H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 48 Citations 10,198 351 World Ranking 3157 National Ranking 32

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Statistics

Tomoki Toda spends much of his time researching Speech recognition, Speech synthesis, Artificial intelligence, Hidden Markov model and Mixture model. Speech recognition and Naturalness are two areas of study in which Tomoki Toda engages in interdisciplinary work. His studies in Speech synthesis integrate themes in fields like Algorithm, Residual, Speaker recognition and Spoofing attack.

His Artificial intelligence research incorporates elements of Natural language processing, Contrast and Pattern recognition. The concepts of his Hidden Markov model study are interwoven with issues in Covariance, Parametric statistics, Robustness and Active listening. His Mixture model study incorporates themes from Maximum likelihood, Utterance, Spectrum and Natural language.

His most cited work include:

  • Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory (765 citations)
  • A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis (334 citations)
  • Speech Synthesis Based on Hidden Markov Models (273 citations)

What are the main themes of his work throughout his whole career to date?

His primary areas of investigation include Speech recognition, Artificial intelligence, Speech synthesis, Hidden Markov model and Natural language processing. His Speech recognition research is multidisciplinary, incorporating elements of Mixture model and Speech enhancement. His Artificial intelligence study combines topics in areas such as Machine learning and Pattern recognition.

Tomoki Toda performs multidisciplinary study in the fields of Speech synthesis and Naturalness via his papers. Tomoki Toda interconnects Voice analysis and Linear predictive coding in the investigation of issues within Voice activity detection. Tomoki Toda regularly ties together related areas like Microphone in his Speech processing studies.

He most often published in these fields:

  • Speech recognition (72.44%)
  • Artificial intelligence (30.00%)
  • Speech synthesis (25.56%)

What were the highlights of his more recent work (between 2018-2021)?

  • Speech recognition (72.44%)
  • Waveform (9.56%)
  • Speech synthesis (25.56%)

In recent papers he was focusing on the following fields of study:

Tomoki Toda mostly deals with Speech recognition, Waveform, Speech synthesis, Autoencoder and Transformer. In general Speech recognition study, his work on Speech processing and Prosody often relates to the realm of Naturalness, thereby connecting several areas of interest. He works mostly in the field of Waveform, limiting it down to topics relating to Algorithm and, in certain cases, Distribution.

Tomoki Toda focuses mostly in the field of Speech synthesis, narrowing it down to topics relating to Training set and, in certain cases, Test data. His Autoencoder study combines topics from a wide range of disciplines, such as Code and Pattern recognition. His research investigates the connection with Transformer and areas like Recurrent neural network which intersect with concerns in Statistical model.

Between 2018 and 2021, his most popular works were:

  • Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit (51 citations)
  • ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (25 citations)
  • Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining. (24 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Speech recognition
  • Statistics

His main research concerns Speech recognition, Speech synthesis, Artificial intelligence, Speech processing and Transformer. His Speech recognition research includes themes of Recurrent neural network and Convolution. His study explores the link between Speech synthesis and topics such as Acoustic model that cross with problems in Hidden Markov model.

Tomoki Toda has researched Artificial intelligence in several fields, including Code, Active listening and Pattern recognition. Tomoki Toda has included themes like Singing, Natural and Prosody in his Speech processing study. The various areas that Tomoki Toda examines in his Transformer study include Sound quality and Pitch contour.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

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

T. Toda;A.W. Black;K. Tokuda.
IEEE Transactions on Audio, Speech, and Language Processing (2007)

1035 Citations

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

Tomoki Toda;Keiichi Tokuda.
The IEICE transactions on information and systems (2007)

546 Citations

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

Tomoki Toda;Keiichi Tokuda.
conference of the international speech communication association (2005)

544 Citations

Speech Synthesis Based on Hidden Markov Models

K. Tokuda;Y. Nankaku;T. Toda;H. Zen.
Proceedings of the IEEE (2013)

473 Citations

A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis(Speech and Hearing)

Tomoki Toda;Keiichi Tokuda.
IEICE Transactions on Information and Systems (2007)

297 Citations

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

Heiga Zen;Tomoki Toda;Masaru Nakamura;Keiichi Tokuda.
The IEICE transactions on information and systems (2007)

291 Citations

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

Tomoki Toda;Alan W. Black;Keiichi Tokuda.
Speech Communication (2008)

275 Citations

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

J. Yamagishi;T. Nose;H. Zen;Zhen-Hua Ling.
IEEE Transactions on Audio, Speech, and Language Processing (2009)

232 Citations

Speaker-Dependent WaveNet Vocoder.

Akira Tamamori;Tomoki Hayashi;Kazuhiro Kobayashi;Kazuya Takeda.
conference of the international speech communication association (2017)

223 Citations

Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum

T. Toda;H. Saruwatari;K. Shikano.
international conference on acoustics, speech, and signal processing (2001)

212 Citations

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

Contact us

Best Scientists Citing Tomoki Toda

Junichi Yamagishi

Junichi Yamagishi

National Institute of Informatics

Publications: 183

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 100

Simon King

Simon King

University of Edinburgh

Publications: 80

Zhen-Hua Ling

Zhen-Hua Ling

University of Science and Technology of China

Publications: 74

Keiichi Tokuda

Keiichi Tokuda

Nagoya Institute of Technology

Publications: 63

Satoshi Nakamura

Satoshi Nakamura

Nara Institute of Science and Technology

Publications: 58

Alan W. Black

Alan W. Black

Carnegie Mellon University

Publications: 46

Frank K. Soong

Frank K. Soong

Microsoft (United States)

Publications: 39

Heiga Zen

Heiga Zen

Google (United States)

Publications: 36

Graham Neubig

Graham Neubig

Carnegie Mellon University

Publications: 36

Yu Tsao

Yu Tsao

Center for Information Technology

Publications: 35

Hirokazu Kameoka

Hirokazu Kameoka

NTT (Japan)

Publications: 35

Tomi Kinnunen

Tomi Kinnunen

University of Eastern Finland

Publications: 32

Thierry Dutoit

Thierry Dutoit

University of Mons

Publications: 32

Eng Siong Chng

Eng Siong Chng

Nanyang Technological University

Publications: 30

Paavo Alku

Paavo Alku

Aalto University

Publications: 29

Something went wrong. Please try again later.