Takuhiro Kaneko

104 papers A* 12A 15B 2Misc 10Journal 52Unranked 13

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flows. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2025	A	`conf`	FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2025	J	`jnl`	FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2025	J	`jnl`	IPCD: Intrinsic Point-Cloud Decomposition. CoRR Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda, Tomoyasu Shimada, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida, Akisato Kimura
2025	A	`conf`	JIS: A Speech Corpus of Japanese Idol Speakers with Various Speaking Styles. INTERSPEECH Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2025	J	`jnl`	JIS: A Speech Corpus of Japanese Idol Speakers with Various Speaking Styles. CoRR Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2025	J	`jnl`	LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models. CoRR Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Yuto Kondo
2025	J	`jnl`	Learning to assess subjective impressions from speech. CoRR Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Noboru Harada
2025	J	`jnl`	Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept. CoRR Shogo Sato, Masaru Tsuchida, Mariko Yamaguchi, Takuhiro Kaneko, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida
2025	J	`jnl`	Rethinking Mean Opinion Scores in Speech Quality Assessment: Aggregation through Quantized Distribution Fitting. CoRR Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2025	Misc	`conf`	Rethinking Mean Opinion Scores in Speech Quality Assessment: Score Aggregation through Quantized Distribution Fitting. ICASSP Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2025	J	`jnl`	Selecting N-lowest scores for training MOS prediction models. CoRR Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2025	A*	`conf`	Structure from Collision. CVPR Takuhiro Kaneko
2025	J	`jnl`	Structure from Collision. CoRR Takuhiro Kaneko
2025	A	`conf`	Unsupervised Single-Image Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training. WACV Shogo Sato, Takuhiro Kaneko, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida, Akisato Kimura
2025	A	`conf`	Vocoder-Projected Feature Discriminator. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2025	J	`jnl`	Vocoder-Projected Feature Discriminator. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2024	A	`conf`	FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2024	J	`jnl`	FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
2024	A*	`conf`	Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization. CVPR Takuhiro Kaneko
2024	J	`jnl`	Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization. CoRR Takuhiro Kaneko
2024	—	`conf`	Learning to Assess Subjective Impressions from Speech. EUSIPCO Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Noboru Harada
2024	A	`conf`	PRVAE-VC2: Non-Parallel Voice Conversion by Distillation of Speech Representations. INTERSPEECH Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Yuto Kondo
2024	Misc	`conf`	Selecting N-Lowest Scores for Training MOS Prediction Models. ICASSP Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2024	Misc	`conf`	Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator. ICASSP Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka
2024	J	`jnl`	Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka
2024	J	`jnl`	Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training. CoRR Shogo Sato, Takuhiro Kaneko, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida, Akisato Kimura
2024	J	`jnl`	VoiceGrad: Non-Parallel Any-to-Many Voice Conversion With Annealed Langevin Dynamics. IEEE ACM Trans. Audio Speech Lang. Process. Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Shogo Seki
2023	A	`conf`	CFVC: Conditional Filtering for Controllable Voice Conversion. INTERSPEECH Kou Tanaka, Takuhiro Kaneko, Hirokazu Kameoka, Shogo Seki
2023	B	`conf`	Frame-Level Event Representation Learning for Semantic-Level Generation and Editing of Avatar Motion. ICMI Ayaka Ideno, Takuhiro Kaneko, Tatsuya Harada
2023	Misc	`conf`	JSV-VC: Jointly Trained Speaker Verification and Voice Conversion Models. ICASSP Shogo Seki, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2023	A*	`conf`	MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fields. ICCV Takuhiro Kaneko
2023	J	`jnl`	MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fields. CoRR Takuhiro Kaneko
2023	J	`jnl`	Non-Parallel Whisper-to-Normal Speaking Style Conversion Using Auxiliary Classifier Variational Autoencoder. IEEE Access Shogo Seki, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka
2023	—	`conf`	PRVAE-VC: Non-Parallel Many-to-Many Voice Conversion with Perturbation-Resistant Variational Autoencoder. SSW Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko
2023	A*	`conf`	Unsupervised Intrinsic Image Decomposition with LiDAR Intensity. CVPR Shogo Sato, Yasuhiro Yao, Taiga Yoshida, Takuhiro Kaneko, Shingo Ando, Jun Shimamura
2023	J	`jnl`	Unsupervised Intrinsic Image Decomposition with LiDAR Intensity. CoRR Shogo Sato, Yasuhiro Yao, Taiga Yoshida, Takuhiro Kaneko, Shingo Ando, Jun Shimamura
2023	—	`conf`	W2N-AVSC: Audiovisual Extension For Whisper-To-Normal Speech Conversion. EUSIPCO Shogo Seki, Kanami Imamura, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Noboru Harada
2023	Misc	`conf`	Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis. ICASSP Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
2023	J	`jnl`	Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
2023	A	`conf`	iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
2023	J	`jnl`	iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
2022	A*	`conf`	AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields. CVPR Takuhiro Kaneko
2022	J	`jnl`	AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields. CoRR Takuhiro Kaneko
2022	A	`conf`	CAUSE: Crossmodal Action Unit Sequence Estimation from Speech. INTERSPEECH Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki, Kou Tanaka
2022	—	`conf`	Distilling Sequence-to-Sequence Voice Conversion Models for Streaming Conversion Applications. SLT Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki
2022	Misc	`conf`	ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform. ICASSP Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka, Shogo Seki
2022	A	`conf`	MISRNet: Lightweight Neural Vocoder Using Multi-Input Single Shared Residual Blocks. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
2022	J	`jnl`	iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform. CoRR Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka, Shogo Seki
2021	A*	`conf`	Blur, Noise, and Compression Robust Generative Adversarial Networks. CVPR Takuhiro Kaneko, Tatsuya Harada
2021	J	`jnl`	FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion. CoRR Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2021	J	`jnl`	Many-to-Many Voice Transformer Network. IEEE ACM Trans. Audio Speech Lang. Process. Hirokazu Kameoka, Wen-Chin Huang, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Tomoki Toda
2021	J	`jnl`	MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2021	Misc	`conf`	Maskcyclegan-VC: Learning Non-Parallel Voice Conversion with Filling in Frames. ICASSP Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2021	A*	`conf`	Unsupervised Learning of Depth and Depth-of-Field Effect From Natural Images With Aperture Rendering Generative Adversarial Networks. CVPR Takuhiro Kaneko
2021	J	`jnl`	Unsupervised Learning of Depth and Depth-of-Field Effect from Natural Images with Aperture Rendering Generative Adversarial Networks. CoRR Takuhiro Kaneko
2020	J	`jnl`	Blur, Noise, and Compression Robust Generative Adversarial Networks. CoRR Takuhiro Kaneko, Tatsuya Harada
2020	J	`jnl`	ConvS2S-VC: Fully Convolutional Sequence-to-Sequence Voice Conversion. IEEE ACM Trans. Audio Speech Lang. Process. Hirokazu Kameoka, Kou Tanaka, Damian Kwasny, Takuhiro Kaneko, Nobukatsu Hojo
2020	A	`conf`	CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-Spectrogram Conversion. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2020	J	`jnl`	CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2020	J	`jnl`	Many-to-Many Voice Transformer Network. CoRR Hirokazu Kameoka, Wen-Chin Huang, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Tomoki Toda
2020	A*	`conf`	Noise Robust Generative Adversarial Networks. CVPR Takuhiro Kaneko, Tatsuya Harada
2020	J	`jnl`	Nonparallel Voice Conversion With Augmented Classifier Star Generative Adversarial Networks. IEEE ACM Trans. Audio Speech Lang. Process. Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo
2020	J	`jnl`	VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics. CoRR Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Shogo Seki
2019	J	`jnl`	ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder. IEEE ACM Trans. Audio Speech Lang. Process. Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo
2019	Misc	`conf`	ATTS2S-VC: Sequence-to-sequence Voice Conversion with Attention and Context Preservation Mechanisms. ICASSP Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo
2019	A	`conf`	Class-Distinct and Class-Mutual Image Generation with GANs. BMVC Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada
2019	J	`jnl`	Crossmodal Voice Conversion. CoRR Hirokazu Kameoka, Kou Tanaka, Aaron Valero Puche, Yasunori Ohishi, Takuhiro Kaneko
2019	J	`jnl`	CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2019	Misc	`conf`	Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion. ICASSP Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2019	A*	`conf`	Label-Noise Robust Generative Adversarial Networks. CVPR Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada
2019	J	`jnl`	Label-Noise Robust Multi-Domain Image-to-Image Translation. CoRR Takuhiro Kaneko, Tatsuya Harada
2019	J	`jnl`	Noise Robust Generative Adversarial Networks. CoRR Takuhiro Kaneko, Tatsuya Harada
2019	A	`conf`	StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2019	J	`jnl`	StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion. CoRR Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo
2019	J	`jnl`	WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation. CoRR Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo
2018	J	`jnl`	ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder. CoRR Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo
2018	J	`jnl`	AttS2S-VC: Sequence-to-Sequence Voice Conversion with Attention and Context Preservation Mechanisms. CoRR Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo
2018	—	`conf`	Automatic Speech Pronunciation Correction with Dynamic Frequency Warping-Based Spectral Conversion. EUSIPCO Nobukatsu Hojo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
2018	J	`jnl`	Class-Distinct and Class-Mutual Image Generation with GANs. CoRR Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada
2018	J	`jnl`	ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion. CoRR Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo
2018	—	`conf`	CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks. EUSIPCO Takuhiro Kaneko, Hirokazu Kameoka
2018	A*	`conf`	Generative Adversarial Image Synthesis With Decision Tree Latent Controller. CVPR Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino
2018	J	`jnl`	Generative Adversarial Image Synthesis with Decision Tree Latent Controller. CoRR Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino
2018	—	`conf`	Generative adversarial network-based approach to signal reconstruction from magnitude spectrogram. EUSIPCO Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando
2018	J	`jnl`	Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms. CoRR Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando
2018	J	`jnl`	Label-Noise Robust Generative Adversarial Networks. CoRR Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada
2018	J	`jnl`	StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks. CoRR Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo
2018	—	`conf`	StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks. SLT Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo
2018	—	`conf`	Synthetic-to-Natural Speech Waveform Conversion Using Cycle-Consistent Adversarial Networks. SLT Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Hirokazu Kameoka
2018	J	`jnl`	WaveCycleGAN: Synthetic-to-natural speech waveform conversion using cycle-consistent adversarial networks. CoRR Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Hirokazu Kameoka
2017	A	`conf`	Generative Adversarial Network-Based Postfilter for STFT Spectrograms. INTERSPEECH Takuhiro Kaneko, Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi
2017	A*	`conf`	Generative Attribute Controller with Conditional Filtered Generative Adversarial Networks. CVPR Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino
2017	Misc	`conf`	Generative adversarial network-based postfilter for statistical parametric speech synthesis. ICASSP Takuhiro Kaneko, Hirokazu Kameoka, Nobukatsu Hojo, Yusuke Ijima, Kaoru Hiramatsu, Kunio Kashino
2017	—	`conf`	Non-native speech conversion with consistency-aware recursive network and generative adversarial network. APSIPA Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Hiroyasu Ando, Kaoru Hiramatsu, Kunio Kashino
2017	J	`jnl`	Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks. CoRR Takuhiro Kaneko, Hirokazu Kameoka
2017	A	`conf`	Sequence-to-Sequence Voice Conversion with Similarity Metric Learned Using Generative Adversarial Networks. INTERSPEECH Takuhiro Kaneko, Hirokazu Kameoka, Kaoru Hiramatsu, Kunio Kashino
2016	A*	`conf`	Adaptive Visual Feedback Generation for Facial Expression Improvement with Multi-task Deep Neural Networks. ACM Multimedia Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino
2016	J	`jnl`	Collective activity localization by spatiality preservation search. Adv. Robotics Shigeyuki Odashima, Masamichi Shimosaka, Takuhiro Kaneko, Rui Fukui, Tomomasa Sato
2014	J	`jnl`	A fully connected model for consistent collective activity recognition in videos. Pattern Recognit. Lett. Takuhiro Kaneko, Masamichi Shimosaka, Shigeyuki Odashima, Rui Fukui, Tomomasa Sato
2014	—	`conf`	Modeling risk anticipation and defensive driving on residential roads with inverse reinforcement learning. ITSC Masamichi Shimosaka, Takuhiro Kaneko, Kentaro Nishi
2012	—	`conf`	Collective Activity Localization with Contextual Spatial Pyramid. ECCV Workshops (3) Shigeyuki Odashima, Masamichi Shimosaka, Takuhiro Kaneko, Rui Fukui, Tomomasa Sato
2012	B	`conf`	Consistent collective activity recognition with fully connected CRFs. ICPR Takuhiro Kaneko, Masamichi Shimosaka, Shigeyuki Odashima, Rui Fukui, Tomomasa Sato
2012	—	`conf`	Viewpoint Invariant Collective Activity Recognition with Relative Action Context. ECCV Workshops (3) Takuhiro Kaneko, Masamichi Shimosaka, Shigeyuki Odashima, Rui Fukui, Tomomasa Sato