PeopleofSuperintelligence

Researcher

Hideki Kawahara

Also known as 河原 英紀, Kawahara Hideki

Hideki Kawahara is a speech scientist whose STRAIGHT system for speech analysis, modification and synthesis extends the classical channel vocoder and became the basis of many speech manipulation experiments and products. After studying electrical engineering at Hokkaido University, he worked at NTT laboratories and ATR from 1977 to 1997, then joined Wakayama University as a professor in 1997. With Alain de Cheveigné, he published the YIN fundamental frequency estimator in 2002, and a STRAIGHT-based text-to-speech system won first place in the Blizzard Challenge in 2005. From August 2015 to June 2016 he was a visiting research scientist in Google's speech group in London, and in 2022 he became both an IEEE Fellow and an ISCA Fellow. He is an emeritus professor at Wakayama University and, since April 2025, a visiting researcher at the University of Electro-Communications.

Timeline

  1. 1968–1977

    Electrical engineering at Hokkaido

    He studies electrical engineering at Hokkaido University from 1968, continuing through the master's course and then the doctoral course until 1977. He holds a Doctor of Engineering from Hokkaido University.

  2. 1977–1997

    Research at NTT and ATR

    He joins NTT's Electro Communications Laboratories as a researcher in 1977 and serves as a senior researcher supervisor at NTT Basic Research Laboratories from 1984 to 1992. From 1992 to 1997, he heads Department 1 of the ATR Human Information Processing Research Laboratories.

  3. 1997–2015

    Professor at Wakayama University

    He becomes a professor in Wakayama University's Faculty of Systems Engineering in April 1997 and leads the CREST Auditory Brain Project as principal investigator from 1997 to 2002. He directs the university's Center for System and Information from 2009 to 2013 and becomes an emeritus professor in April 2015.

  4. 1997–2002

    Pitch-adaptive analysis and YIN

    At ICASSP in 1997, he presents "Speech Representation and Transformation using Adaptive Interpolation of Weighted Spectrum: VOCODER Revisited." His 1999 Speech Communication paper with Ikuyo Masuda-Katsuse and Alain de Cheveigné, on pitch-adaptive time-frequency smoothing and instantaneous-frequency-based F0 extraction, wins the EURASIP best paper award for 1998–1999. In 2002, he and de Cheveigné publish YIN, a fundamental frequency estimator for speech and music, in the Journal of the Acoustical Society of America.

  5. 2005–2008

    Blizzard win and TANDEM-STRAIGHT

    A STRAIGHT-based text-to-speech system wins first place in the Blizzard Challenge, reported at Interspeech 2005. In a 2006 invited review, he describes STRAIGHT, a speech analysis, modification and synthesis system, as an extension of the classical channel vocoder. He presents TANDEM-STRAIGHT, a completely new reformulation of STRAIGHT, at ICASSP 2008.

  6. 2015–2016

    Visiting scientist at Google UK

    From August 2015 to June 2016, he is a visiting research scientist in Google's speech group in London, where he develops an F0 and aperiodicity analysis framework for high-quality speech synthesis with Yannis Agiomyrgiannakis and Heiga Zen, presented at the ISCA workshop SSW9 in 2016. As a 2015–2016 APSIPA Distinguished Lecturer, he speaks at Stanford's CCRMA in November 2015 about STRAIGHT, by then the basis of many speech manipulation experiments and products.

  7. 2019–2022

    IEEE and ISCA fellowships

    The Acoustical Society of Japan gives him its Distinguished Contribution Award in May 2019 for contributions to hearing research and speech technologies. In January 2022, the IEEE elevates him to Fellow for contributions to auditory-inspired speech signal processing and science. He becomes an ISCA Fellow in 2022 for contributions to speech signal processing and speech science by introducing flexible speech analysis, modification and synthesis systems.

  8. Since 2025

    Visiting researcher at UEC

    In April 2025, he joins the University of Electro-Communications' School of Informatics and Engineering as a visiting researcher and remains an emeritus professor at Wakayama University. He releases all of STRAIGHT's functions, including generalized voice morphing, as open-source GUI tools based on the WORLD vocoder, which he and Masanori Morise describe in Acoustical Science and Technology in 2024 and 2025.

  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 Hideki Kawahara yet. Send us a free-licensed photo.

  1. Hideki Kawahara - My portal - researchmap researchmap.jp. Checked 19 October 2026.
  2. Hideki Kawahara, Emeritus Professor, Wakayama University web.wakayama-u.ac.jp. Checked 19 October 2026.
  3. Fundamental frequency — librosa 1.0.0 documentation librosa.org. Checked 19 October 2026.
  4. STRAIGHT, exploitation of the other aspect of VOCODER: Perceptually isomorphic decomposition of speech sounds jstage.jst.go.jp. Checked 19 October 2026.
  5. [1605.07809] Using instantaneous frequency and aperiodicity detection to estimate F0 for high-quality speech synthesis arxiv.org. Checked 19 October 2026.
  6. APSIPA - Education apsipa.org. Checked 19 October 2026.
  7. Hideki Kawahara on STRAIGHT (high resolution speech modifications) | CCRMA ccrma.stanford.edu. Checked 19 October 2026.
  8. 46 SPS Members Elevated to Fellow | IEEE Signal Processing Society signalprocessingsociety.org. Checked 19 October 2026.
  9. ISCA - ISCA Fellow Program isca-speech.org. Checked 19 October 2026.