Takuma Okamoto

59 papers A 7C 7Misc 15Journal 19Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	GST-BERT-TTS: Prosody Prediction Without Accentual Labels For Multi-Speaker TTS Using BERT With Global Style Tokens. INTERSPEECH Tadashi Ogura, Takuma Okamoto, Yamato Ohtani, Erica Cooper, Tomoki Toda, Hisashi Kawai
2025	C	`conf`	Layer-wise Analysis for Quality of Multilingual Synthesized Speech. ASRU Erica Cooper, Takuma Okamoto, Yamato Ohtani, Tomoki Toda, Hisashi Kawai
2025	J	`jnl`	Layer-wise Analysis for Quality of Multilingual Synthesized Speech. CoRR Erica Cooper, Takuma Okamoto, Yamato Ohtani, Tomoki Toda, Hisashi Kawai
2025	Misc	`conf`	Mora-Level Prosody Prediction for Text-to-Speech Using Japanese BERT Without Accentual Labels. ICASSP Tadashi Ogura, Takuma Okamoto, Yamato Ohtani, Erica Cooper, Tomoki Toda, Hisashi Kawai
2025	J	`jnl`	Phoneme-Level Duration Controllable Neural Text-to-Speech With Phoneme Embedding Skip Connection and Modified Gaussian Duration Modeling. IEEE Access Tadashi Ogura, Takuma Okamoto, Yamato Ohtani, Erica Cooper, Tomoki Toda, Hisashi Kawai
2025	—	`conf`	SFC-L1: Sound Field Control With Least Absolute Deviation Regression. WASPAA Takuma Okamoto
2025	J	`jnl`	Sequence-to-Sequence Voice Conversion With Weighted Guided Attention. IEEE Access Haruki Yamashita, Takuma Okamoto, Ryoichi Takashima, Yamato Ohtani, Tetsuya Takiguchi, Tomoki Toda, Hisashi Kawai
2025	A	`conf`	Simultaneous Speech Translation Integrated Compact Multiple Sound Spot Synthesis System On A Laptop Carried Out With A Backpack. INTERSPEECH Takuma Okamoto, Michiyo Kono
2025	C	`conf`	Speech Masking System Based on Spatially Separated Multiple TTS Maskers With A Compact Circular Loudspeaker Array. ASRU Takuma Okamoto
2025	C	`conf`	Voice Factor Control Using FIR-Based Fast Neural Vocoder for Speech Generation Applications. ASRU Yamato Ohtani, Takuma Okamoto, Tomoki Toda, Hisashi Kawai
2024	A	`conf`	Challenge of Singing Voice Synthesis Using Only Text-To-Speech Corpus With FIRNet Source-Filter Neural Vocoder. INTERSPEECH Takuma Okamoto, Yamato Ohtani, Sota Shimizu, Tomoki Toda, Hisashi Kawai
2024	Misc	`conf`	Convnext-TTS And Convnext-VC: Convnext-Based Fast End-To-End Sequence-To-Sequence Text-To-Speech And Voice Conversion. ICASSP Takuma Okamoto, Yamato Ohtani, Tomoki Toda, Hisashi Kawai
2024	Misc	`conf`	FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter. ICASSP Yamato Ohtani, Takuma Okamoto, Tomoki Toda, Hisashi Kawai
2024	J	`jnl`	Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling. IEEE Access Haruki Yamashita, Takuma Okamoto, Ryoichi Takashima, Yamato Ohtani, Tetsuya Takiguchi, Tomoki Toda, Hisashi Kawai
2024	A	`conf`	Mobile PresenTra: NICT fast neural text-to-speech system on smartphones with incremental inference of MS-FC-HiFi-GAN for law-latency synthesis. INTERSPEECH Takuma Okamoto, Yamato Ohtani, Hisashi Kawai
2023	Misc	`conf`	Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder. ICASSP Ryota Komatsu, Yusuke Kimura, Takuma Okamoto, Takahiro Shinozaki
2023	A	`conf`	E2E-S2S-VC: End-To-End Sequence-To-Sequence Voice Conversion. INTERSPEECH Takuma Okamoto, Tomoki Toda, Hisashi Kawai
2023	J	`jnl`	Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder. IEEE ACM Trans. Audio Speech Lang. Process. Keisuke Matsubara, Takuma Okamoto, Ryoichi Takashima, Tetsuya Takiguchi, Tomoki Toda, Hisashi Kawai
2023	C	`conf`	WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer. ASRU Takuma Okamoto, Haruki Yamashita, Yamato Ohtani, Tomoki Toda, Hisashi Kawai
2022	J	`jnl`	Automatic Spoken Language Acquisition Based on Observation and Dialogue. IEEE J. Sel. Top. Signal Process. Ryota Komatsu, Shengzhou Gao, Wenxin Hou, Mingxin Zhang, Tomohiro Tanaka, Keisuke Toyoda, Yusuke Kimura, Kent Hino, Yu Iwamoto, Kosuke Mori, Takuma Okamoto, Takahiro Shinozaki
2022	J	`jnl`	Neural speech-rate conversion with multispeaker WaveNet vocoder. Speech Commun. Takuma Okamoto, Keisuke Matsubara, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2022	J	`jnl`	Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation. CoRR Detai Xin, Shinnosuke Takamichi, Takuma Okamoto, Hisashi Kawai, Hiroshi Saruwatari
2021	—	`conf`	2D Multizone Sound Field Synthesis with Interior-Exterior Ambisonics. WASPAA Takuma Okamoto
2021	Misc	`conf`	Close-Talking Recording with Planarly Distributed Microphones. ICASSP Takuma Okamoto
2021	J	`jnl`	Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU. IEEE Access Keisuke Matsubara, Takuma Okamoto, Ryoichi Takashima, Tetsuya Takiguchi, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2021	Misc	`conf`	High-Intelligibility Speech Synthesis for Dysarthric Speakers with LPCNet-Based TTS and CycleVAE-Based VC. ICASSP Keisuke Matsubara, Takuma Okamoto, Ryoichi Takashima, Tetsuya Takiguchi, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2021	C	`conf`	Multi-Stream HiFi-GAN with Data-Driven Waveform Decomposition. ASRU Takuma Okamoto, Tomoki Toda, Hisashi Kawai
2021	Misc	`conf`	Noise Level Limited Sub-Modeling for Diffusion Probabilistic Vocoders. ICASSP Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2021	J	`jnl`	Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network. IEEE ACM Trans. Audio Speech Lang. Process. Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda
2020	A	`conf`	Quasi-Periodic Parallel WaveGAN Vocoder: A Non-Autoregressive Pitch-Dependent Dilated Convolution Model for Parametric Speech Generation. INTERSPEECH Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda
2020	J	`jnl`	Quasi-Periodic Parallel WaveGAN Vocoder: A Non-autoregressive Pitch-dependent Dilated Convolution Model for Parametric Speech Generation. CoRR Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda
2020	J	`jnl`	Quasi-Periodic Parallel WaveGAN: A Non-autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Network. CoRR Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda
2020	—	`ch.`	Text-to-Speech Synthesis. Speech-to-Speech Translation Yoshinori Shiga, Jinfu Ni, Kentaro Tachibana, Takuma Okamoto
2020	Misc	`conf`	Transformer-Based Text-to-Speech with Weighted Forced Attention. ICASSP Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2019	—	`conf`	3D Localized Sound Zone Generation with a Planar Omni-Directional Loudspeaker Array. WASPAA Takuma Okamoto
2019	Misc	`conf`	Horizontal 3D Sound Field Recording and 2.5D Synthesis with Omni-directional Circular Arrays. ICASSP Takuma Okamoto
2019	Misc	`conf`	Investigations of Real-time Gaussian Fftnet and Parallel Wavenet Neural Vocoders with Simple Acoustic Features. ICASSP Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2019	A	`conf`	Real-Time Neural Text-to-Speech with Sequence-to-Sequence Acoustic Model and WaveGlow or Single Gaussian WaveRNN Vocoders. INTERSPEECH Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2019	C	`conf`	Tacotron-Based Acoustic Model Using Phoneme Alignment for Practical Neural Text-to-Speech Systems. ASRU Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2018	—	`conf`	2.5D Localized Sound Zone Generation with a Circular Array of Fixed-Directivity Loudspeakers. IWAENC Takuma Okamoto
2018	Misc	`conf`	An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features. ICASSP Takuma Okamoto, Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2018	—	`conf`	Improving FFTNet Vocoder with Noise Shaping and Subband Approaches. SLT Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2017	Misc	`conf`	Analytical approach to 2.5D sound field control using a circular double-layer array of fixed-directivity loudspeakers. ICASSP Takuma Okamoto
2017	—	`conf`	Angular spectrum decomposition-based 2.5D higher-order spherical harmonic sound field synthesis with a linear loudspeaker array. WASPAA Takuma Okamoto
2017	J	`jnl`	Development of Wearable Sheet-Type Shear Force Sensor and Measurement System that is Insusceptible to Temperature and Pressure. Sensors Shigeru Toyama, Yasuhiro Tanaka, Satoshi Shirogane, Takashi Nakamura, Tokio Umino, Ryo Uehara, Takuma Okamoto, Hiroshi Igarashi
2017	J	`jnl`	Horizontal Local Sound Field Propagation Based on Sound Source Dimension Mismatch. J. Inf. Hiding Multim. Signal Process. Takuma Okamoto
2017	J	`jnl`	Localized Sound Zone Generation Based on External Radiation Canceller. J. Inf. Hiding Multim. Signal Process. Takuma Okamoto
2017	C	`conf`	Subband wavenet with overlapped single-sideband filterbanks. ASRU Takuma Okamoto, Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
2016	Misc	`conf`	2.5D higher order ambisonics for a sound field described by angular spectrum coefficients. ICASSP Takuma Okamoto
2015	J	`jnl`	A Spatial Extrapolation Method to Derive High-Order Ambisonics Data from Stereo Sources. J. Inf. Hiding Multim. Signal Process. Jorge Treviño, Yôiti Suzuki, Takuma Okamoto, Yukio Iwaya, Junfeng Li
2015	—	`conf`	Analytical methods of generating multiple sound zones for open and baffled circular loudspeaker arrays. WASPAA Takuma Okamoto
2015	Misc	`conf`	Near-field sound propagation based on a circular and linear array combination. ICASSP Takuma Okamoto
2014	Misc	`conf`	Generation of multiple sound zones by spatial filtering in wavenumber domain using a linear array of loudspeakers. ICASSP Takuma Okamoto
2014	J	`jnl`	Sound Field Reproduction Using Ambisonics and Irregular Loudspeaker Arrays. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. Jorge Treviño, Takuma Okamoto, Yukio Iwaya, Yôiti Suzuki
2013	—	`conf`	Extrapolation of Horizontal Ambisonics Data from Mainstream Stereo Sources. IIH-MSP Jorge Treviño, Takuma Okamoto, Yukio Iwaya, Junfeng Li, Yôiti Suzuki
2013	—	`conf`	Morpion Solitaire 5D: a new upper bound 121 on the maximum score. CCCG Akitoshi Kawamura, Takuma Okamoto, Yuichi Tatsu, Yushi Uno, Masahide Yamato
2013	J	`jnl`	Morpion Solitaire 5D: a new upper bound of 121 on the maximum score. CoRR Akitoshi Kawamura, Takuma Okamoto, Yuichi Tatsu, Yushi Uno, Masahide Yamato
2010	—	`conf`	Comparative performance evaluation of near 3D sound field reproduction system with directional loudspeakers and wave field synthesis. IUCS Toshiyuki Kimura, Yoko Yamakata, Michiaki Katsumoto, Takuma Okamoto, Satoshi Yairi, Yukio Iwaya, Yôiti Suzuki
2010	J	`jnl`	Multiple Description Coding Using Time Domain Division for MP3 coded Sound Signal. J. Inf. Hiding Multim. Signal Process. Hoseok Wey, Akinori Ito, Takuma Okamoto, Yôiti Suzuki