Continuous Speech Recognition Using an On-Line Speaker Adaptation Method Based on Automatic Speaker Clustering (<Special Issue>Special Issue on Speech Information Processing)
スポンサーリンク
概要
- 論文の詳細を見る
This paper evaluates an on-line incremental speaker adaptation method for co-channel conversation including multiple speakers with the assumption that the speaker is unknown and changes frequently. After performing the speaker clustering treatment based on the Vector Quantization (VQ) distortion for every utterance, acoustic models for each cluster are adapted by Maximum Likelihood Linear Regression (MLLR) or Maximum A Posteriori probability (MAP). The performance of continuous speech recognition could be improved. In this paper, to prove the efficiency of the speaker clustering method for improving the performance of continuous speech recognition, the continuous speech recognition experiments with supervised and unsupervised cluster adaptation were conducted, respectively. Finally, evaluation experiments based on other prepared test data were performed on continuous syllable recognition and large vocabulary continuous speech recognition (LVCSR). The efficiency of the speaker adaptation and clustering methods presented in this paper was supported strongly by the experimental results.
- 社団法人電子情報通信学会の論文
- 2003-03-01
著者
-
ZHANG Wei
Department of Health Toxicology, School of Radiation Medicine and Public Health, Soochow University,
-
Nakagawa Seiichi
Department of Information and Computer Sciences, Toyohashi University of Technology
-
Nakagawa Seiichi
Department Of Information And Computer Sciences Toyohashi University Of Technology
-
Nakagawa Seiichi
Department Of Information And Computer Sciences Toyohashi University
-
Zhang Wei
Department Of Anesthesiology First Affiliated Hospital Zhengzhou University
-
Zhang Wei
Department Of Information And Computer Sciences Toyohashi University Of Technology
-
Nakagawa Seiichi
Department of Computer Science and Engineering, Toyohashi University of Technology
関連論文
- MIMO-OC Scheme to Suppress Co-channel Interference
- Aberrant Promoter Methylation of p16^ and O^6-Methylguanine-DNA Methyltransferase Genes in Workers at a Chinese Uranium Mine
- Anti-inflammatory and Analgesic Activities of Edgeworthia chrysantha and Its Effective Chemical Constituents(Pharmacognosy)
- Annexin II promotes invasion and migration of human hepatocellular carcinoma cells in vitro via its interaction with HAb18G/CD147
- Impaired atrial synchronicity in patients with metabolic syndrome associated with insulin resistance and independent of hypertension
- Topic dependent language model based on on-line voting (言語理解とコミュニケーション)
- A transitive translation for Indonesian-Japanese CLQA (自然言語処理)
- A Machine Learning Approach for an Indonesian-English Cross Language Question Answering System(Natural Language Processing)
- Indonesian-Japanese Transitive Translation using English for CLIR
- 7-O-Methylaromadendrin Stimulates Glucose Uptake and Improves Insulin Resistance in Vitro
- High Field NMR Study of Yb_Y_InCu_4 up to 30T(Condensed matter: electronic structure and electrical, magnetic, and optical properties)
- H-T Phase Diagram of First-Order Valence Transtition in Yb_Y_xInCu_4 : an Experimental Observation on Falicov-Kimball Model
- Clinical evaluation of oral levofloxacin 500mg once-daily dosage for treatment of lower respiratory tract infections and urinary tract infections : a prospective multicenter study in China
- MIMO-OC Scheme to Suppress Co-channel Interference
- Synthesis, Crystal Structure, and Nonlinear Optical Property of Two New Chromophores Containing Furan Ring as a Conjugation Bridge
- Arylaldehydes-pentafluorophenyl Hydrazones as Second-order Nonlinear Optical Chromophores : A Novel Approach for Remarkably Defeating the Nonlinearity-transparency Trade-off
- A Comparative Study of Output Probability Functions in HMMs
- Homeostasis Model Assessment-Insulin Resistance (HOMA-IR), a Key Role for Assessing the Ovulation Function in Polycystic Ovary Syndrome (PCOS) Patients with Insulin Resistance
- Enhanced Left Atrial Reservoir, Increased Conduit, and Weakened Booster Pump Function in Hypertensive Patients with Paroxysmal Atrial Fibrillation
- Topic dependent language model based on on-line voting (音声)
- Topic dependent language model based on clustering of noun word history
- Word and class dependency of N-gram language model (音声言語情報処理)
- Word and class dependency of N-gram language model (言語理解とコミュニケーション・第9回音声言語シンポジウム)
- Word and class dependency of N-gram language model (音声・第9回音声言語シンポジウム)
- Automated Experimental Assembly for Studying the Reaction-Diffusion Behavior of Belousov-Zhabotinsky Reactions under Microgravity
- Cerebrotendinous xanthomatosis with a compound heterozygote mutation and severe polyneuropathy
- Genetic polymorphisms in the cytochrome P450 1A1 and 2E1 genes, smoking, drinking and prostate cancer susceptibility : A case-control study in a Han nationality population in Southern China
- Text-Independent/Text-Prompted Speaker Recognition by Combining Speaker-Specific GMM with Speaker Adapted Syllable-Based HMM(Speaker Recognition, Statistical Modeling for Speech Processing)
- Attenuated Listeria infection activates natural killer cell cytotoxicity to regress melanoma growth in vivo
- Cytokinins from the tRNA of the Red Alga Porphyra perforata J. Ag.
- Orbital Period Study of the RS CVn-Type Binary WW Draconis
- Optoelectronic Implementation of Bipolar Analog Neural Network Using Shadow Casting (OPTICAL COMPUTING 1)
- Relationship Between Ricinus Communis Agglutinin-1 Binding and Nucleolar Organizer Regions in Human Gliomas
- Effect of Interferon-y on ACNU-induced DNA Damage and Cytotoxicity in Human Glioblastoma Cells
- A Precision Machining of Gears : Slow-Scanning Field Controlled Electrochemical Honing
- Head-Down Tilt Posture Attenuates Anaphylactic Hypotension in Mice and Rats
- N^G-Nitro-L-arginine Methyl Ester, but Not Methylene Blue, Attenuates Anaphylactic Hypotension in Anesthetized Mice
- Performance Analysis of IEEE802.11e EDCA(Terrestrial Radio Communications)
- Evaluation of Combinational Use of Discriminant Analysis-Based Acoustic Feature Transformation and Discriminative Training
- LVCSR based on context-dependent syllable acoustic models (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- Robust distant speech recognition by combining variable-term spectrum based position-dependent CMN with conventional CMN (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- Linear Discriminant Analysis Using a Generalized Mean of Class Covariances and Its Application to Speech Recognition
- Robust Speech Recognition by Combining Short-Term and Long-Term Spectrum Based Position-Dependent CMN with Conventional CMN
- Robust distant speech recognition by combining variable-term spectrum based position-dependent CMN with conventional CMN
- Improving Keyword Recognition of Spoken Queries by Combining Multiple Speech Recognizer's Outputs for Speech-driven WEB Retrieval Task(Spoken Language Systems, Corpus-Based Speech Technologies)
- An Unsupervised Speaker Adaptation Method for Lecture-Style Spontaneous Speech Recognition Using Multiple Recognition Systems(Spoken Language Systems, Corpus-Based Speech Technologies)
- Speaker Change Detection and Speaker Clustering Using VQ Distortion Measure
- Pathogenic Acanthamoeba Induces Apoptosis of Human Corneal Epithelial Cells
- Expression of NDRG2 in Clear Cell Renal Cell Carcinoma(Molecular and Cell Biology)
- Evidence for Muscarinic 3 Receptor Mediated Ion Transport in HT29 Cells Studied by X-ray Microanalysis
- Reduction expression of thrombomodulin and endothelial cell nitric oxide synthase in dermatomyositis
- Succeeding Word Prediction for Speech Recognition Based on Stochastic Language Model
- Synthesis and Luminescent Properties of Two Copolymers Containing Dithienothiophene and Fluorene
- Expression level of insulin-like growth factor binding protein 5 mRNA is a prognostic factor for breast cancer
- Increased expressions and activations of apoptosis-related factors in cell signaling during incised skin wound healing in mice : A preliminary study for forensic wound age estimation
- Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System
- Distant Speech Recognition Using a Microphone Array Network
- Auditory perception versus automatic estimation of location and orientation of an acoustic source in a real environment
- Continuous Speech Recognition Using an On-Line Speaker Adaptation Method Based on Automatic Speaker Clustering (Special Issue on Speech Information Processing)
- Hepatitis B virus infections in families in which the mothers are negative but the fathers are positive for HBsAg
- Distant-Talking Speech Recognition Based on Spectral Subtraction by Multi-Channel LMS Algorithm
- The effects of E_μ,3'α(hs 1,2)and 3'κenhancers on mutation of an lg-VDJ-Cγ2a lgheavy gene in cultured B cells
- Anthocyanin Synthesis, Growth and Nutrient Uptake in Suspension Cultures of Strawberry Cells
- Scanning electron microscopic changes in the morphology of rabbit pulmonary tissue biopsied following ischemia and reperfusion : a window of opportunity?
- A Spoken Dialog System for Spontaneous Conversations Considering Response Timing and Response Type
- Transitional change in interaction between HIF-1 and HNF-4 in response to hypoxia
- Synthesis and Properties of Helical Poly (macromonomer) Consisting of Polyacetylene Main Chain and Poly (methyl methacrylate) Side Chains
- Early Postoperative Heterotopic Omental Ossification : Report of a Case
- The overlap of corticobasal degeneration and Alzheimer changes : An autopsy case
- Clincial and pathological study of distal motor neuropathy with N88S mutation in BSCL2
- A Phase-Segregated Model for Plant Cell Culture : The Effect of Cell Volume Fraction
- Clonal instability of V region hypermutation in the Ramos Burkitt's lymphoma cell line
- Quantitation of Irinotecan and its two major metabolites using a liquid chromatography-electrospray ionization tandem mass spectrometric
- Portacaval shunting attenuates portal hypertension and systemic hypotension in rat anaphylactic shock
- Antioxidant treatment with quercetin ameliorates erectile dysfunction in streptozotocin-induced diabetic rats(GENETICS, MOLECULAR BIOLOGY, AND GENE ENGINEERING)
- Phase Transition and Crystal Structure of Ba_2CuO_x Oxide
- Combined use of adult fiberoptic bronchoscope and CARTO catheter for tracheal intubation in children with known difficult airway
- Crystal Structure of Ternary Ba_8YCu_4O Phase
- Indonesian-Japanese Transitive Translation using English for CLIR
- NG-Nitro-L-arginine Methyl Ester, but Not Methylene Blue, Attenuates Anaphylactic Hypotension in Anesthetized Mice
- An overview on systemic lupus erythematosus pregnancy
- Polarization Properties of Deep-Ultraviolet Optical Gain in Al-Rich AlGaN Structures
- Mutations in mitochondrially encoded complex I enzyme as the second common cause in a cohort of Chinese patients with mitochondrial myopathy, encephalopathy, lactic acidosis and stroke-like episodes
- Class-Based N-Gram Language Model for New Words Using Out-of-Vocabulary to In-Vocabulary Similarity
- Recurrent Aortic Aneurysm due to Behcet’s Disease: A Case Report from China
- Mitral Paravalvular Abnormal Tunnel with Mitral Regurgitation Caused by Anterior Chest Trauma
- Impaired dimer assembly and decreased stability of naturally recurring R260C mutant A subunit for coagulation factor XIII
- Establishment of an in Vitro Model of the Human Placental Barrier by Placenta Slice Culture and Ussing Chamber