Speaker interpolation for HMM-based speech synthesis system
スポンサーリンク
概要
- 論文の詳細を見る
This paper describes an approach to voice characteristics conversion for an HMM-based text-to-speech synthesis system using speaker interpolation.Although most text-to-speech synthesis systems which synthesize speech by concatenating speech units can synthesize speech with acceptable quality, they still cannot synthesize speech with various voice quality such as speaker individualities and emotions;In order to control speaker individualities and emotions, therefore, they need a large database, which records speech units with various voice characteristics in sythesis phase.On the other hand, our system synthesize speech with untrained speaker's voice quality by interpolating HMM parameters among some representative speakers' HMM sets.Accordingly, our system can synthesize speech with various voice quality without large database in synthesis phase.An HMM interpolation technique is derived from a probabilistic similarity measure for HMMs, and used to synthesize speech with untrained speaker's voice quality by interpolating HMM parameters among some representative speakers' HMM sets.The results of subjective experiments show that we can gradually change the voice quality of synthesized speech from one's to the other's by changing the interpolation ratio.
- 社団法人 日本音響学会の論文
著者
-
Yoshimura Takayoshi
Department of Cardiology, Ikuwakai Memorial Hospital
-
Masuko Takashi
Department Of Agricultural And Biological Chemistry College Of Bioresource Sciences Nihon University
-
Tokuda Keiichi
Department Of Computer Science And Engineering Nagoya Institute Of Technology
-
Kobayashi Takao
Department Of Bioregulatory Function Graduate School Of Medicine The University Of Tokyo
-
Kitamura Tadashi
Department Of Cardiothoracic Surgery Faculty Of Medicine University Of Tokyo
-
Yoshimura Takayoshi
Department of Computer Science,Nagoya Institute of Technology,Gokiso-cho,Showa-ku,Nagoya,466-8555 Japan
-
Masuko Takashi
Department of Information Processing,Interdisciplinary Graduate School of Science and Engineering,Tokyo Institute of Technology,4259,Nagatsuta-cho,Midori-ku,Yokohama,226-8502 Japan
関連論文
- Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005(Speech and Herring)
- Insufficient Stent Expansion as a Predictive Factor of Neointimal Hyperplasia After Stenting : A study using volumetric intravasculer ultrasound
- Effect of Residual Peri-Stent Plaque Volume on Neointimal Hyperplasia following Stenting : A Volumetric Intravascular Ultrasound Study
- Enhancement of Veratridine-Induced Sodium Dynamics in NG108-15 Cells during Differentiation(Pharmacology)
- A promising technique to measure water vapor content in the polar atmosphere: Lyman-α/OH fluorescence hygrometer
- Pulmonary embolism is an important cause of death in young adults
- 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
- A New Murine Model for Atherosclerosis with Inflammation in the Periodontal Tissue Induced by Immunization with Heat Shock Protein 60
- Preventive Effect of Ninjin-to(Ren-Shen-Tang), a Kampo(Japanese Traditional) Formulation, on Spontaneous Autoimmune Diabetes in Non-Obese Diabetic(NOD)Mice
- 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)
- -140-THE ENDOMYOCARDIAL BIOPSY FINDINGS AND CLINICAL FEATURES OF HEAVY DRINKERS WITH HEART FAILURE IN COMPARISON WITH THOSE OF PATIENTS OF DILATED CARDIOMYOPATHY : Cardiomyopathy : FREE COMMUNICATIONS(I) : PROCEEDINGS OF THE 53th ANNUAL SCIENTIFIC MEETING
- High frequency of erythromycin A resistance and distribution of mefE and ermB genes in clinical isolates of Streptococcus pneumoniae in Japan
- Potential of macrolide antibiotics to inhibit protein synthesis of Pseudomonas aeruginosa : suppression of virulence factors and stress response
- 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
- 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)
- PJ-443 Inhibitory Effect of Low Dose Pioglitazone on the In-stent Restenosis in Patients with Acute Myocardial Infarction and Type 2 Diabetes(Acute myocardial infarction, clinical (diagnosis/treatment)-9 (IHD) PJ75,Poster Session (Japanese),The 70th Anniv
- 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
- Q-Switching and Mode Selectiorn of Coupled-Cavity Er,Yb:Glass Lasers
- The aerial and fruit surface populations of fungi in nonchemical banana production in the Philippines
- A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System
- A Flash-lamp-Pumped Nd : YAG Laser with Dual-Telescopic Optics Configuration
- Circular Leaf Spot of Sweet Basil Caused by Cercospora guatemalensis New to Japan
- Brown Leaf Spot on Lantana spp. Caused by Pseudocercospora guianensis
- Low Pressure Plasma Confined in a Miniature Cylindrical Chamber and Its Application for In-Situ Elemental Analysis
- Deuterium Emission in Laser Plasma Induced by Transversely Excited Atmospheric Pressure CO_2 Laser in Low-Pressure of Helium Surrounding Gas
- Hydrogen Analysis in Solid using Laser-Induced Shock Wave Plasma
- 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)
- SUSCEPTIBILITY OF ANIMALS TO HEPATOCARCINOGENIC AROMATIC AMINES CORRELATES WITH THE INDUCTION OF THE CARCINOGEN ACTIVATION ENZYME (S) WITH THE AMINES
- Notes on some plant-inhabiting fungi collected from the Nansei Islands (2)
- Addition and reexamination of Japanese species belonging to the genus Cercospora and allied genera. VI. Four Pseudocercospora species from Ohshima Island, Tokyo
- Comparative in-vitro activity of carbapenem antibiotics against respiratory pathogens isolated between 1999 and 2000
- Addition and reexamination of Japanese species belonging to the genus Cercospora and allied genera. IV. Newly recorded species from Japan (1)
- 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
- Notes on new and noteworthy plant-inhabiting fungi from Japan (1)
- 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
- Ultraviolet Rayleigh Lidar for Wind and Temperature Measurements
- A Covariance-Typing Technique for HMM-Based Speech Synthesis
- Noradrenaline production was increased in cultured sympathetic nerve tissue after stimulation with eclamptic serum
- 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
- FRS-028 Amiodarone not only Reverses Electrical Remodeling but Suppresses Matrix Metalloproteinases 2 Activity in Canine Pacing-induced Persistent Atrial Fibrillation Model(Arrhythmia-Basic : Molecular and Genetic : Basis (A) : FRS4)(Featured Research Ses
- Seedborne fungi detected on stored solanaceous berry seeds and their biological activities
- Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Single-Line and Diffraction-Limited UV Nitrogen Oscillator-Amplifier Lasers
- Addition of Pestalotiopsis spp. to leaf spot pathogens of Japanese persimmon
- 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
- New canker diseases of Abies veitchii and Acer crataegifolium caused by Neonectria castaneicola
- Molecular Phylogenetic Analysis of Ribosomal DNA Internal Transcribed Spacer Regions and Comparison of Fertility in Phomopsis Isolates from Fruit Trees
- PROGNOSIS OF HYDATIDIFORM MOLE : FOLLOW-UP STUDY ON 2918 CASES IN SPECIAL REFERENCE TO AGING
- Ferromagnetic Crystalline Anisotropy and Transition Temperature of Ti-Substituted Magnetite
- Notes on new and noteworthy plant-inhabiting fungi from Japan (2) : Griphosphaerioma zelkovicola sp. nov. with Sarcostroma anamorph isolated from bark of Zelkova serrata
- A new species of Pestalosphaeria, the teleomorph of Pestalotiopsis neglecta
- Addition and reexamination of Japanese species belonging to the genus Cercospora and allied genera III Species described by Japanese mycologists (2)
- Addition and reexamination of Japanese species belonging to the genus Cercospora and allied genera II Species described by Japanese mycologists (1)
- 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)
- Notes on various plant-inhabiting fungi from Hachijo Island, Tokyo (1)
- Aloe ring spot, a new disease of aloe caused by Haematonectria haematococca (Berk. & Broome) Samuels & Nirenberg (anamorph : Fusarium sp.)
- Notes on new and noteworthy plant-inhabiting fungi in Japan (3)
- Taxonomic studies of nectrioid fungi in Japan. I : The genus Neonectria
- Neonectria amamiensis and Cylindrocarpon amamiense, a new nectrioid fungus and its sporodochial anamorph on Pinus luchuensis from Japan
- Taxonomic studies of nectrioid fungi in Japan. II : The genus Bionectria
- Taxonomic studies of nectrioid fungi in Japan. III. The genus Cosmospora
- Bayesian Context Clustering Using Cross Validation for Speech Recognition
- Speech recognition based on statistical models including multiple phonetic decision trees
- Malate dehydrogenases from nitrifying bacteria : purification and properties
- A Bayesian Framework Using Multiple Model Structures for Speech Recognition
- Speaker interpolation for HMM-based speech synthesis system