Speech recognition, by both humans and machines, benefits from visual observation of the face, especially at low signal-to-noise ratios (SNRs). It has often been noticed, however, that the audible and visible correlates of a phoneme may be asynchronous; perhaps for this reason, automatic speech recognition structures that allow asynchrony between the audible phoneme and the visible viseme outpe...

The authors present a visual articulation model for speech synthesis and a method to obtain it from measured data. This visual articulation model is integrated into MASSY, the Modular Audiovisual Speech SYnthesizer, and used to control visible articulator movements described by six motion parameters: one for the up-down movement of the lower jaw, three for the lips and two for the tongue. The v...

This paper presents a method for determining the vocaltract spectrum from the positions of xed points on the articulatory organs. The method is based on the search of a database comprised of pairs of articulatory and acoustic data representing the direct relationship between the articulator position and vocal-tract spectrum. To compile the database, the electro-magnetic articulograph (EMA) syst...

It has been shown that articulator movements during speech are adjusted along a number of spatiotemporal dimensions. For example, variations in the extent of lip, jaw, or tongue motion are associated with proportional changes in the respective articulators' peak velocity. Modifications in the timing of lip and jaw actions are apparently constrained, exhibiting relative timing covariation. Sylla...

The selection of effective articulatory features is an important component of tasks such as acoustic-to-articulator inversion and articulatory synthesis. Although it is common to use direct articulatory sensor measurements as feature variables, this approach fails to incorporate important physiological information such as palate height and shape and thus is not as representative of vocal tract ...

Papaspyridakos and Lal Papaspyridakos and Lal The dental literature is replete with techniques for registering maxillomandibular relationships and transferring them accurately to the articulator. For edentulous patients receiving implants, several methods have been described for articulating the definitive implant cast at the appropriate occlusal vertical dimension (OVD) in the centric relation...

Is there a need to apply phonetics in speech technology development? How can phonetic thinking influence the quality of the final product (synthesised speech, speech recognition)? What happens if phonetic aspects are not used? What branches of phonetics are used, and what is to be used in speech technology? How phonetic thinking can be embedded into the development procedure of a speech technol...

The Berkeley Phonetics Machine is a Linux virtual machine image produced and used by the UC Berkeley Phonology Lab as a platform for phonetic research. It contains a full data analysis stack based on Python and R and also specialized tools for phonetic research. The machine is designed as a flexible and productive platform for established and novel research agendas that can be easily shared and...

OF THE DISSERTATION Degrees of Incompleteness in Neutralization: Paradigm Uniformity in a Phonetics with Weighted Constraints