default search action
BibTeX records: Yoshihiko Nankaku
@article{DBLP:journals/access/FujimotoHNT25,
author = {Takato Fujimoto and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {V2Coder: {A} Non-Autoregressive Vocoder Based on Hierarchical Variational
Autoencoders},
journal = {{IEEE} Access},
volume = {13},
pages = {92833--92847},
year = {2025}
}
@inproceedings{DBLP:conf/icassp/HonoHNT24,
author = {Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion
Probabilistic Model},
booktitle = {{ICASSP}},
pages = {12782--12786},
publisher = {{IEEE}},
year = {2024}
}
@article{DBLP:journals/corr/abs-2402-14692,
author = {Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion
Probabilistic Model},
journal = {CoRR},
volume = {abs/2402.14692},
year = {2024}
}
@inproceedings{DBLP:conf/icassp/HonoHNT23,
author = {Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing Voice Synthesis Based on a Musical Note Position-Aware Attention
Mechanism},
booktitle = {{ICASSP}},
pages = {1--5},
publisher = {{IEEE}},
year = {2023}
}
@inproceedings{DBLP:conf/icassp/YoshimuraTNOHHNT23,
author = {Takenori Yoshimura and
Shinji Takaki and
Kazuhiro Nakamura and
Keiichiro Oura and
Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Embedding a Differentiable Mel-Cepstral Synthesis Filter to a Neural
Speech Synthesis System},
booktitle = {{ICASSP}},
pages = {1--5},
publisher = {{IEEE}},
year = {2023}
}
@article{DBLP:journals/corr/abs-2301-02262,
author = {Miku Nishihara and
Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing voice synthesis based on frame-level sequence-to-sequence
models considering vocal timing deviation},
journal = {CoRR},
volume = {abs/2301.02262},
year = {2023}
}
@inproceedings{DBLP:conf/gcce/NakamuraHSTNK22,
author = {Yasutaka Nakamura and
Seiichi Harata and
Takuto Sakuma and
Yoshihiro Tanaka and
Yoshihiko Nankaku and
Shohei Kato},
title = {Enhancing Social Telepresence on Text Communication Using Robot Avatar
that Reflects User's Chatting States},
booktitle = {{GCCE}},
pages = {707--709},
publisher = {{IEEE}},
year = {2022}
}
@inproceedings{DBLP:conf/icassp/FujimotoHNT22,
author = {Takato Fujimoto and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Autoregressive Variational Autoencoder with a Hidden Semi-Markov Model-Based
Structured Attention for Speech Synthesis},
booktitle = {{ICASSP}},
pages = {7462--7466},
publisher = {{IEEE}},
year = {2022}
}
@inproceedings{DBLP:conf/interspeech/MitsuiZSHNT22,
author = {Kentaro Mitsui and
Tianyu Zhao and
Kei Sawada and
Yukiya Hono and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {End-to-End Text-to-Speech Based on Latent Representation of Speaking
Styles Using Spontaneous Dialogue},
booktitle = {{INTERSPEECH}},
pages = {2328--2332},
publisher = {{ISCA}},
year = {2022}
}
@article{DBLP:journals/corr/abs-2206-12040,
author = {Kentaro Mitsui and
Tianyu Zhao and
Kei Sawada and
Yukiya Hono and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {End-to-End Text-to-Speech Based on Latent Representation of Speaking
Styles Using Spontaneous Dialogue},
journal = {CoRR},
volume = {abs/2206.12040},
year = {2022}
}
@article{DBLP:journals/corr/abs-2211-11222,
author = {Takenori Yoshimura and
Shinji Takaki and
Kazuhiro Nakamura and
Keiichiro Oura and
Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural
Speech Synthesis System},
journal = {CoRR},
volume = {abs/2211.11222},
year = {2022}
}
@article{DBLP:journals/corr/abs-2212-13703,
author = {Yukiya Hono and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing Voice Synthesis Based on a Musical Note Position-Aware Attention
Mechanism},
journal = {CoRR},
volume = {abs/2212.13703},
year = {2022}
}
@article{DBLP:journals/access/HonoTHONT21,
author = {Yukiya Hono and
Shinji Takaki and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {PeriodNet: {A} Non-Autoregressive Raw Waveform Generative Model With
a Structure Separating Periodic and Aperiodic Components},
journal = {{IEEE} Access},
volume = {9},
pages = {137599--137612},
year = {2021}
}
@article{DBLP:journals/taslp/HonoHONT21,
author = {Yukiya Hono and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Sinsy: {A} Deep Neural Network-Based Singing Voice Synthesis System},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {2803--2815},
year = {2021}
}
@inproceedings{DBLP:conf/icassp/HonoTHONT21,
author = {Yukiya Hono and
Shinji Takaki and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Periodnet: {A} Non-Autoregressive Waveform Generation Model with a
Structure Separating Periodic and Aperiodic Components},
booktitle = {{ICASSP}},
pages = {6049--6053},
publisher = {{IEEE}},
year = {2021}
}
@article{DBLP:journals/corr/abs-2102-07786,
author = {Yukiya Hono and
Shinji Takaki and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {PeriodNet: {A} non-autoregressive waveform generation model with a
structure separating periodic and aperiodic components},
journal = {CoRR},
volume = {abs/2102.07786},
year = {2021}
}
@article{DBLP:journals/corr/abs-2108-02776,
author = {Yukiya Hono and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Sinsy: {A} Deep Neural Network-Based Singing Voice Synthesis System},
journal = {CoRR},
volume = {abs/2108.02776},
year = {2021}
}
@inproceedings{DBLP:conf/icassp/NakamuraTHONT20,
author = {Kazuhiro Nakamura and
Shinji Takaki and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Fast and High-Quality Singing Voice Synthesis System Based on Convolutional
Neural Networks},
booktitle = {{ICASSP}},
pages = {7239--7243},
publisher = {{IEEE}},
year = {2020}
}
@inproceedings{DBLP:conf/icassp/FujimotoTHONT20,
author = {Takato Fujimoto and
Shinji Takaki and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Semi-Supervised Learning Based on Hierarchical Generative Models for
End-to-End Speech Synthesis},
booktitle = {{ICASSP}},
pages = {7644--7648},
publisher = {{IEEE}},
year = {2020}
}
@inproceedings{DBLP:conf/interspeech/HonoTSHONT20,
author = {Yukiya Hono and
Kazuna Tsuboi and
Kei Sawada and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Hierarchical Multi-Grained Generative Model for Expressive Speech
Synthesis},
booktitle = {{INTERSPEECH}},
pages = {3441--3445},
publisher = {{ISCA}},
year = {2020}
}
@article{DBLP:journals/corr/abs-2009-08474,
author = {Yukiya Hono and
Kazuna Tsuboi and
Kei Sawada and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Hierarchical Multi-Grained Generative Model for Expressive Speech
Synthesis},
journal = {CoRR},
volume = {abs/2009.08474},
year = {2020}
}
@inproceedings{DBLP:conf/icassp/HonoHONT19,
author = {Yukiya Hono and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing Voice Synthesis Based on Generative Adversarial Networks},
booktitle = {{ICASSP}},
pages = {6955--6959},
publisher = {{IEEE}},
year = {2019}
}
@inproceedings{DBLP:conf/icassp/YoshimuraHONT19,
author = {Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Speaker-dependent Wavenet-based Delay-free Adpcm Speech Coding},
booktitle = {{ICASSP}},
pages = {7145--7149},
publisher = {{IEEE}},
year = {2019}
}
@inproceedings{DBLP:conf/ssw/OuraNHNT19,
author = {Keiichiro Oura and
Kazuhiro Nakamura and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Deep neural network based real-time speech vocoder with periodic and
aperiodic inputs},
booktitle = {{SSW}},
pages = {13--18},
publisher = {{ISCA}},
year = {2019}
}
@inproceedings{DBLP:conf/ssw/FujimotoHONT19,
author = {Takato Fujimoto and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Impacts of input linguistic feature representation on Japanese end-to-end
speech synthesis},
booktitle = {{SSW}},
pages = {166--171},
publisher = {{ISCA}},
year = {2019}
}
@inproceedings{DBLP:conf/ssw/ShimadaHONT19,
author = {Motoki Shimada and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Low computational cost speech synthesis based on deep neural networks
using hidden semi-Markov model structures},
booktitle = {{SSW}},
pages = {177--182},
publisher = {{ISCA}},
year = {2019}
}
@article{DBLP:journals/corr/abs-1904-06868,
author = {Kazuhiro Nakamura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing voice synthesis based on convolutional neural networks},
journal = {CoRR},
volume = {abs/1904.06868},
year = {2019}
}
@article{DBLP:journals/corr/abs-1910-11690,
author = {Kazuhiro Nakamura and
Shinji Takaki and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Fast and High-Quality Singing Voice Synthesis System based on Convolutional
Neural Networks},
journal = {CoRR},
volume = {abs/1910.11690},
year = {2019}
}
@article{DBLP:journals/taslp/YoshimuraHONT18,
author = {Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based
Speech Waveform Synthesis},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {26},
number = {7},
pages = {1173--1180},
year = {2018}
}
@inproceedings{DBLP:conf/apsipa/KasugaiTSHONT18,
author = {Takayuki Kasugai and
Yoshinari Tsuzuki and
Kei Sawada and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Image Recognition Based on Convolutional Neural Networks Using Features
Generated from Separable Lattice Hidden Markov Models},
booktitle = {{APSIPA}},
pages = {324--328},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/apsipa/NakaoHONT18,
author = {Kento Nakao and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks
Using Hidden Semi-Markov Model Structures},
booktitle = {{APSIPA}},
pages = {638--643},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/apsipa/FujimotoYHONT18,
author = {Takato Fujimoto and
Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Speech Synthesis Using WaveNet Vocoder Based on Periodic/Aperiodic
Decomposition},
booktitle = {{APSIPA}},
pages = {644--648},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/apsipa/HonoMNHONT18,
author = {Yukiya Hono and
Shumma Murata and
Kazuhiro Nakamura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Recent Development of the DNN-based Singing Voice Synthesis System
- Sinsy},
booktitle = {{APSIPA}},
pages = {1003--1009},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/apsipa/YoshimuraKHONT18,
author = {Takenori Yoshimura and
Natsumi Koike and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Discriminative Feature Extraction Based on Sequential Variational
Autoencoder for Speaker Recognition},
booktitle = {{APSIPA}},
pages = {1742--1746},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/apsipa/SendaHSHONT18,
author = {Koki Senda and
Yukiya Hono and
Kei Sawada and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing Voice Conversion Using Posted Waveform Data on Music Social
Media},
booktitle = {{APSIPA}},
pages = {1913--1917},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/blizzard/SawadaYHONT18,
author = {Kei Sawada and
Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {The NITech text-to-speech system for the Blizzard Challenge 2018},
booktitle = {Blizzard Challenge},
publisher = {{ISCA}},
year = {2018}
}
@inproceedings{DBLP:conf/icassp/IchikawaSHNT18,
author = {Eiji Ichikawa and
Kei Sawada and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Image Recognition Based on Separable Lattice Hmms Using a Deep Neural
Network for Output Probability Distributions},
booktitle = {{ICASSP}},
pages = {3021--3025},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/icassp/NiwaYHONT18,
author = {Jumpei Niwa and
Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Statistical Voice Conversion Based on Wavenet},
booktitle = {{ICASSP}},
pages = {5289--5293},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/slt/YoshimuraHONT18,
author = {Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {WaveNet-Based Zero-Delay Lossless Speech Coding},
booktitle = {{SLT}},
pages = {153--158},
publisher = {{IEEE}},
year = {2018}
}
@article{DBLP:journals/taslp/YoshimuraHONT17,
author = {Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Simultaneous Optimization of Multiple Tree-Based Factor Analyzed {HMM}
for Speech Synthesis},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {25},
number = {9},
pages = {1836--1845},
year = {2017}
}
@inproceedings{DBLP:conf/icassp/TsuzukiSHNT17,
author = {Yoshinari Tsuzuki and
Kei Sawada and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Image recognition based on discriminative models using features generated
from separable lattice {HMMS}},
booktitle = {{ICASSP}},
pages = {2607--2611},
publisher = {{IEEE}},
year = {2017}
}
@inproceedings{DBLP:conf/interspeech/GullyYMHNT17,
author = {Amelia Jane Gully and
Takenori Yoshimura and
Damian T. Murphy and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Articulatory Text-to-Speech Synthesis Using the Digital Waveguide
Mesh Driven by a Deep Neural Network},
booktitle = {{INTERSPEECH}},
pages = {234--238},
publisher = {{ISCA}},
year = {2017}
}
@incollection{DBLP:books/sp/17/TokudaLNOHYTUTRY17,
author = {Keiichi Tokuda and
Akinobu Lee and
Yoshihiko Nankaku and
Keiichiro Oura and
Kei Hashimoto and
Daisuke Yamamoto and
Ichi Takumi and
Takahiro Uchiya and
Shuhei Tsutsumi and
Steve Renals and
Junichi Yamagishi},
title = {User Generated Dialogue Systems: uDialogue},
booktitle = {Human-Harmonized Information Technology {(2)}},
pages = {77--114},
publisher = {Springer},
year = {2017}
}
@article{DBLP:journals/ieicet/SawadaTHNT16,
author = {Kei Sawada and
Akira Tamamori and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A Bayesian Approach to Image Recognition Based on Separable Lattice
Hidden Markov Models},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {99-D},
number = {12},
pages = {3119--3131},
year = {2016}
}
@inproceedings{DBLP:conf/icassp/HashimotoONT16,
author = {Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Trajectory training considering global variance for speech synthesis
based on neural networks},
booktitle = {{ICASSP}},
pages = {5600--5604},
publisher = {{IEEE}},
year = {2016}
}
@inproceedings{DBLP:conf/interspeech/HosakaHONT16,
author = {Naoki Hosaka and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Voice Conversion Based on Trajectory Model Training of Neural Networks
Considering Global Variance},
booktitle = {{INTERSPEECH}},
pages = {307--311},
publisher = {{ISCA}},
year = {2016}
}
@inproceedings{DBLP:conf/interspeech/NishimuraHONT16,
author = {Masanari Nishimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Singing Voice Synthesis Based on Deep Neural Networks},
booktitle = {{INTERSPEECH}},
pages = {2478--2482},
publisher = {{ISCA}},
year = {2016}
}
@inproceedings{DBLP:conf/interspeech/DallHONT16,
author = {Rasmus Dall and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Redefining the Linguistic Context Feature Set for {HMM} and {DNN}
{TTS} Through Position and Parsing},
booktitle = {{INTERSPEECH}},
pages = {2851--2855},
publisher = {{ISCA}},
year = {2016}
}
@inproceedings{DBLP:conf/ssw/TokudaHON16,
author = {Keiichi Tokuda and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku},
title = {Temporal modeling in neural network based statistical parametric speech
synthesis},
booktitle = {{SSW}},
pages = {106--111},
publisher = {{ISCA}},
year = {2016}
}
@inproceedings{DBLP:conf/icassp/HashimotoONT15,
author = {Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {The effect of neural networks in statistical parametric speech synthesis},
booktitle = {{ICASSP}},
pages = {4455--4459},
publisher = {{IEEE}},
year = {2015}
}
@inproceedings{DBLP:conf/interspeech/YoshimuraHNT15,
author = {Takenori Yoshimura and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Simultaneous optimization of multiple tree structures for factor analyzed
HMM-based speech synthesis},
booktitle = {{INTERSPEECH}},
pages = {1196--1200},
publisher = {{ISCA}},
year = {2015}
}
@inproceedings{DBLP:conf/interspeech/GangireddyRNL15,
author = {Siva Reddy Gangireddy and
Steve Renals and
Yoshihiko Nankaku and
Akinobu Lee},
title = {Prosodically-enhanced recurrent neural network language models},
booktitle = {{INTERSPEECH}},
pages = {2390--2394},
publisher = {{ISCA}},
year = {2015}
}
@article{DBLP:journals/ieicet/NakamuraHNT14,
author = {Kazuhiro Nakamura and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Integration of Spectral Feature Extraction and Modeling for HMM-Based
Speech Synthesis},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {97-D},
number = {6},
pages = {1438--1448},
year = {2014}
}
@article{DBLP:journals/ieicet/TamamoriNT14,
author = {Akira Tamamori and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Image Recognition Based on Separable Lattice Trajectory 2-D HMMs},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {97-D},
number = {7},
pages = {1842--1854},
year = {2014}
}
@article{DBLP:journals/jstsp/TakakiNT14,
author = {Shinji Takaki and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Contextual Additive Structure for HMM-Based Speech Synthesis},
journal = {{IEEE} J. Sel. Top. Signal Process.},
volume = {8},
number = {2},
pages = {229--238},
year = {2014}
}
@inproceedings{DBLP:conf/icassp/NakamuraONT14,
author = {Kazuhiro Nakamura and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {HMM-Based singing voice synthesis and its application to Japanese
and English},
booktitle = {{ICASSP}},
pages = {265--269},
publisher = {{IEEE}},
year = {2014}
}
@inproceedings{DBLP:conf/icassp/ShirotaNHONT14,
author = {Kanako Shirota and
Kazuhiro Nakamura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Integration of speaker and pitch adaptive training for HMM-based singing
voice synthesis},
booktitle = {{ICASSP}},
pages = {2559--2563},
publisher = {{IEEE}},
year = {2014}
}
@inproceedings{DBLP:conf/interspeech/NakamuraHONT14,
author = {Kazuhiro Nakamura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A mel-cepstral analysis technique restoring high frequency components
from low-sampling-rate speech},
booktitle = {{INTERSPEECH}},
pages = {2494--2498},
publisher = {{ISCA}},
year = {2014}
}
@article{DBLP:journals/ieicet/ShiotaHNT13,
author = {Sayaka Shiota and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A Bayesian Framework Using Multiple Model Structures for Speech Recognition},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {96-D},
number = {4},
pages = {939--948},
year = {2013}
}
@article{DBLP:journals/pieee/TokudaNTZYO13,
author = {Keiichi Tokuda and
Yoshihiko Nankaku and
Tomoki Toda and
Heiga Zen and
Junichi Yamagishi and
Keiichiro Oura},
title = {Speech Synthesis Based on Hidden Markov Models},
journal = {Proc. {IEEE}},
volume = {101},
number = {5},
pages = {1234--1252},
year = {2013}
}
@inproceedings{DBLP:conf/apsipa/SawadaHNT13,
author = {Kei Sawada and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Image recognition based on hidden Markov eigen-image models using
variational Bayesian method},
booktitle = {{APSIPA}},
pages = {1--8},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/icassp/MakinoTHNT13,
author = {Takaya Makino and
Shinji Takaki and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Separable lattice 2-D {HMMS} introducing state duration control for
recognition of images with various variations},
booktitle = {{ICASSP}},
pages = {3203--3207},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/icassp/TamamoriNT13,
author = {Akira Tamamori and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Image recognition based on separable lattice trajectory 2-D {HMMS}},
booktitle = {{ICASSP}},
pages = {3467--3471},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/icassp/TakakiNT13,
author = {Shinji Takaki and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Contextual partial additive structure for HMM-based speech synthesis},
booktitle = {{ICASSP}},
pages = {7878--7882},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/icassp/NakamuraHNT13,
author = {Kazuhiro Nakamura and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Integration of acoustic modeling and mel-cepstral analysis for HMM-based
speech synthesis},
booktitle = {{ICASSP}},
pages = {7883--7887},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/ssw/YoshimuraHONT13,
author = {Takenori Yoshimura and
Kei Hashimoto and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Cross-lingual speaker adaptation based on factor analysis using bilingual
speech data for HMM-based speech synthesis},
booktitle = {{SSW}},
pages = {297--302},
publisher = {{ISCA}},
year = {2013}
}
@article{DBLP:journals/ieicet/TamamoriNT12,
author = {Akira Tamamori and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {An Extension of Separable Lattice 2-D HMMs for Rotational Data Variations},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {95-D},
number = {8},
pages = {2074--2083},
year = {2012}
}
@article{DBLP:journals/taslp/ZenGNT12,
author = {Heiga Zen and
Mark J. F. Gales and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Product of Experts for Statistical Parametric Speech Synthesis},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {20},
number = {3},
pages = {794--805},
year = {2012}
}
@inproceedings{DBLP:conf/icassp/SawadaTHNT12,
author = {Kei Sawada and
Akira Tamamori and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Face recognition based on separable lattice 2-D {HMMS} using variational
bayesian method},
booktitle = {{ICASSP}},
pages = {2205--2208},
publisher = {{IEEE}},
year = {2012}
}
@inproceedings{DBLP:conf/icassp/KumakiNT12,
author = {Keisuke Kumaki and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Face recognition based on extended separable lattice 2-D {HMMS}},
booktitle = {{ICASSP}},
pages = {2209--2212},
publisher = {{IEEE}},
year = {2012}
}
@inproceedings{DBLP:conf/icassp/ShiotaHNT12,
author = {Sayaka Shiota and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A model structure integration based on a Bayesian framework for speech
recognition},
booktitle = {{ICASSP}},
pages = {4813--4816},
publisher = {{IEEE}},
year = {2012}
}
@inproceedings{DBLP:conf/icassp/OuraMNT12,
author = {Keiichiro Oura and
Ayami Mase and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Pitch adaptive training for hmm-based singing voice synthesis},
booktitle = {{ICASSP}},
pages = {5377--5380},
publisher = {{IEEE}},
year = {2012}
}
@inproceedings{DBLP:conf/interspeech/OliveiraSNT12,
author = {Viviane de Franca Oliveira and
Sayaka Shiota and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Cross-lingual Speaker Adaptation for HMM-based Speech Synthesis based
on Perceptual Characteristics and Speaker Interpolation},
booktitle = {{INTERSPEECH}},
pages = {983--986},
publisher = {{ISCA}},
year = {2012}
}
@inproceedings{DBLP:conf/interspeech/HattoriHNT12,
author = {Takafumi Hattori and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A Bayesian Approach to Speaker Recognition Based on GMMs Using Multiple
Model Structures},
booktitle = {{INTERSPEECH}},
pages = {1107--1110},
publisher = {{ISCA}},
year = {2012}
}
@article{DBLP:journals/ieicet/HashimotoZNLT11,
author = {Kei Hashimoto and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Bayesian Context Clustering Using Cross Validation for Speech Recognition},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {94-D},
number = {3},
pages = {668--678},
year = {2011}
}
@article{DBLP:journals/taslp/ZenNT11,
author = {Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Continuous Stochastic Feature Mapping Based on Trajectory HMMs},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {19},
number = {2},
pages = {417--430},
year = {2011}
}
@inproceedings{DBLP:conf/icassp/TakakiONT11,
author = {Shinji Takaki and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {An optimization algorithm of independent mean and variance parameter
tying structures for HMM-based speech synthesis},
booktitle = {{ICASSP}},
pages = {4700--4703},
publisher = {{IEEE}},
year = {2011}
}
@inproceedings{DBLP:conf/icassp/PanNTT11,
author = {Shifeng Pan and
Yoshihiko Nankaku and
Keiichi Tokuda and
Jianhua Tao},
title = {Global variance modeling on frequency domain delta {LSP} for HMM-based
speech synthesis},
booktitle = {{ICASSP}},
pages = {4716--4719},
publisher = {{IEEE}},
year = {2011}
}
@inproceedings{DBLP:conf/interspeech/HashimotoNT11,
author = {Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Multi-Speaker Modeling with Shared Prior Distributions and Model Structures
for Bayesian Speech Synthesis},
booktitle = {{INTERSPEECH}},
pages = {113--116},
publisher = {{ISCA}},
year = {2011}
}
@inproceedings{DBLP:conf/interspeech/LiNT11,
author = {Lei Li and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A Bayesian Approach to Voice Conversion Based on GMMs Using Multiple
Model Structures},
booktitle = {{INTERSPEECH}},
pages = {661--664},
publisher = {{ISCA}},
year = {2011}
}
@inproceedings{DBLP:conf/interspeech/RemesNT11,
author = {Ulpu Remes and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {GMM-Based Missing-Feature Reconstruction on Multi-Frame Windows},
booktitle = {{INTERSPEECH}},
pages = {1665--1668},
publisher = {{ISCA}},
year = {2011}
}
@inproceedings{DBLP:conf/interspeech/ChenNZTLD11,
author = {Ling{-}Hui Chen and
Yoshihiko Nankaku and
Heiga Zen and
Keiichi Tokuda and
Zhen{-}Hua Ling and
Li{-}Rong Dai},
title = {Estimation of Window Coefficients for Dynamic Feature Extraction for
HMM-Based Speech Synthesis},
booktitle = {{INTERSPEECH}},
pages = {1801--1804},
publisher = {{ISCA}},
year = {2011}
}
@inproceedings{DBLP:conf/interspeech/ItoNL11,
author = {Naoaki Ito and
Yoshihiko Nankaku and
Akinobu Lee},
title = {Evaluation of Tree-Trellis Based Decoding in Over-Million {LVCSR}},
booktitle = {{INTERSPEECH}},
pages = {1937--1940},
publisher = {{ISCA}},
year = {2011}
}
@article{DBLP:journals/ieicet/OuraZNLT10,
author = {Keiichiro Oura and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {A Covariance-Tying Technique for HMM-Based Speech Synthesis},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {93-D},
number = {3},
pages = {595--601},
year = {2010}
}
@inproceedings{DBLP:conf/eamt/Martinez-GomezH10,
author = {Pascual Mart{\'{\i}}nez{-}G{\'{o}}mez and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda and
Germ{\'{a}}n Sanchis{-}Trilles},
title = {A Deterministic Annealing-Based Training Algorithm For Statistical
Machine Translation Models},
booktitle = {{EAMT}},
publisher = {European Association for Machine Translation},
year = {2010}
}
@inproceedings{DBLP:conf/icassp/TakahashiTNT10,
author = {Yoshiaki Takahashi and
Akira Tamamori and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Face recognition based on separable lattice 2-D {HMM} with state duration
modeling},
booktitle = {{ICASSP}},
pages = {2162--2165},
publisher = {{IEEE}},
year = {2010}
}
@inproceedings{DBLP:conf/icassp/TamamoriNT10,
author = {Akira Tamamori and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {An extension of Separable Lattice 2-D {HMMS} for rotational data variations},
booktitle = {{ICASSP}},
pages = {2206--2209},
publisher = {{IEEE}},
year = {2010}
}
@inproceedings{DBLP:conf/icassp/KazumiNT10,
author = {Kyosuke Kazumi and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Factor analyzed voice models for HMM-based speech synthesis},
booktitle = {{ICASSP}},
pages = {4234--4237},
publisher = {{IEEE}},
year = {2010}
}
@inproceedings{DBLP:conf/icassp/ZenGNT10,
author = {Heiga Zen and
Mark J. F. Gales and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Statistical parametric speech synthesis based on product of experts},
booktitle = {{ICASSP}},
pages = {4242--4245},
publisher = {{IEEE}},
year = {2010}
}
@inproceedings{DBLP:conf/interspeech/HayashiNLT10,
author = {Toyohiro Hayashi and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Speaker adaptation based on nonlinear spectral transform for speech
recognition},
booktitle = {{INTERSPEECH}},
pages = {542--545},
publisher = {{ISCA}},
year = {2010}
}
@inproceedings{DBLP:conf/interspeech/MaseONT10,
author = {Ayami Mase and
Keiichiro Oura and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {HMM-based singing voice synthesis system using pitch-shifted pseudo
training data},
booktitle = {{INTERSPEECH}},
pages = {845--848},
publisher = {{ISCA}},
year = {2010}
}
@inproceedings{DBLP:conf/interspeech/SaitoNLT10,
author = {Akira Saito and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Voice activity detection based on conditional random fields using
multiple features},
booktitle = {{INTERSPEECH}},
pages = {2086--2089},
publisher = {{ISCA}},
year = {2010}
}
@inproceedings{DBLP:conf/ssw/TakakiNT10,
author = {Shinji Takaki and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Spectral modeling with contextual additive structure for HMM-based
speech synthesis},
booktitle = {{SSW}},
pages = {100--105},
publisher = {{ISCA}},
year = {2010}
}
@inproceedings{DBLP:conf/ssw/HashimotoNT10,
author = {Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Bayesian speech synthesis framework integrating training and synthesis
processes},
booktitle = {{SSW}},
pages = {106--111},
publisher = {{ISCA}},
year = {2010}
}
@inproceedings{DBLP:conf/ssw/OuraMYMNT10,
author = {Keiichiro Oura and
Ayami Mase and
Tomohiko Yamada and
Satoru Muto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Recent development of the HMM-based singing voice synthesis system
- Sinsy},
booktitle = {{SSW}},
pages = {211--216},
publisher = {{ISCA}},
year = {2010}
}
@inproceedings{DBLP:conf/icassp/YutaniUNLT09,
author = {Kaori Yutani and
Yosuke Uto and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Voice conversion based on simultaneous modelling of spectrum and {F0}},
booktitle = {{ICASSP}},
pages = {3897--3900},
publisher = {{IEEE}},
year = {2009}
}
@inproceedings{DBLP:conf/icassp/HashimotoZNMT09,
author = {Kei Hashimoto and
Heiga Zen and
Yoshihiko Nankaku and
Takashi Masuko and
Keiichi Tokuda},
title = {A Bayesian approach to HMM-based speech synthesis},
booktitle = {{ICASSP}},
pages = {4029--4032},
publisher = {{IEEE}},
year = {2009}
}
@inproceedings{DBLP:conf/icassp/ZenNT09,
author = {Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Stereo-based stochastic noise compensation based on trajectory {GMMS}},
booktitle = {{ICASSP}},
pages = {4577--4580},
publisher = {{IEEE}},
year = {2009}
}
@inproceedings{DBLP:conf/interspeech/WuNT09,
author = {Yi{-}Jian Wu and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {State mapping based method for cross-lingual speaker adaptation in
HMM-based speech synthesis},
booktitle = {{INTERSPEECH}},
pages = {528--531},
publisher = {{ISCA}},
year = {2009}
}
@inproceedings{DBLP:conf/interspeech/ShiotaHNT09,
author = {Sayaka Shiota and
Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Deterministic annealing based training algorithm for Bayesian speech
recognition},
booktitle = {{INTERSPEECH}},
pages = {680--683},
publisher = {{ISCA}},
year = {2009}
}
@inproceedings{DBLP:conf/interspeech/HashimotoNT09,
author = {Kei Hashimoto and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A Bayesian approach to Hidden Semi-Markov Model based speech synthesis},
booktitle = {{INTERSPEECH}},
pages = {1751--1754},
publisher = {{ISCA}},
year = {2009}
}
@inproceedings{DBLP:conf/interspeech/OuraZNLT09,
author = {Keiichiro Oura and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Tying covariance matrices to reduce the footprint of HMM-based speech
synthesis systems},
booktitle = {{INTERSPEECH}},
pages = {1759--1762},
publisher = {{ISCA}},
year = {2009}
}
@article{DBLP:journals/ieicet/OuraZNLT08,
author = {Keiichiro Oura and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition
System},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {91-D},
number = {11},
pages = {2693--2700},
year = {2008}
}
@inproceedings{DBLP:conf/icassp/NankakuNZT08,
author = {Yoshihiko Nankaku and
Kazuhiro Nakamura and
Heiga Zen and
Keiichi Tokuda},
title = {Acoustic modeling with contextual additive structure for HMM-based
speech recognition},
booktitle = {{ICASSP}},
pages = {4469--4472},
publisher = {{IEEE}},
year = {2008}
}
@inproceedings{DBLP:conf/interspeech/YoshimiKNLT08,
author = {Yoshitaka Yoshimi and
Ryota Kakitsuba and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Probabilistic answer selection based on conditional random fields
for spoken dialog system},
booktitle = {{INTERSPEECH}},
pages = {215--218},
publisher = {{ISCA}},
year = {2008}
}
@inproceedings{DBLP:conf/interspeech/ShiotaHZNLT08,
author = {Sayaka Shiota and
Kei Hashimoto and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Acoustic modeling based on model structure annealing for speech recognition},
booktitle = {{INTERSPEECH}},
pages = {932--935},
publisher = {{ISCA}},
year = {2008}
}
@inproceedings{DBLP:conf/interspeech/HashimotoZNLT08,
author = {Kei Hashimoto and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Bayesian context clustering using cross valid prior distribution for
HMM-based speech recognition},
booktitle = {{INTERSPEECH}},
pages = {936--939},
publisher = {{ISCA}},
year = {2008}
}
@inproceedings{DBLP:conf/interspeech/ZenNT08,
author = {Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Probabilistic feature mapping based on trajectory HMMs},
booktitle = {{INTERSPEECH}},
pages = {1068--1071},
publisher = {{ISCA}},
year = {2008}
}
@inproceedings{DBLP:conf/interspeech/YutaniUNTT08,
author = {Kaori Yutani and
Yosuke Uto and
Yoshihiko Nankaku and
Tomoki Toda and
Keiichi Tokuda},
title = {Simultaneous conversion of duration and spectrum based on statistical
models including time-sequence matching},
booktitle = {{INTERSPEECH}},
pages = {1072--1075},
publisher = {{ISCA}},
year = {2008}
}
@inproceedings{DBLP:conf/interspeech/ItoHNLT08,
author = {Tatsuya Ito and
Kei Hashimoto and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Speaker recognition based on variational Bayesian method},
booktitle = {{INTERSPEECH}},
pages = {1417--1420},
publisher = {{ISCA}},
year = {2008}
}
@inproceedings{DBLP:conf/iscslp/OuraNTTMSN08,
author = {Keiichiro Oura and
Yoshihiko Nankaku and
Tomoki Toda and
Keiichi Tokuda and
Ranniery Maia and
Shinsuke Sakai and
Satoshi Nakamura},
title = {Simultaneous Acoustic, Prosodic, and Phrasing Model Training for TTs
Conversion Systems},
booktitle = {{ISCSLP}},
pages = {1--4},
publisher = {{IEEE}},
year = {2008}
}
@inproceedings{DBLP:conf/icassp/NankakuT07,
author = {Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Face Recognition using Hidden Markov Eigenface Models},
booktitle = {{ICASSP} {(2)}},
pages = {469--472},
publisher = {{IEEE}},
year = {2007}
}
@inproceedings{DBLP:conf/interspeech/MaiaTZNT07,
author = {Ranniery Maia and
Tomoki Toda and
Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {A trainable excitation model for HMM-based speech synthesis},
booktitle = {{INTERSPEECH}},
pages = {1909--1912},
publisher = {{ISCA}},
year = {2007}
}
@inproceedings{DBLP:conf/interspeech/ZenNT07,
author = {Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Model-space {MLLR} for trajectory HMMs},
booktitle = {{INTERSPEECH}},
pages = {2065--2068},
publisher = {{ISCA}},
year = {2007}
}
@inproceedings{DBLP:conf/ssw/MaiaTZNT07,
author = {Ranniery Maia and
Tomoki Toda and
Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {An excitation model for HMM-based speech synthesis based on residual
modeling},
booktitle = {{SSW}},
pages = {131--136},
publisher = {{ISCA}},
year = {2007}
}
@inproceedings{DBLP:conf/ssw/NankakuNTT07,
author = {Yoshihiko Nankaku and
Kenichi Nakamura and
Tomoki Toda and
Keiichi Tokuda},
title = {Spectral conversion based on statistical models including time-sequence
matching},
booktitle = {{SSW}},
pages = {333--338},
publisher = {{ISCA}},
year = {2007}
}
@inproceedings{DBLP:conf/icassp/OuraZNLT06,
author = {Keiichiro Oura and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {Hidden Semi-Markov Model Based Speech Recognition System using Weighted
Finite-State Transducer},
booktitle = {{ICASSP} {(1)}},
pages = {33--36},
publisher = {{IEEE}},
year = {2006}
}
@inproceedings{DBLP:conf/icassp/NakamuraTNT06,
author = {Kenichi Nakamura and
Tomoki Toda and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {On the Use of Phonetic Information for Mapping from Articulatory Movements
to Vocal Tract Spectrum},
booktitle = {{ICASSP} {(1)}},
pages = {93--96},
publisher = {{IEEE}},
year = {2006}
}
@inproceedings{DBLP:conf/icassp/KurataNTKG06,
author = {Daisuke Kurata and
Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura and
Zoubin Ghahramani},
title = {Face Recognition Based on Separable Lattice {HMMS}},
booktitle = {{ICASSP} {(5)}},
pages = {737--740},
publisher = {{IEEE}},
year = {2006}
}
@inproceedings{DBLP:conf/icassp/ZenNTK06,
author = {Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Estimating Trajectory Hmm Parameters Using Monte Carlo Em With Gibbs
Sampler},
booktitle = {{ICASSP} {(1)}},
pages = {1173--1176},
publisher = {{IEEE}},
year = {2006}
}
@inproceedings{DBLP:conf/interspeech/HakamataLNT06,
author = {Tomohiro Hakamata and
Akinobu Lee and
Yoshihiko Nankaku and
Keiichi Tokuda},
title = {Reducing computation on parallel decoding using frame-wise confidence
scores},
booktitle = {{INTERSPEECH}},
publisher = {{ISCA}},
year = {2006}
}
@inproceedings{DBLP:conf/interspeech/SainoZNLT06,
author = {Keijiro Saino and
Heiga Zen and
Yoshihiko Nankaku and
Akinobu Lee and
Keiichi Tokuda},
title = {An HMM-based singing voice synthesis system},
booktitle = {{INTERSPEECH}},
publisher = {{ISCA}},
year = {2006}
}
@inproceedings{DBLP:conf/interspeech/UtoNTLT06,
author = {Yosuke Uto and
Yoshihiko Nankaku and
Tomoki Toda and
Akinobu Lee and
Keiichi Tokuda},
title = {Voice conversion based on mixtures of factor analyzers},
booktitle = {{INTERSPEECH}},
publisher = {{ISCA}},
year = {2006}
}
@inproceedings{DBLP:conf/interspeech/ZenNTK06,
author = {Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Speaker adaptation of trajectory HMMs using feature-space {MLLR}},
booktitle = {{INTERSPEECH}},
publisher = {{ISCA}},
year = {2006}
}
@article{DBLP:journals/ieicet/LimaZNTKR05,
author = {Amaro A. de Lima and
Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura and
Fernando Gil Resende},
title = {Applying Sparse {KPCA} for Feature Extraction in Speech Recognition},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {88-D},
number = {3},
pages = {401--409},
year = {2005}
}
@article{DBLP:journals/ieicet/SuzukiZNMTK05,
author = {Hiroyuki Suzuki and
Heiga Zen and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Continuous Speech Recognition Based on General Factor Dependent Acoustic
Models},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {88-D},
number = {3},
pages = {410--417},
year = {2005}
}
@article{DBLP:journals/ieicet/YamamotoNMTK05,
author = {Hiroyoshi Yamamoto and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {88-D},
number = {3},
pages = {418--424},
year = {2005}
}
@article{DBLP:journals/ieicet/ItayaZNMTK05,
author = {Yohei Itaya and
Heiga Zen and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Deterministic Annealing {EM} Algorithm in Acoustic Modeling for Speaker
and Speech Recognition},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {88-D},
number = {3},
pages = {425--431},
year = {2005}
}
@inproceedings{DBLP:conf/icassp/LimaZNTKR05,
author = {Amaro A. de Lima and
Heiga Zen and
Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura and
Fernando Gil Resende},
title = {Sparse {KPCA} for Feature Extraction in Speech Recognition},
booktitle = {{ICASSP} {(1)}},
pages = {353--356},
publisher = {{IEEE}},
year = {2005}
}
@article{DBLP:journals/ieicet/LimaZNMTK04,
author = {Amaro A. de Lima and
Heiga Zen and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {On the Use of Kernel {PCA} for Feature Extraction in Speech Recognition},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {87-D},
number = {12},
pages = {2802--2811},
year = {2004}
}
@inproceedings{DBLP:conf/icassp/YamamotoNMTK04,
author = {Hiroyoshi Yamamoto and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Parameter sharing and minimum classification error training of mixtures
of factor analyzers for speaker identification},
booktitle = {{ICASSP} {(1)}},
pages = {29--32},
publisher = {{IEEE}},
year = {2004}
}
@inproceedings{DBLP:conf/interspeech/ItayaZNMTK04,
author = {Yohei Itaya and
Heiga Zen and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Deterministic annealing {EM} algorithm in parameter estimation for
acoustic model},
booktitle = {{INTERSPEECH}},
pages = {433--436},
publisher = {{ISCA}},
year = {2004}
}
@inproceedings{DBLP:conf/icassp/SuzukiZNMTK03,
author = {Hiroyuki Suzuki and
Heiga Zen and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Speech recognition using voice-characteristic-dependent acoustic models},
booktitle = {{ICASSP} {(1)}},
pages = {740--743},
publisher = {{IEEE}},
year = {2003}
}
@inproceedings{DBLP:conf/interspeech/LimaZNMTK03,
author = {Amaro A. de Lima and
Heiga Zen and
Yoshihiko Nankaku and
Chiyomi Miyajima and
Keiichi Tokuda and
Tadashi Kitamura},
title = {On the use of kernel {PCA} for feature extraction in speech recognition},
booktitle = {{INTERSPEECH}},
pages = {2625--2628},
publisher = {{ISCA}},
year = {2003}
}
@inproceedings{DBLP:conf/icip/NankakuTKK00,
author = {Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura and
Takao Kobayashi},
title = {Normalized Training for HMM-Based Visual Speech Recognition},
booktitle = {{ICIP}},
pages = {234--237},
publisher = {{IEEE}},
year = {2000}
}
@inproceedings{DBLP:conf/interspeech/NankakuTK99,
author = {Yoshihiko Nankaku and
Keiichi Tokuda and
Tadashi Kitamura},
title = {Intensity- and location-normalized training for HMM-based visual speech
recognition},
booktitle = {{EUROSPEECH}},
pages = {1287--1290},
publisher = {{ISCA}},
year = {1999}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-07-07 21:16 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: