A Training Method of Average Voice Model for HMM-Based Speech Synthesis(<Special Section>Digital Signal Processing)
スポンサーリンク
概要
- 論文の詳細を見る
This paper describes a new training method of average voice model for speech synthesis in which arbitrary speaker's voice is generated based on speaker adaptation. When the amount of training data is limited, the distributions of average voice model often have bias depending on speaker and/or gender and this will degrade the quality of synthetic speech. In the proposed method, to reduce the influence of speaker dependence, we incorporate a context clustering technique called shared decision tree context clustering and speaker adaptive training into the training procedure of average voice model. From the results of subjective tests, we show that the average voice model trained using the proposed method generates more natural sounding speech than the conventional average voice model. Moreover, it is shown that voice characteristics and prosodic features of synthetic speech generated from the adapted model using the proposed method are closer to the target speaker than the conventional method.
- 社団法人電子情報通信学会の論文
- 2003-08-01
著者
-
TOKUDA Keiichi
Department of Computer Science and Engineering, Nagoya Institute of Technology
-
Masuko T
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology:(present
-
Masuko Takashi
近畿大学 薬学部細胞生物学
-
Tachibana Makoto
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology:(present
-
Masuko Takashi
Laboratory Of Cell Biology School Of Pharmaceutical Sciences Kinki University
-
Masuko Takashi
Departments Of Molecular Biology Pharmaceutical Institute Tohoku University
-
Masuko Takashi
Department Of Agricultural And Biological Chemistry College Of Bioresource Sciences Nihon University
-
Tokuda K
Department Of Computer Science And Engineering Nagoya Institute Of Technology
-
Tokuda Keiichi
Department Of Computer Science And Engineering Nagoya Institute Of Technology
-
Masuko Takashi
Tokyo Inst. Technol. Yokohama‐shi Jpn
-
YAMAGISHI Junichi
Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
-
MASUKO Takashi
Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
-
KOBAYASHI Takao
Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
-
TAMURA Masatsune
Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
-
Kobayashi Takao
Tokyo Inst. Technol. Yokohama‐shi Jpn
-
Tokuda Keiichi
The Department Of Computer Science Nagoya Institute Of Technology
-
Tachibana Makoto
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology
-
Tamura Masatsune
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology:(present
-
Masuko Takashi
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology
-
Kobayashi T
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology
-
Yamagishi Junichi
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology
-
Kobayashi Takao
Interdisciplinary Graduate School Of Science And Engineering Tokyo Institute Of Technology
-
Matsuyama Taiji
Department Of Pharmacy Shizuoka Kousei Hospital
-
Tokuda Keiichi
Department Of Computer Science Naogya Institute Of Technology
-
Kobayashi Takao
Department Of Obstetrics And Gynecology Hamamatsu University School Of Medicine
関連論文
- The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006
- Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005(Speech and Herring)
- Enhancement of Veratridine-Induced Sodium Dynamics in NG108-15 Cells during Differentiation(Pharmacology)
- Antibody epitope peptides as potential inducers of IgG antibodies against CD98 oncoprotein
- Identification of cell proliferation-associated epitope on CD98 oncoprotein using phage display random peptide library
- Molecular Structural and Functional Characterization of Tumor Suppressive Anti-ErbB-2 Monoclonal Antibody by Phage Display System
- Immunohistochemical expression and pathogenesis of BLM in the human brain and visceral organs
- Phage Display Cloning and Characterization of Monoclonal Antibody Genes and Recombinant Fab Fragment against the CD98 Oncoprotein
- Colocalization of CP125/CD98 with Tropomyosin Isoforms at the Cell-Cell Adhesion Boundary^1
- Identification and Immunological Characterization of a Novel 40 - kDa Protein Linked to CD98 Antigen
- Applying Sparse KPCA for Feature Extraction in Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- On the Use of Kernel PCA for Feature Extraction in Speech Recognition(Speech and Hearing)
- A Style Control Technique for HMM-Based Expressive Speech Synthesis(Speech and Hearing)
- A Style Adaptation Technique for Speech Synthesis Using HSMM and Suprasegmental Features(Speech Synthesis, Statistical Modeling for Speech Processing)
- Speech Synthesis with Various Emotional Expressions and Speaking Styles by Style Interpolation and Morphing(Life-like Agent and its Communication)
- Acoustic Modeling of Speaking Styles and Emotional Expressions in HMM-Based Speech Synthesis(Speech Synthesis and Prosody, Corpus-Based Speech Technologies)
- Identification of Truncated Human Glutamate Transporter
- Partial Involvement of Group I Metabotropic Glutamate Receptors in the Neurotoxicity of 3-N-Oxalyl-L-2,3-diaminopropanoic Acid(L-β-ODAP)(Pharmacology)
- Characterization and In Vitro Cytotoxic Effect of Adriamycin-conjugated Monoclonal Antibody Prepared Against Breast Cancer Cell Line
- Characterization of A New Breast Cancer-Associated Antigen and Its Relationship to MUC1 and TAG-72 Antigens
- Characterization of Cell Surface Antigens Expressed in the HMA-1 Breast Cancer Cell Line
- Effects of Dexamethasone and Aminophylline on Survival of Jurkat and HL-60 Cells(Pharmacology)
- Malate dehydrogenases from nitrifying bacteria : purification and properties
- Ribulose-1,5-Bisphosphate Carboxylase/Oxygenase from a Nitrite-Oxidizing Chemoautotroph, Nitrobacter agilis ATCC 14123 : Purification and Properties
- The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006
- A Hidden Semi-Markov Model-Based Speech Synthesis System(Speech and Hearing)
- State Duration Modeling for HMM-Based Speech Synthesis(Speech and Hearing)
- A Training Method of Average Voice Model for HMM-Based Speech Synthesis(Digital Signal Processing)
- A Context Clustering Technique for Average Voice Models (Special Issue on Speech Information Processing)
- Speaker Adaptation of Pitch and Spectrum for HMM-Based Speech Synthesis
- Multi-Space Probability Distribution HMM(Special Issue on the 2000 IEICE Excellent Paper Award)
- Vector Quantization of Speech Spectral Parameters Using Statistics of Static and Dynamic Features
- Text-Independent Speaker Identification Using Gaussian Mixture Models Based on Multi-Space Probability Distribution (Special Issue on Biometric Person Authentication)
- Application of Fluorescence Polarization Immunoassay for Determination of Methotrexate-Polyglutamates in Rheumatoid Arthritis Patients
- A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation
- An Enzyme Immunoassay for Cell Proliferation Using Monoclonal Antibodies Directed against a Cell Proliferation-Associated Antigen
- A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System
- Homotypic Adhesion through Carcinoembryonic Antigen Plays a Role in Hepatic Metastasis Development
- Mixture Density Models Based on Mel-Cepstral Representation of Gaussian Process(Digital Signal Processing)
- A 16kb/s Wideband CELP-Based Speech Coder Using Mel-Generalized Cepstral Analysis
- Development of Material Management System for Newspapers (Special Issue on New Generation Database Technologies)
- SUSCEPTIBILITY OF ANIMALS TO HEPATOCARCINOGENIC AROMATIC AMINES CORRELATES WITH THE INDUCTION OF THE CARCINOGEN ACTIVATION ENZYME (S) WITH THE AMINES
- Conidiomatal development of Pestalotiopsis guepinii and P. neglecta on leaves of Gardenia jasminoides
- Pycnidial development of Phyllosticta harai and Sphaeropsis sp.
- LMS-Based Algorithms with Multi-Band Decomposition of the Estimation Error Applied to System Identification (Special Section on Digital Signal Processing)
- Multi-Band Decomposition of the Linear Prediction Error Applied to Adaptive AR Spectral Estimation
- Robust F_0 Estimation of Speech Signal Using Harmonicity Measure Based on Instantaneous Frequency(Speech and Hearing)
- Intracellular Localization of UDP-Glucuronosyltransferase Expressed from the Transfected cDNA in Cultured Cells
- Adaptive AR Spectral Estimation Based on Wavelet Decomposition of the Linear Prediction Error
- A Covariance-Typing Technique for HMM-Based Speech Synthesis
- An autopsy case of cyclopia with 13 trisomy with special reference to histological abnormalities of the eyeball
- Acrania : an autopsy case and review of the literature
- Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Significance of integrin αvβ5 and erbB3 in enhanced cell migration and liver metastasis of colon carcinomas stimulated by hepatocyte-derived heregulin
- Dihydrofolate Reductase Gene Intronic 19-bp Deletion Polymorphisms in a Japanese Population
- A Rapid Model Adaptation Technique for Emotional Speech Recognition with Style Estimation Based on Multiple-Regression HMM
- HMM-Based Style Control for Expressive Speech Synthesis with Arbitrary Speaker's Voice Using Model Adaptation
- Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Continuous Speech Recognition Based on General Factor Dependent Acoustic Models(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive Training(Speech and Hearing)
- A Technique for Estimating Intensity of Emotional Expressions and Speaking Styles in Speech Based on Multiple-Regression HSMM
- Bayesian Context Clustering Using Cross Validation for Speech Recognition
- Reformulating the HMM as a Trajectory Model
- Reformulating the HMM as a Trajectory Model
- Reformulating the HMM as a Trajectory Model
- HMM-Based Voice Conversion Using Quantized F0 Context
- Speech recognition based on statistical models including multiple phonetic decision trees
- Human Walking Motion Synthesis with Desired Pace and Stride Length Based on HSMM(Life-like Agent and its Communication)
- FOREWORD
- Malate dehydrogenases from nitrifying bacteria : purification and properties
- A context clustering technique for improvement of tone intelligibility of average-voice-based Thai speech synthesis (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- A Bayesian Framework Using Multiple Model Structures for Speech Recognition
- An Extension of Separable Lattice 2-D HMMs for Rotational Data Variations
- Speaker interpolation for HMM-based speech synthesis system
- A Bayesian Framework Using Multiple Model Structures for Speech Recognition