Robust estimation of multiple-regression HMM parameters for dimension-based expressive dialogue speech synthesis
نویسندگان
چکیده
This paper describes spontaneous dialogue speech synthesis based on multiple-regression hidden semi-Markov model (MRHSMM), which enables users to specify paralinguistic information of synthesized speech with a dimensional representation. Paralinguistic aspects of synthesized speech are controlled by multiple regression models whose explanatory variables are abstract dimensions such as pleasant-unpleasant and arousedsleepy. For robust estimation of the regression matrices of the MRHSMMwith unbalanced spontaneous dialogue speech samples, the re-estimation formulae were derived in the framework of the maximum a posteriori (MAP) estimation. The result of a perceptual experiment confirmed that the naturalness of synthesized speech was improved by applying the MAP estimation for regression matrices. In addition a high correlation (R ≃ 0.7) wasobserved between given and perceived paralinguistic information, which implies that the proposed method could successfully reflect intended paralinguistic messages on the synthesized speech.
منابع مشابه
A style control technique for singing voice synthesis based on multiple-regression HSMM
This paper proposes a technique for controlling singing style in the HMM-based singing voice synthesis. A style control technique based on multiple regression HSMM (MRHSMM), which was originally proposed for the HMM-based expressive speech synthesis, is applied to the conventional technique. The idea of pitch adaptive training is introduced into the MRHSMM to improve the modeling accuracy of fu...
متن کاملAn intuitive style control technique in HMM-based expressive speech synthesis using subjective style intensity and multiple-regression global variance model
To control intuitively the intensities of emotional expressions and speaking styles for synthetic speech, we introduce subjective style intensities and multiple-regression global variance (MRGV) models into hidden Markov model (HMM)-based expressive speech synthesis. A problem in the conventional parametric style modeling and style control techniques is that the intensities of styles appearing ...
متن کاملRecent Development of HMM-Based Expressive Speech Synthesis and Its Applications
This paper describes the recent development of HMM-based expressive speech synthesis. Although the expressive speech includes a wide variety of expressions such as emotions, speaking styles, intention, attitude, emphasis, focus, and so on, we mainly refer to the speech synthesis techniques for emotions and speaking styles, which would be the most primary expressions in human speech communicatio...
متن کاملSpeech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملFactored Mllr Adaptation for Hmm-based Expressive Speech Synthesis
One of the most popular approaches to parameter adaptation in hidden Markov model (HMM) based systems is the maximum likelihood linear regression (MLLR) technique. In our previous work, we proposed factored MLLR (FMLLR) where MLLR parameter is defined as a function of a control parameter vector. We presented a method to train the FMLLR parameters based on a general framework of the expectationm...
متن کامل