Shinji Takaki

发表

Complex-Valued Restricted Boltzmann Machine for Direct Learning of Frequency Spectra

Junichi Yamagishi, Toru Nakashika, Shinji Takaki, 2017, INTERSPEECH.

Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Rakugo speech synthesis using segment-to-segment neural transduction and style tokens — toward speech synthesis for entertaining audiences

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2019 .

Investigation of Using Continuous Representation of Various Linguistic Units in Neural Network Based Text-to-Speech Synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2016, IEICE Trans. Inf. Syst..

Does the Lombard Effect Improve Emotional Communication in Noise? - Analysis of Emotional Speech Acted in Noise -

Junichi Yamagishi, Yi Zhao, Shinji Takaki, 2019, INTERSPEECH.

Generative Adversarial Network-Based Postfilter for STFT Spectrograms

Hirokazu Kameoka, Takuhiro Kaneko, Junichi Yamagishi, 2017, INTERSPEECH.

STFT Spectral Loss for Training a Neural Speech Waveform Model

Xin Wang, Junichi Yamagishi, Toru Nakashika, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks

Junichi Yamagishi, Cassia Valentini-Botinhao, Xin Wang, 2016, INTERSPEECH.

Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model pdf

Junichi Yamagishi, Gustav Eje Henter, Xin Wang, 2019, ArXiv.

Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech

Junichi Yamagishi, Cassia Valentini-Botinhao, Xin Wang, 2016, SSW.

Modeling of Rakugo Speech and Its Limitations: Toward Speech Synthesis That Entertains Audiences

Junichi Yamagishi, Xin Wang, Shinji Takaki, 2019, IEEE Access.

Investigating very deep highway networks for parametric speech synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2018, Speech Commun..

Speaker Adaptation of Various Components in Deep Neural Network based Speech Synthesis

Junichi Yamagishi, Shinji Takaki, SangJin Kim, 2016, SSW.

Semi-Supervised Learning Based on Hierarchical Generative Models for End-to-End Speech Synthesis

Yoshihiko Nankaku, Kei Hashimoto, Shinji Takaki, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Comparison of Recent Waveform Generation and Acoustic Modeling Methods for Neural-Network-Based Speech Synthesis

Lauri Juvela, Junichi Yamagishi, Xin Wang, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Proceedings of 9th ISCA Speech Synthesis Workshop

Junichi Yamagishi, Xin Wang, Shinji Takaki, 2016 .

CONTEXTUAL ADDITIVE STRUCTURES IN HMM-BASED SPEECH SYNTHESIS

Shinji Takaki, シンジタカキ, 高木信二, 2014 .

Autoregressive Neural F0 Model for Statistical Parametric Speech Synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Enhance the Word Vector with Prosodic Information for the Recurrent Neural Network Based TTS System

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2016, INTERSPEECH.

Deep Denoising Auto-encoder for Statistical Speech Synthesis pdf

Junichi Yamagishi, Shinji Takaki, Zhenzhou Wu, 2015, ArXiv.

An autoregressive recurrent mixture density network for parametric speech synthesis

Junichi Yamagishi, Shinji Takaki, Xin Wang, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Separable lattice 2-D HMMS introducing state duration control for recognition of images with various variations

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

A Comparative Study of the Performance of HMM, DNN, and RNN based Speech Synthesis Systems Trained on Very Large Speaker-Dependent Corpora

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2016, SSW.

A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural $F_0$ Model for Statistical Parametric Speech Synthesis

Simon King, Junichi Yamagishi, Shinji Takaki, 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Neural Source-filter-based Waveform Model for Statistical Parametric Speech Synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Contextual Additive Structure for HMM-Based Speech Synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2014, IEEE Journal of Selected Topics in Signal Processing.

A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis

Junichi Yamagishi, Shinji Takaki, J. Yamagishi, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Investigation of Enhanced Tacotron Text-to-speech Synthesis Systems with Self-attention for Pitch Accent Language

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Contextual partial additive structure for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Autoregressive quantized F0 modeling using a recurrent neural network with feedback links (音声)

Junichi Yamagishi, Xin Wang, Shinji Takaki, 2017 .

Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes

Junichi Yamagishi, Yoshikazu Nishimura, Shinji Takaki, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra

Junichi Yamagishi, Toru Nakashika, Shinji Takaki, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech

Xin Wang, Cassia Valentini-Botinhao, Shinji Takaki, 2016 .

Multiple feed-forward deep neural networks for statistical parametric speech synthesis

Junichi Yamagishi, Shinji Takaki, SangJin Kim, 2015, INTERSPEECH.

Wasserstein GAN and Waveform Loss-Based Acoustic Model Training for Multi-Speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder

Nobuaki Minematsu, Yi Zhao, Junichi Yamagishi, 2018, IEEE Access.

A Function-wise Pre-training Technique for Constructing a Deep Neural Network based Spectral Model in Statistical Parametric Speech Synthesis

Zhizheng Wu, Junichi Yamagishi, Shinji Takaki, 2015 .

Constructing a Deep Neural Network Based Spectral Model for Statistical Speech Synthesis

Shinji Takaki, Junichi Yamagishi, 2016, Recent Advances in Nonlinear Speech Processing.

Complex-Valued Restricted Boltzmann Machine for Direct Speech Parameterization from Complex Spectra pdf

Junichi Yamagishi, Toru Nakashika, Shinji Takaki, 2018, ArXiv.

International Conference on NONLINEAR SPEECH PROCESSING 2015

Junichi Yamagishi, Shinji Takaki, 2015 .

9th ISCA Speech Synthesis Workshop

Junichi Yamagishi, Shinji Takaki, Xin Wang, 2016 .

An RNN-Based Quantized F0 Model with Multi-Tier Feedback Links for Text-to-Speech Synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2017, INTERSPEECH.

Adapting and controlling DNN-based speech synthesis using input codes

Junichi Yamagishi, Gustav Eje Henter, Shinji Takaki, 2017, ICASSP.

Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform pdf

Hirokazu Kameoka, Junichi Yamagishi, Shinji Takaki, 2019, ArXiv.

Direct Modeling of Frequency Spectra and Waveform Generation Based on Phase Recovery for DNN-Based Speech Synthesis

Hirokazu Kameoka, Junichi Yamagishi, Shinji Takaki, 2017, INTERSPEECH.

Using Text and Acoustic Features in Predicting Glottal Excitation Waveforms for Parametric Speech Synthesis with Recurrent Neural Networks

Lauri Juvela, Paavo Alku, Xin Wang, 2016, INTERSPEECH.

Spectral modeling with contextual additive structure for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2010, SSW.

Investigating different representations for modeling and controlling multiple emotions in DNN-based speech synthesis

Junichi Yamagishi, Gustav Eje Henter, Shinji Takaki, 2018, Speech Commun..

The NII speech synthesis entry for Blizzard Challenge 2016

Lauri Juvela, Xin Wang, Junichi Yamagishi, 2016 .

Bidirectional Voice Conversion Based on Joint Training Using Gaussian-Gaussian Deep Relational Model

Toru Nakashika, Shinji Takaki, Kentaro Sone, 2018, Odyssey.

Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Characteristics of Polyphonic Music Style and Markov Model of Pitch-Class Intervals

Eita Nakamura, Shinji Takaki, Shinji Takaki, 2015, MCM.

Investigating Very Deep Highway Networks for Parametric Speech Synthesis

Xin Wang, Junichi Yamagishi, Shinji Takaki, 2016, SSW.

PeriodNet: A Non-Autoregressive Raw Waveform Generative Model With a Structure Separating Periodic and Aperiodic Components

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, IEEE Access.

Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, 2108.13985.

Periodnet: A Non-Autoregressive Waveform Generation Model with a Structure Separating Periodic and Aperiodic Components

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).