Data-driven analysis of realtime vocal tract MRI using correlated image regions

Adam C. Lammert*, Michael I. Proctor, Shrikanth S. Narayanan

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

42 Citations (Scopus)

Abstract

Realtime MRI provides useful data about the human vocal tract, but also introduces many of the challenges of processing high-dimensional image data. Intuitively, data reduction would proceed by finding the air-tissue boundaries in the images, and tracing an outline of the vocal tract. This approach is anatomically well-founded. We explore an alternative approach which is data-driven and has a complementary set of advantages. Our method directly examines pixel intensities. By analyzing how the pixels co-vary over time, we segment the image into spatially localized regions, in which the pixels are highly correlated with each other. Intensity variations in these correlated regions correspond to vocal tract constrictions, which are meaningful units of speech production. We show how these regions can be extracted entirely automatically, or with manual guidance. We present two examples and discuss its merits, including the opportunity to do direct data-driven time series modeling.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Place of PublicationBaixas, France
PublisherInternational Speech Communication Association
Pages1572-1575
Number of pages4
ISBN (Print)9781617821233
Publication statusPublished - 2010
Externally publishedYes
Event11th Annual Conference of the International-Speech-Communication-Association 2010 - Makuhari, Japan
Duration: 26 Sep 201030 Sep 2010

Conference

Conference11th Annual Conference of the International-Speech-Communication-Association 2010
CountryJapan
CityMakuhari
Period26/09/1030/09/10

Fingerprint Dive into the research topics of 'Data-driven analysis of realtime vocal tract MRI using correlated image regions'. Together they form a unique fingerprint.

Cite this