TAILIEUCHUNG - Báo cáo khoa học: "Statistical Modeling for Unit Selection in Speech Synthesis"

Traditional concatenative speech synthesis systems use a number of heuristics to define the target and concatenation costs, essential for the design of the unit selection component. In contrast to these approaches, we introduce a general statistical modeling framework for unit selection inspired by automatic speech recognition. Given appropriate data, techniques based on that framework can result in a more accurate unit selection, thereby improving the general quality of a speech synthesizer. They can also lead to a more modular and a substantially more efficient system. . | Statistical Modeling for Unit Selection in Speech Synthesis Cyril Allauzen and Mehryar Mohri and Michael Riley AT T Labs - Research 180 Park Avenue Florham Park NJ 07932 USA allauzen mohri riley @ Abstract Traditional concatenative speech synthesis systems use a number of heuristics to define the target and concatenation costs essential for the design of the unit selection component. In contrast to these approaches we introduce a general statistical modeling framework for unit selection inspired by automatic speech recognition. Given appropriate data techniques based on that framework can result in a more accurate unit selection thereby improving the general quality of a speech synthesizer. They can also lead to a more modular and a substantially more efficient system. We present a new unit selection system based on statistical modeling. To overcome the original absence of data we use an existing high-quality unit selection system to generate a corpus of unit sequences. We show that the concatenation cost can be accurately estimated from this corpus using a statistical n-gram language model over units. We used weighted automata and transducers for the representation of the components of the system and designed a new and more efficient composition algorithm making use of string potentials for their combination. The resulting statistical unit selection is shown to be about times faster than the last release of the AT T Natural Voices Product while preserving the same quality and offers much flexibility for the use and integration of new and more complex components. 1 Motivation A concatenative speech synthesis system Hunt and Black 1996 Beutnagel et al. 1999a consists of three components. The first component the textanalysis frontend takes text as input and outputs a sequence of feature vectors that characterize the acoustic signal to synthesize. The first element of each of these vectors is the predicted phone or halfphone other elements are .

• Báo cáo khoa học
• Statistical Modeling
• Unit Selection in Speech Synthesis
• Cyril Allauzen and Mehryar Mohri and Michael Riley
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Statistical regression modeling of hardened AISI 52100 steel
• Machinability study of hardened AISI 52100 steel
• Cemented carbide insert
• Dry machining of AISI 52100 steel hardened
• Statistical regression model
• Fast Syntactic Analysis
• Statistical Language Modeling
• Substructure Sharing and Uptraining
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Discriminative Feature Tied Mixture Modeling
• Statistical Machine Translation
• Bing Xiang and Abraham Ittycheriah
• Modeling Human Sentence Processing Data
• Statistical Parts of Speech Tagger
• Jihyun Park
• Modeling with Structures
• Long Papers
• Exploring Asymmetric Clustering
• Jianfeng Gao
• Fish production
• Time series
• Total fish production
• Fish production of India
• Wind turbine
• Quantitative evaluation
• Variable speed electronics
• Yaw drive
• Entering data
• Palette swapping
• Environmental envelope
• Probability distribution
• Environmental
• Statistical Distributions
• BMC Bioinformatics
• Mass spectrometry
• Molecule identification
• Silico fragmentation
• Sample size
• Structural equation modeling
• Supply chain management
• Statistical power analysis
• Critical analysis
• Genome Biology
• Gene addiction
• Probabilistic modeling framework
• Cancer research
• Statistical Digital
• Signal Processing
• Multirate Systems
• Pattern Classification
• Schaums Outline
• Drug combination
• High throughput screen
• Cancer therapy
• Cancer cell lines
• Bliss independence
• Veterinary epidemiology
• Demonstrating association
• Observational studies
• Design considerations
• Clinical trials
• Mathematical modeling
• BMC Genomics
• Microbial genomics
• Core genome
• SNP GC content
• Core genome GC content
• Statistical parameter estimation
• Electro Discharge Machining
• Design of Experiments
• Response Surface Methodology
• Desirability Function Approach
• Process Modeling
• Multi Objective Optimization
• phân tích không gian địa lý
• kỹ thuật trắc địa
• dữ liệu viễn thám
• khoa học môi trường
• quản lý tài nguyên