Glottal Estimation Using a Nonlinear Arma Filter
نویسندگان
چکیده
EGG, which depicts the degree of contact between vocal folds, is a measurable proxy for glottal pressure wave, and thus contains information of pitch and GCI. In this project, I proposed a TDRNN, or a nonlinear ARMA filter, that turns input speech waveforms to approximation of EGG, which can be further applied to pitch tracking or GCI location. Two baseline systems, a linear MA filter and a nonlinear MA filter, are also experimented and evaluated. Preliminary experiments have confirm the ability of the proposed system to estimate EGG, and further analysis discloses more interesting findings.
منابع مشابه
Identification of an Autonomous Underwater Vehicle Dynamic Using Extended Kalman Filter with ARMA Noise Model
In the procedure of designing an underwater vehicle or robot, its maneuverability and controllability must be simulated and tested, before the product is finalized for manufacturing. Since the hydrodynamic forces and moments highly affect the dynamic and maneuverability of the system, they must be estimated with a reasonable accuracy. In this study, hydrodynamic coefficients of an autonomous un...
متن کاملA New Iterative Algorithm for ARMA Modelling of Vowels and glottal Flow Estimation based on Blind System Identification
In this paper the voiced speech signal is modelled as an ARMA process with: 1an AR filter whose coefficients are obtained using a new iterative model-based algorithm and 2an MA filter whose input is the glottal excitation and its output is the linear prediction residual or the input of the AR filter. The AR filter is estimated using an iterative algorithm in which the Liljencrants–Fant (LF) mod...
متن کاملA robust glottal source model estimation technique
This paper describes a robust glottal source estimation method based on a joint source-filter separation technique. In this method, the glottal flow derivative is modelled as the Liljencrants-Fant (LF) model and the vocal tract is described as a time-varying ARX model. Since the joint estimation problem is a multi-parameter nonlinear optimization procedure, we separate the optimization procedur...
متن کاملVoiced Speech Synthesis Using Pitch Asynchronous Code Excited Linear Filters for the Glottal Source
This paper proposes a model for natural quality voiced speech synthesis using code excited linear all-pole filter for modeling the glottal source signal. Classical glottal signal models are explicit-time functions which inhibit joint sourcetract parameter estimation and require pitch synchronous estimation with precise segmentation of open and closed glottis phase. These problems are overcome i...
متن کاملRotated Unscented Kalman Filter for Two State Nonlinear Systems
In the several past years, Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) havebecame basic algorithm for state-variables and parameters estimation of discrete nonlinear systems.The UKF has consistently outperformed for estimation. Sometimes least estimation error doesn't yieldwith UKF for the most nonlinear systems. In this paper, we use a new approach for a two variablestate no...
متن کامل