World's Best Scientists 2026 revealed!
Award Badge
Computer Science
Japan
2025

D-Index & Metrics

Computer Science

D-Index
61
Citations
19955
World Ranking
3013
National Ranking
23

Research.com Recognitions

  • 2025 - Research.com Computer Science in Japan Leader Award
  • 2022 - Research.com Computer Science in Japan Leader Award

Overview

Keiichi Tokuda is affiliated with the Nagoya Institute of Technology in Japan. The primary field of research includes computer science, with a significant focus on artificial intelligence and signal processing. Their work spans multiple subfields including plant science, mechanical engineering, and civil and structural engineering.

The scientist's research topics cover several areas related to speech and audio technologies. These topics include:

  • Speech Recognition and Synthesis
  • Speech and Audio Processing
  • Topic Modeling
  • Music and Audio Processing
  • Speech and Dialogue Systems
  • Natural Language Processing Techniques
  • Smart Agriculture and AI

Keiichi Tokuda has a publication record across multiple well-known venues. Frequent publication venues are:

  • arXiv (Cornell University)
  • IEEE Access
  • IEEE Open Journal of Signal Processing
  • Interspeech 2022
  • ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing

Recent notable papers authored or co-authored by Keiichi Tokuda include:

  • Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech (2024, IEEE Open Journal of Signal Processing)
  • End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue (2022, Interspeech 2022)
  • PeriodNet: A Non-Autoregressive Raw Waveform Generative Model With a Structure Separating Periodic and Aperiodic Components (2021, IEEE Access)
  • Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism (2021, arXiv)
  • Autoregressive Variational Autoencoder with a Hidden Semi-Markov Model-Based Structured Attention for Speech Synthesis (2022, ICASSP 2022)

Keiichi Tokuda has collaborated with several frequent co-authors, including:

  • Yoshihiko Nankaku
  • Yukiya Hono
  • Kei Hashimoto
  • Keiichiro Oura
  • Shinji Takaki

The collective body of work mainly focuses on advancing speech synthesis and recognition technologies, leveraging structured attention mechanisms, variational autoencoders, and generative models to improve raw waveform processing and multilingual text-to-speech systems.

Best Publications

  • Statistical Parametric Speech Synthesis

    A.W. Black;H. Zen;K. Tokuda

  • Speech parameter generation algorithms for HMM-based speech synthesis

    K. Tokuda;T. Yoshimura;T. Masuko;T. Kobayashi

  • Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory

    T. Toda;A.W. Black;K. Tokuda

  • Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis

    Takayoshi Yoshimura;Keiichi Tokuda;Takashi Masuko;Takao Kobayashi

  • The HMM-based speech synthesis system (HTS) version 2.0.

    Heiga Zen;Takashi Nose;Junichi Yamagishi;Shinji Sako

  • A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis

    Tomoki Toda;Keiichi Tokuda

  • Speech Synthesis Based on Hidden Markov Models

    K. Tokuda;Y. Nankaku;T. Toda;H. Zen

  • Speech parameter generation algorithm considering global variance for HMM-based speech synthesis

    Tomoki Toda;Keiichi Tokuda

  • AN HMM-BASED SPEECH SYNTHESIS SYSTEM APPLIED TO ENGLISH

    Keiichi Tokuda;Heiga Zen;Alan W. Black

  • An adaptive algorithm for mel-cepstral analysis of speech

    T. Fukada;K. Tokuda;T. Kobayashi;S. Imai

  • Hidden Markov models based on multi-space probability distribution for pitch pattern modeling

    K. Tokuda;T. Masuko;N. Miyazaki;T. Kobayashi

  • Speech parameter generation from HMM using dynamic features

    K. Tokuda;T. Kobayashi;S. Imai

  • Mel-generalized cepstral analysis - a unified approach to speech spectral estimation.

    Keiichi Tokuda;Takao Kobayashi;Takashi Masuko;Satoshi Imai

  • Multi-Space Probability Distribution HMM

    Keiichi Tokuda;Takashi Masuko;Noboru Miyazaki;Takao Kobayashi

  • A Hidden Semi-Markov Model-Based Speech Synthesis System

    Heiga Zen;Keiichi Tokuda;Takashi Masuko;Takao Kobayasih

  • Speech synthesis using HMMs with dynamic features

    T. Masuko;K. Tokuda;T. Kobayashi;S. Imai

  • Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005

    Heiga Zen;Tomoki Toda;Masaru Nakamura;Keiichi Tokuda

  • Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model

    Tomoki Toda;Alan W. Black;Keiichi Tokuda

  • Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

    J. Yamagishi;T. Nose;H. Zen;Zhen-Hua Ling

  • The Blizzard Challenge - 2005: Evaluating corpus-based speech synthesis on common datasets

    Alan W. Black;Keiichi Tokuda

  • Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2009

    Junichi Yamagishi;B. Usabaev;Simon King;Oliver Watts

Frequent Co-Authors

Takao Kobayashi
Takao Kobayashi Tokyo Institute of Technology
Heiga Zen
Heiga Zen Google (United States)
Takashi Masuko
Takashi Masuko Preferred Networks, Inc.
Tomoki Toda
Tomoki Toda Nagoya University
Junichi Yamagishi
Junichi Yamagishi National Institute of Informatics
Alan W. Black
Alan W. Black Carnegie Mellon University
Satoshi Nakamura
Satoshi Nakamura Nara Institute of Science and Technology
Mikko Kurimo
Mikko Kurimo Aalto University
Shigeki Sagayama
Shigeki Sagayama University of Tokyo
William Byrne
William Byrne University of Cambridge

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online study options in Computer Science opens up flexible and affordable pathways to advance your career. Many students consider pursuing an online MBA cheap to gain essential business and management skills alongside their technical expertise. This combination can boost your chances for leadership roles within tech industries.

If you're seeking a quicker route to a graduate credential, a 1 year masters degree online provides a fast track for upskilling without a long-term commitment. These programs are popular among those aiming to switch careers or enhance their qualifications rapidly.

Online education now offers a variety of online degrees that pay well, particularly in the tech and information sectors. Fields such as data science, software development, and information security offer strong job prospects and high earning potential.

AI is another area gaining momentum, and finding the best online ai degrees can help you break into cutting-edge careers. Affordable, quality programs provide the skills needed for roles in automation, machine learning, and AI development.

Best Scientists Citing Keiichi Tokuda

Trending Scientists

Recently Published Articles