Search

This paper discusses the subject of pronunciation visualization, based on methodologies in experimental phonetics. It presents a brief survey of major Polish instrumental research into articulation, focusing primarily on contemporary dynamic visualizations using electromagnetic articulography. The author's own investigations were conducted using an AG 500 articulograph, a device which records and visualizes the working and movement of the articulatory organs. Two speakers were recorded: one with standard pronunciation and the other with articulation defects. A multi-specialist team prepared vocal tract models, taking into account the speaker's anatomical conditions as recorded with the articulograph, video recordings, and photographs. Articulographic data enabled the preparation of pronunciation animations of 45 words, which show the standard realization of all vowels and consonants of Polish, and eight animations of non-standard articulation. [ABSTRACT FROM AUTHOR]

• POLEMAD is the first relational database containing multimodal speech data for Polish language obtained from electromagnetic articulograph, multichannel audio recorder and stereoscopic vision system. • Containing speech samples from 20 subjects, the database is one of the largest datasets of this type in the world. • A new type of images obtained from an acoustic camera is stored in the POLEMAD database. • The database can facilitate experiments on speech inversion including dynamic Bayesian networks. The structure and functionality of the POLEMAD database constructed on the basis of a study using Electromagnetic Articulograph AG 500, an acoustic camera, and 3 video cameras are described in the paper. The article describes also data types stored in the database including speaker data, EMA data, video and sound recordings, phonetic information, and dynamic Bayesian network (DBN) models. The database allows for selective extraction of various types of samples for further analysis, which is performed by SQL queries generated in MATLAB® using Database Toolbox™. The possibilities of potential future application of the database in statistical analysis and automation of experiments on speech inversion using DBN are described in the paper as well. Image, graphical abstract [ABSTRACT FROM AUTHOR]