Takuma Okamoto

According to our database, Takuma Okamoto authored at least 40 papers between 2010 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder.

Keisuke Matsubara, Takuma Okamoto, Ryoichi Takashima, Tetsuya Takiguchi, Tomoki Toda, Hisashi Kawai

IEEE ACM Trans. Audio Speech Lang. Process., 2023

Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder.

Ryota Komatsu, Yusuke Kimura, Takuma Okamoto, Takahiro Shinozaki

Proceedings of the IEEE International Conference on Acoustics, 2023

WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer.

Takuma Okamoto, Haruki Yamashita, Yamato Ohtani, Tomoki Toda, Hisashi Kawai

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

Neural speech-rate conversion with multispeaker WaveNet vocoder.

Takuma Okamoto, Keisuke Matsubara, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Speech Commun., 2022

Automatic Spoken Language Acquisition Based on Observation and Dialogue.

Ryota Komatsu, Shengzhou Gao, Wenxin Hou, Mingxin Zhang, Tomohiro Tanaka, Keisuke Toyoda, Yusuke Kimura, Kent Hino, Yu Iwamoto, Kosuke Mori, Takuma Okamoto, Takahiro Shinozaki

IEEE J. Sel. Top. Signal Process., 2022

Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation.

Detai Xin, Shinnosuke Takamichi, Takuma Okamoto, Hisashi Kawai, Hiroshi Saruwatari

CoRR, 2022

2021

Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network.

Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda

IEEE ACM Trans. Audio Speech Lang. Process., 2021

Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU.

Keisuke Matsubara, Takuma Okamoto, Ryoichi Takashima, Tetsuya Takiguchi, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

IEEE Access, 2021

2D Multizone Sound Field Synthesis with Interior-Exterior Ambisonics.

Takuma Okamoto

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2021

Noise Level Limited Sub-Modeling for Diffusion Probabilistic Vocoders.

Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the IEEE International Conference on Acoustics, 2021

Close-Talking Recording with Planarly Distributed Microphones.

Takuma Okamoto

Proceedings of the IEEE International Conference on Acoustics, 2021

High-Intelligibility Speech Synthesis for Dysarthric Speakers with LPCNet-Based TTS and CycleVAE-Based VC.

Keisuke Matsubara, Takuma Okamoto, Ryoichi Takashima, Tetsuya Takiguchi, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the IEEE International Conference on Acoustics, 2021

Multi-Stream HiFi-GAN with Data-Driven Waveform Decomposition.

Takuma Okamoto, Tomoki Toda, Hisashi Kawai

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2020

Text-to-Speech Synthesis.

Yoshinori Shiga, Jinfu Ni, Kentaro Tachibana, Takuma Okamoto

Proceedings of the Speech-to-Speech Translation, 2020

Quasi-Periodic Parallel WaveGAN Vocoder: A Non-Autoregressive Pitch-Dependent Dilated Convolution Model for Parametric Speech Generation.

Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda

Proceedings of the Interspeech 2020, 2020

Transformer-Based Text-to-Speech with Weighted Forced Attention.

Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

3D Localized Sound Zone Generation with a Planar Omni-Directional Loudspeaker Array.

Takuma Okamoto

Proceedings of the 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2019

Real-Time Neural Text-to-Speech with Sequence-to-Sequence Acoustic Model and WaveGlow or Single Gaussian WaveRNN Vocoders.

Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the Interspeech 2019, 2019

Investigations of Real-time Gaussian Fftnet and Parallel Wavenet Neural Vocoders with Simple Acoustic Features.

Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the IEEE International Conference on Acoustics, 2019

Horizontal 3D Sound Field Recording and 2.5D Synthesis with Omni-directional Circular Arrays.

Takuma Okamoto

Proceedings of the IEEE International Conference on Acoustics, 2019

Tacotron-Based Acoustic Model Using Phoneme Alignment for Practical Neural Text-to-Speech Systems.

Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Improving FFTNet Vocoder with Noise Shaping and Subband Approaches.

Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

2.5D Localized Sound Zone Generation with a Circular Array of Fixed-Directivity Loudspeakers.

Takuma Okamoto

Proceedings of the 16th International Workshop on Acoustic Signal Enhancement, 2018

An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features.

Takuma Okamoto, Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Development of Wearable Sheet-Type Shear Force Sensor and Measurement System that is Insusceptible to Temperature and Pressure.

Shigeru Toyama, Yasuhiro Tanaka, Satoshi Shirogane, Takashi Nakamura, Tokio Umino, Ryo Uehara, Takuma Okamoto, Hiroshi Igarashi

Sensors, 2017

Localized Sound Zone Generation Based on External Radiation Canceller.

Takuma Okamoto

J. Inf. Hiding Multim. Signal Process., 2017

Horizontal Local Sound Field Propagation Based on Sound Source Dimension Mismatch.

Takuma Okamoto

J. Inf. Hiding Multim. Signal Process., 2017

Angular spectrum decomposition-based 2.5D higher-order spherical harmonic sound field synthesis with a linear loudspeaker array.

Takuma Okamoto

Proceedings of the 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2017

Analytical approach to 2.5D sound field control using a circular double-layer array of fixed-directivity loudspeakers.

Takuma Okamoto

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Subband wavenet with overlapped single-sideband filterbanks.

Takuma Okamoto, Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016

2.5D higher order ambisonics for a sound field described by angular spectrum coefficients.

Takuma Okamoto

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

A Spatial Extrapolation Method to Derive High-Order Ambisonics Data from Stereo Sources.

Jorge Treviño, Yôiti Suzuki, Takuma Okamoto, Yukio Iwaya, Junfeng Li

J. Inf. Hiding Multim. Signal Process., 2015

Analytical methods of generating multiple sound zones for open and baffled circular loudspeaker arrays.

Takuma Okamoto

Proceedings of the 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2015

Near-field sound propagation based on a circular and linear array combination.

Takuma Okamoto

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Sound Field Reproduction Using Ambisonics and Irregular Loudspeaker Arrays.

Jorge Treviño, Takuma Okamoto, Yukio Iwaya, Yôiti Suzuki

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2014

Generation of multiple sound zones by spatial filtering in wavenumber domain using a linear array of loudspeakers.

Takuma Okamoto

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Extrapolation of Horizontal Ambisonics Data from Mainstream Stereo Sources.

Jorge Treviño, Takuma Okamoto, Yukio Iwaya, Junfeng Li, Yôiti Suzuki

Proceedings of the Ninth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2013

Morpion Solitaire 5D: a new upper bound 121 on the maximum score.

Akitoshi Kawamura, Takuma Okamoto, Yuichi Tatsu, Yushi Uno, Masahide Yamato

Proceedings of the 25th Canadian Conference on Computational Geometry, 2013

2010

Multiple Description Coding Using Time Domain Division for MP3 coded Sound Signal.

Hoseok Wey, Akinori Ito, Takuma Okamoto, Yôiti Suzuki

J. Inf. Hiding Multim. Signal Process., 2010

Comparative performance evaluation of near 3D sound field reproduction system with directional loudspeakers and wave field synthesis.

Toshiyuki Kimura, Yoko Yamakata, Michiaki Katsumoto, Takuma Okamoto, Satoshi Yairi, Yukio Iwaya, Yôiti Suzuki

Proceedings of the 4th International Universal Communication Symposium, 2010