Preliminary inversion mapping results with a new EMA corpus

نویسنده

  • Korin Richmond
چکیده

In this paper, we apply our inversion mapping method, the trajectory mixture density network (TMDN), to a new corpus of articulatory data, recorded with a Carstens AG500 electromagnetic articulograph. This new data set, mngu0, is relatively large and phonetically rich, among other beneficial characteristics. We obtain good results, with a root mean square (RMS) error of only 0.99mm. This compares very well with our previous lowest result of 1.54mm RMS error for equivalent coils of the MOCHA fsew0 EMA data. We interpret this as showing the mngu0 data set is potentially more consistent than the fsew0 data set, and is very useful for research which calls for articulatory trajectory data. It also supports our view that the TMDN is very much suited to the inversion mapping problem.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Towards unsupervised articulatory resynthesis of German utterances using EMA data

As part of ongoing research towards integrating an articulatory synthesizer into a text-to-speech (TTS) framework, a corpus of German utterances recorded with electromagnetic articulography (EMA) is resynthesized to provide training data for statistical models. The resynthesis is based on a measure of similarity between the original and resynthesized EMA trajectories, weighted by articulatory r...

متن کامل

Learning Articulation from Cepstral Coefficients

We work on a special case of the speech inversion problem, namely the mapping from Mel Frequency Cepstral Coeeficients onto articulatory trajectories, derived by EMA. We employ Support Vector Regression, and use PCA and ICA as means to account for the spatial structure of the problem. Our results are comparable to those achieved by older attempts on the same task, indicating probably some natur...

متن کامل

Inversion of Gravity Data by Constrained Nonlinear Optimization based on nonlinear Programming Techniques for Mapping Bedrock Topography

A constrained nonlinear optimization method based on nonlinear programming techniques has been applied to map geometry of bedrock of sedimentary basins by inversion of gravity anomaly data. In the inversion, the applying model is a 2-D model that is composed of a set of juxtaposed prisms whose lower depths have been considered as unknown model parameters. The applied inversion method is a nonli...

متن کامل

Intra-Operative Lymphatic Mapping and Sentinel Node Biopsy in Laryngeal Carcinoma: Preliminary Results

Introduction: Sentinel node mapping has been used for laryngeal carcinoma in several studies, with excellent results thus far.In the current study, we report our preliminary results on sentinel node mapping in laryngeal carcinoma using intra-operative peri-tumoral injection of a radiotracer.   Materials and Methods: Patients with biopsy-proven squamous cell carcinoma of the larynx were included...

متن کامل

HMMs and GMMs based methods for acoustic - to - articulatory speech inversion

Afin de récupérer les mouvements des articulateurs tels que les lèvres, la mâchoire ou la langue, à partir du son de parole, nous avons développé et comparé deux méthodes d’inversion basées l’une sur les modèles de Markov cachés (HMMs) et l’autre sur les modèles de mélanges de gaussiennes (GMMs). Les mouvements des articulateurs sont caractérisés par les coordonnées médiosagittales de bobines d...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009