178 citations · 496 across the 34 of their papers we have counts for
34 papers
iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
The inverse short-time Fourier transform network (iSTFTNet) has garnered attention owing to its fast, lightweight, and high-fidelity speech synthesis. It obtains these characterist…
Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quali…
DisC-VC: Disentangled and F0-Controllable Neural Voice Conversion
Chihiro Watanabe, Hirokazu Kameoka
Voice conversion is a task to convert a non-linguistic feature of a given utterance. Since naturalness of speech strongly depends on its pitch pattern, in some applications, it wou…
Speak Like a Dog: Human to Non-human creature Voice Conversion
Kohei Suzuki, Shoki Sakamoto, Tadahiro Taniguchi +1
This paper proposes a new voice conversion (VC) task from human speech to dog-like speech while preserving linguistic information as an example of human to non-human creature voice…
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka +1
In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vo…
FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures
Li Li, Hirokazu Kameoka, Shoji Makino
This paper proposes a new source model and training scheme to improve the accuracy and speed of the multichannel variational autoencoder (MVAE) method. The MVAE method is a recentl…
StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
Shoki Sakamoto, Akira Taniguchi, Tadahiro Taniguchi +1
Preserving the linguistic content of input speech is essential during voice conversion (VC). The star generative adversarial network-based VC method (StarGAN-VC) is a recently deve…
FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
This paper proposes a non-autoregressive extension of our previously proposed sequence-to-sequence (S2S) model-based voice conversion (VC) methods. S2S model-based VC methods have…
StarGAN-based Emotional Voice Conversion for Japanese Phrases
Asuka Moritani, Ryo Ozaki, Shoki Sakamoto +2
This paper shows that StarGAN-VC, a spectral envelope transformation method for non-parallel many-to-many voice conversion (VC), is capable of emotional VC (EVC). Although StarGAN-…
MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
Non-parallel voice conversion (VC) is a technique for training voice converters without a parallel corpus. Cycle-consistent adversarial network-based VCs (CycleGAN-VC and CycleGAN-…
CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial n…
VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka +2
In this paper, we propose a non-parallel any-to-many voice conversion (VC) method termed VoiceGrad. Inspired by WaveGrad, a recently introduced novel waveform generation method, Vo…
X-DC: Explainable Deep Clustering based on Learnable Spectrogram Templates
Chihiro Watanabe, Hirokazu Kameoka
Deep neural networks (DNNs) have achieved substantial predictive performance in various speech processing tasks. Particularly, it has been shown that a monaural speech separation t…
Pretraining Techniques for Sequence-to-Sequence Voice Conversion
Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu +2
Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can su…
Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks
Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka +1
We previously proposed a method that allows for nonparallel voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of…
Many-to-Many Voice Transformer Network
Hirokazu Kameoka, Wen-Chin Huang, Kou Tanaka +3
This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which enables simultaneous conversion of the voice characteristics, pit…
Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining
Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu +2
We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are a…
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Xin Wang, Junichi Yamagishi, Massimiliano Todisco +37
Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is v…
StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
Non-parallel multi-domain voice conversion (VC) is a technique for learning mappings among multiple domains without relying on parallel data. This is important but challenging owin…
CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been…
Crossmodal Voice Conversion
Hirokazu Kameoka, Kou Tanaka, Aaron Valero Puche +2
Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop…
WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation
Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko +1
WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference wi…
Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform
Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi
Recently, we proposed short-time Fourier transform (STFT)-based loss functions for training a neural speech waveform model. In this paper, we generalize the above framework and pro…
Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier
Li Li, Hirokazu Kameoka, Shoji Makino
This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in…