Heiga Zen

发表

Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, IEICE Trans. Inf. Syst..

Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007, SSW.

Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis

Heiga Zen, Keiichi Tokuda, H. Zen, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An HMM-based singing voice synthesis system

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, INTERSPEECH.

Gaussian Process Experts for Voice Conversion

Heiga Zen, Mark J. F. Gales, Nicholas Pilkington, 2011, INTERSPEECH.

Training a parametric-based logF0 model with the minimum generation error criterion

Heiga Zen, Mark J. F. Gales, Javier Latorre, 2010, INTERSPEECH.

AN HMM-BASED SPEECH SYNTHESIS SYSTEM APPLIED TO ENGLISH

Heiga Zen, Alan W. Black, Keiichi Tokuda, 2003 .

The Effect of Using Normalized Models in Statistical Speech Synthesis

Heiga Zen, William J. Byrne, Matt Shannon, 2011, INTERSPEECH.

Sparse KPCA for feature extraction in speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Estimation of Window Coefficients for Dynamic Feature Extraction for HMM-Based Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2011, INTERSPEECH.

On building a concatenative speech synthesis system from the blizzard challenge speech databases

Heiga Zen, Zhiwei Shuang, Raimo Bakis, 2005, INTERSPEECH.

Statistical Parametric Speech Synthesis

Heiga Zen, Keiichi Tokuda, Alan W. Black, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Context-dependent additive log f_0 model for HMM-based speech synthesis

Heiga Zen, Norbert Braunschweiler, H. Zen, 2009, INTERSPEECH.

Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2003, INTERSPEECH.

Decision tree-based context clustering based on cross validation and hierarchical priors

Heiga Zen, Mark J. F. Gales, H. Zen, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis

Heiga Zen, Andrew W. Senior, A. Senior, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise

Heiga Zen, Simon King, Junichi Yamagishi, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Globally Normalized Model for Statistical Speech Synthesis

Heiga Zen, H. Zen, 2011 .

A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Deep learning in speech synthesis

Heiga Zen, H. Zen, 2013, SSW.

Speech Research at Google to Enable Universal Speech Interfaces

Heiga Zen, Johan Schalkwyk, Michiel Bacchiani, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

Sequence-to-sequence Neural Network Model with 2D Attention for Learning Japanese Pitch Accents

Heiga Zen, Antoine Bruguier, Arkady Arkhangorodsky, 2018, INTERSPEECH.

Hidden Semi-Markov Model Based Speech Synthesis System

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2006 .

Autoregressive Models for Statistical Parametric Speech Synthesis

Heiga Zen, William J. Byrne, Matt Shannon, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Directly modeling voiced and unvoiced components in speech waveforms by neural networks

Heiga Zen, Keiichi Tokuda, H. Zen, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007, IEICE Trans. Inf. Syst..

Improving the performance of HMM-based very low bit rate speech coding

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Deterministic annealing EM algorithm in parameter estimation for acoustic model

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2004, INTERSPEECH.

Model-space MLLR for trajectory HMMs

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2007, INTERSPEECH.

Hidden Semi-Markov Model Based Speech Recognition System using Weighted Finite-State Transducer

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Speaker-Independent HMM-based Speech Synthesis System: HTS-2007 System for the Blizzard Challenge 2007

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007 .

Acoustic Modeling for Speech Synthesis: from HMM to RNN

Heiga Zen, 2015 .

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling pdf

Heiga Zen, Ye Jia, Isaac Elias, 2020, ArXiv.

An overview of nitech HMM-based speech synthesis system for blizzard challenge 2005

Heiga Zen, Tomoki Toda, H. Zen, 2005, INTERSPEECH.

Unsupervised adaptation for HMM-based speech synthesis

Heiga Zen, Keiichi Tokuda, Simon King, 2008, INTERSPEECH.

Decision tree-based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2003, INTERSPEECH.

Estimating Trajectory Hmm Parameters Using Monte Carlo Em With Gibbs Sampler

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Proc. 2009 Asia-Pacific Signal and Information Processing Association (APSIPA)

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2009 .

A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, IEICE Trans. Inf. Syst..

Parallel Tacotron: Non-Autoregressive and Controllable TTS pdf

Heiga Zen, Ron J. Weiss, Ye Jia, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Recent development of the HMM-based speech synthesis system (HTS)

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2009 .

Using instantaneous frequency and aperiodicity detection to estimate F0 for high-quality speech synthesis

Heiga Zen, Hideki Kawahara, Yannis Agiomyrgiannakis, 2016, SSW.

Continuous Speech Recognition Based on General Factor Dependent Acoustic Models(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005 .

Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends

Heiga Zen, Li Deng, Zhen-Hua Ling, 2015, IEEE Signal Processing Magazine.

Statistical parametric speech synthesis based on product of experts

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improvement in TF-IDF scheme for Web pages based on the contents of their hyperlinked neighboring pages

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2005 .

Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization

Heiga Zen, Sacha Krstulovic, Mark J. F. Gales, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2009, INTERSPEECH.

Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior

Heiga Zen, Bhuvana Ramabhadran, Yu Zhang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An introduction of trajectory model into HMM-based speech synthesis

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004, SSW.

Continuous Speech Recognition Based on General Factor Dependent Acoustic Models

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, IEICE Trans. Inf. Syst..

ICSLP 2006 Summary -Acoustic Modeling and Speech Synthesis-

Heiga Zen, Yoshihiko Nankaku, Tomoki Toda, 2006 .

Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2007, Comput. Speech Lang..

Statistical parametric synthesis based on products of experts

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010 .

An HMM-Based Brazilian Portuguese Speech Synthesizer and Its Characteristics DOI: 10.14209/jcis.2006.11

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2015 .

HMM-based polyglot speech synthesis by speaker and language adaptive training

Heiga Zen, Sacha Krstulovic, Kate Knill, 2010, SSW.

Speaker adaptation of trajectory HMMs using feature-space MLLR

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, INTERSPEECH.

Statistical Parametric Speech Synthesis

Heiga Zen, Keiichi Tokuda, Alan W. Black, 2007, IEEE International Conference on Acoustics, Speech, and Signal Processing.

State Duration Modeling for HMM-Based Speech Synthesis

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2007, IEICE Trans. Inf. Syst..

Stereo-based stochastic noise compensation based on trajectory GMMS

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Performance evaluation of the speaker-independent HMM-based speech synthesis system “HTS 2007” for the Blizzard Challenge 2007

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Parallel WaveNet: Fast High-Fidelity Speech Synthesis

Heiga Zen, Erich Elsen, Alex Graves, 2017, ICML.

E-Society Software Development Project for Speech Recognition and Synthesis(Technical Report)

Heiga Zen, Tomoki Toda, Kiyohiro Shikano, 2003 .

Decision tree distribution tying based on a dimensional split technique

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2002, INTERSPEECH.

Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques

Heiga Zen, Shinji Watanabe, Tomohiro Nakatani, 2019, IEEE Signal Processing Magazine.

On the Use of Kernel PCA for Feature Extraction in Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2003, IEICE Trans. Inf. Syst..

Multipulse Sequences for Residual Signal Modeling

Heiga Zen, Mark J. F. Gales, Kate Knill, 2011, INTERSPEECH.

Acoustic modeling with contextual additive structure for HMM-based speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Towards the development of a brazilian portuguese text-to-speech system based on HMM

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2003, INTERSPEECH.

The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2006, IEICE Trans. Inf. Syst..

Sample Efficient Adaptive Text-to-Speech pdf

Heiga Zen, Quan Wang, Nando de Freitas, 2018, ICLR.

Context adaptive training with factorized decision trees for HMM-based speech synthesis

Heiga Zen, Kai Yu, Steve J. Young, 2010, INTERSPEECH.

Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters

Heiga Zen, Mark J. F. Gales, Ranniery Maia, 2010, SSW.

A trainable excitation model for HMM-based speech synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2007, INTERSPEECH.

Product of Experts for Statistical Parametric Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

An implementation of decision tree-based context clustering on graphics processing units

Heiga Zen, Nicholas Pilkington, 2010, INTERSPEECH.

Autoregressive Models for Statistical

Heiga Zen, Matt Shannon, William Byrne, 2013 .

Multi-Language Multi-Speaker Acoustic Modeling for LSTM-RNN Based Statistical Parametric Speech Synthesis

Heiga Zen, Bo Li, H. Zen, 2016, INTERSPEECH.

Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

Heiga Zen, Bhuvana Ramabhadran, Yonghui Wu, 2019, INTERSPEECH.

Statistical parametric speech synthesis using deep neural networks

Heiga Zen, Andrew W. Senior, Mike Schuster, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices

Heiga Zen, Fergus Henderson, Yannis Agiomyrgiannakis, 2016, INTERSPEECH.

Constructing emotional speech synthesizers with limited speech database

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004, INTERSPEECH.

LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

Heiga Zen, Yu Zhang, Yonghui Wu, 2019, INTERSPEECH.

Applying Sparse KPCA for Feature Extraction in Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, IEICE Trans. Inf. Syst..

Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis

Heiga Zen, Hasim Sak, H. Zen, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bayesian Context Clustering Using Cross Validation for Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2011, IEICE Trans. Inf. Syst..

Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, INTERSPEECH.

Combining multiple high quality corpora for improving HMM-TTS

Heiga Zen, Mark J. F. Gales, Kate Knill, 2012, INTERSPEECH.

Speech Synthesis Based on Hidden Markov Models

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2013, Proceedings of the IEEE.

WaveGrad: Estimating Gradients for Waveform Generation pdf

Heiga Zen, Mohammad Norouzi, Ron J. Weiss, 2020, ICLR.

A Bayesian approach to HMM-based speech synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

An excitation model for HMM-based speech synthesis based on residual modeling

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2007, SSW.

WaveNet: A Generative Model for Raw Audio pdf

Heiga Zen, Alex Graves, Oriol Vinyals, 2016, SSW.

Probabilistic feature mapping based on trajectory HMMs

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, INTERSPEECH.

[Invited] Generative Model-Based Text-to-Speech Synthesis

Heiga Zen, 2018, 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE).

The HTS-2008 System: Yet Another Evaluation of the Speaker-Adaptive HMM-based Speech Synthesis System in The 2008 Blizzard Challenge

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2008 .

Simultaneous clustering of phonetic context, dimension, and state position for acoustic modeling using decision trees

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2005, Systems and Computers in Japan.

Speaker-Independent HMM-based Speech Synthesis System

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007 .

Speech recognition using voice-characteristic-dependent acoustic models

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Acoustic modeling based on model structure annealing for speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, INTERSPEECH.

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

Generative Model-Based Text-to-Speech Synthesis

Heiga Zen, H. Zen, 2017 .

A Covariance-Tying Technique for HMM-Based Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010, IEICE Trans. Inf. Syst..

The HMM-based speech synthesis system (HTS) version 2.0

Heiga Zen, Keiichi Tokuda, Takashi Nose, 2007, SSW.

Reformulating the HMM as a Trajectory Model

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004 .