopkins, he is a researcher in the Speech@FIT group in Brno and received a Czech AI Award in December 2025.

Timeline

  1. 1946–1972

    Electrical engineering in Brno

    Born in 1946 in Nové Město na Moravě, he graduates in electrical engineering from Brno University of Technology in 1972.

  2. 1980s

    Perceptual linear prediction

    After a doctorate at Tokyo University, he works in US industrial research in the 1980s for Panasonic Technologies and U.S. West Advanced Technologies. In 1987, he presents perceptually based linear prediction (PLP), a low-order all-pole model of the critical-band auditory spectrum that gives higher speaker-independent recognition accuracy than standard linear prediction at lower computational cost. PLP becomes one of the two primary feature sets used internationally for speech recognition.

  3. 1990s

    RASTA and a lab in Oregon

    In 1991, with Nelson Morgan, Aruna Bayya and Phil Kohn, he presents RASTA-PLP, an analysis technique that resists distortion from the communication channel and cuts recognition errors on telephone-quality digits by an order of magnitude. In the first half of the 1990s, he becomes a professor at the Oregon Graduate Institute in Portland, where many Czech students from Brno come to study with him around 2000.

  4. 2003–2022

    From IDIAP to Johns Hopkins

    In 2003, he moves to Switzerland as research director of the IDIAP Research Institute in Martigny and becomes a titular professor at EPFL in Lausanne. At the end of 2008, he joins Johns Hopkins University, where he heads the Center for Language and Speech Processing for 12 years and holds the Julian S. Smith Professorship of Electrical Engineering. He becomes a professor emeritus at Johns Hopkins in 2022.

  5. 2011–2013

    ISCA Fellow and ISCA Medal

    ISCA names him a Fellow in 2011 for his contributions in bio-inspired approaches to processing of speech. He receives the ISCA Medal for Scientific Achievement at Interspeech 2013 in Lyon, France.

  6. 2020

    The IEEE Flanagan Award

    He receives the 2020 IEEE James L. Flanagan Speech and Audio Processing Award for contributions to speech processing and feature extraction for robust speech recognition. His work includes TRAP, one of the first techniques to use very large temporal contexts of speech, and TANDEM, which interfaces neural-net features with conventional speech recognition systems.

  7. December 2025

    A Czech AI Award

    In December 2025, he receives one of six AI Awards presented at Vzlet in Prague, the only professional AI awards in the Czech Republic, for his long-term contribution to speech recognition and machine processing.

  8. As of October 2026

    Researcher at Speech@FIT in Brno

    He is a researcher in the Speech@FIT research group at Brno University of Technology, where he helps lead projects and mentor young scientists, and an emeritus professor at Johns Hopkins University. Brno is where he spends most of the year.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Hynek Hermansky yet. Send us a free-licensed photo.

  1. AI Awards for Professor Hynek Heřmanský: The significance of an extraordinary scientific figure recognized at home as well fit.vut.cz. Checked 19 October 2026.
  2. ISCA Archive - Automatic speech recognition and human auditory perception isca-archive.org. Checked 19 October 2026.
  3. Hynek Hermansky - Engineering and Technology History Wiki ethw.org. Checked 19 October 2026.
  4. ISCA Archive - Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP) isca-archive.org. Checked 19 October 2026.
  5. ISCA - ISCA Fellow Program isca-speech.org. Checked 19 October 2026.
  6. ISCA - ISCA Medal for Scientific Achievement isca-speech.org. Checked 19 October 2026.
  7. IEEE SLTC Newsletter - June 2019 | IEEE Signal Processing Society signalprocessingsociety.org. Checked 19 October 2026.
  8. Hynek Hermansky: Learning: It’s not just for machines anymore | VGS Invited Talks @ FIT vgs-it.fit.vutbr.cz. Checked 19 October 2026.