Hiroki Kanagawa

18 papers A 5Misc 4Journal 4Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Multi-interaction TTS toward professional recording reproduction. CoRR Hiroki Kanagawa, Kenichi Fujita, Aya Watanabe, Yusuke Ijima
2024	A	`conf`	Knowledge Distillation from Self-Supervised Representation Learning Model with Discrete Speech Units for Any-to-Any Streaming Voice Conversion. INTERSPEECH Hiroki Kanagawa, Yusuke Ijima
2024	Misc	`conf`	Noise-Robust Zero-Shot Text-to-Speech Synthesis Conditioned on Self-Supervised Speech-Representation Model with Adapters. ICASSP Kenichi Fujita, Hiroshi Sato, Takanori Ashihara, Hiroki Kanagawa, Marc Delcroix, Takafumi Moriya, Yusuke Ijima
2024	J	`jnl`	Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters. CoRR Kenichi Fujita, Hiroshi Sato, Takanori Ashihara, Hiroki Kanagawa, Marc Delcroix, Takafumi Moriya, Yusuke Ijima
2024	A	`conf`	Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training. INTERSPEECH Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima
2023	Misc	`conf`	Enhancement of Text-Predicting Style Token With Generative Adversarial Network for Expressive Speech Synthesis. ICASSP Hiroki Kanagawa, Yusuke Ijima
2023	A	`conf`	VC-T: Streaming Voice Conversion Based on Neural Transducer. INTERSPEECH Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima
2023	—	`conf`	Zero-Shot Text-to-Speech Synthesis Conditioned Using Self-Supervised Speech Representation Model. ICASSP Workshops Kenichi Fujita, Takanori Ashihara, Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima
2023	J	`jnl`	Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model. CoRR Kenichi Fujita, Takanori Ashihara, Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima
2022	A	`conf`	Joint Modeling of Multi-Sample and Subband Signals for Fast Neural Vocoding on CPU. INTERSPEECH Hiroki Kanagawa, Yusuke Ijima, Hiroyuki Toda
2022	Misc	`conf`	Multi-Sample Subband Wavernn Via Multivariate Gaussian. ICASSP Hiroki Kanagawa, Yusuke Ijima
2022	—	`conf`	SIMD-Size Aware Weight Regularization for Fast Neural Vocoding on CPU. SLT Hiroki Kanagawa, Yusuke Ijima
2022	J	`jnl`	SIMD-size aware weight regularization for fast neural vocoding on CPU. CoRR Hiroki Kanagawa, Yusuke Ijima
2020	A	`conf`	Lightweight LPCNet-Based Neural Vocoder with Tensor Decomposition. INTERSPEECH Hiroki Kanagawa, Yusuke Ijima
2019	—	`conf`	Multi-Speaker Modeling for DNN-based Speech Synthesis Incorporating Generative Adversarial Networks. SSW Hiroki Kanagawa, Yusuke Ijima
2018	—	`conf`	Efficient Building Strategy with Knowledge Distillation for Small-Footprint Acoustic Models. SLT Takafumi Moriya, Hiroki Kanagawa, Kiyoaki Matsui, Takaaki Fukutomi, Yusuke Shinohara, Yoshikazu Yamaguchi, Manabu Okamoto, Yushi Aono
2015	—	`conf`	Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN. APSIPA Hiroki Kanagawa, Yuuki Tachioka, Shinji Watanabe, Jun Ishii
2013	Misc	`conf`	Speaker-independent style conversion for HMM-based expressive speech synthesis. ICASSP Hiroki Kanagawa, Takashi Nose, Takao Kobayashi