Accuracy Assessment for AG500, Electromagnetic Articulograph

Yunusova, Yana; Green, Jordan R.; Mefferd, Antje S.

doi:10.1044/1092-4388(2008/07-0218)

Cited by 88 publications

(52 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EMA is the source of kinematic data used in our experiments next. Here, the positions of the tongue, lips, and other articulators can be accurately inferred at a rate of 200 Hz to within 0.5 mm [26] relative to fixed transmitters around the speaker's head that produce alternating magnetic fields. These systems produce no audible noise, and the coils do not interfere with regular speech.…”

Section: B Representations For Speech Productionmentioning

confidence: 99%

Articulatory Knowledge in the Recognition of Dysarthric Speech

Rudzicz

2011

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-Disabled speech is not compatible with modern generative and acoustic-only models of speech recognition (ASR). This work considers the use of theoretical and empirical knowledge of the vocal tract for atypical speech in labeling segmented and unsegmented sequences. These combined models are compared against discriminative models such as neural networks, support vector machines, and conditional random fields. Results show significant improvements in accuracy over the baseline through the use of production knowledge. Furthermore, although the statistics of vocal tract movement do not appear to be transferable between regular and disabled speakers, transforming the space of the former given knowledge of the latter before retraining gives high accuracy. This work may be applied within components of assistive software for speakers with dysarthria.

show abstract

Section: B Representations For Speech Productionmentioning

confidence: 99%

Articulatory Knowledge in the Recognition of Dysarthric Speech

Rudzicz

2011

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Compared with X-ray and MRI, EMA is much more affordable while maintaining high resolution. The spatial precision of motion tracking using EMA (AG500) is approximately 0.5 mm [10]. The subject with attached sensors was seated with her head within an electromagnetic cube.…”

Section: A Participant Stimuli Device and Proceduresmentioning

confidence: 99%

“…Without tongue information, a high recognition accuracy (e.g., greater than 90%) is unlikely. Fortunately, recently developed electromagnetic articulography devices provide a reasonably affordable, noninvasive, and accurate way to track the 3D motions of tongue [10].…”

Section: Introductionmentioning

confidence: 99%

Vowel recognition from continuous articulatory movements for speaker-dependent applications

Wang

Green

Samal

et al. 2010

2010 4th International Conference on Signal Processing and Communication Systems

Self Cite

View full text Add to dashboard Cite

Abstract-A novel approach was developed to recognize vowels from continuous tongue and lip movements. Vowels were classified based on movement patterns (rather than on derived articulatory features, e.g., lip opening) using a machine learning approach. Recognition accuracy on a single-speaker dataset was 94.02% with a very short latency. Recognition accuracy was better for high vowels than for low vowels. This finding parallels previous empirical findings on tongue movements during vowels. The recognition algorithm was then used to drive an articulation-to-acoustics synthesizer. The synthesizer recognizes vowels from continuous input stream of tongue and lip movements and plays the corresponding sound samples in near real-time.

show abstract

“…Unlike the optical motion tracking that is used to record external, facial structures, the electromagnetic technology provides a way to accurately track tongue movements during speech 11 .The system uses a combination of 5 and 6-degree-of-freedom (5DOF and 6DOF) sensors to record articulatory motions in a calibrated volume (30 x 30 x 30 cm). Movement data and acoustic data are acquired simultaneously.…”

Section: Articulatory Subsystem: Tonguementioning

confidence: 99%

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis (ALS)

Yunusova¹,

Green²,

Wang³

et al. 2011

JoVE

Self Cite

View full text Add to dashboard Cite

Improved methods for assessing bulbar impairment are necessary for expediting diagnosis of bulbar dysfunction in ALS, for predicting disease progression across speech subsystems, and for addressing the critical need for sensitive outcome measures for ongoing experimental treatment trials. To address this need, we are obtaining longitudinal profiles of bulbar impairment in 100 individuals based on a comprehensive instrumentation-based assessment that yield objective measures. Using instrumental approaches to quantify speech-related behaviors is very important in a field that has primarily relied on subjective, auditory-perceptual forms of speech assessment 1 . Our assessment protocol measures performance across all of the speech subsystems, which include respiratory, phonatory (laryngeal), resonatory (velopharyngeal), and articulatory. The articulatory subsystem is divided into the facial components (jaw and lip), and the tongue. Prior research has suggested that each speech subsystem responds differently to neurological diseases such as ALS. The current protocol is designed to test the performance of each speech subsystem as independently from other subsystems as possible. The speech subsystems are evaluated in the context of more global changes to speech performance. These speech system level variables include speaking rate and intelligibility of speech.The protocol requires specialized instrumentation, and commercial and custom software. The respiratory, phonatory, and resonatory subsystems are evaluated using pressure-flow (aerodynamic) and acoustic methods. The articulatory subsystem is assessed using 3D motion tracking techniques. The objective measures that are used to quantify bulbar impairment have been well established in the speech literature and show sensitivity to changes in bulbar function with disease progression. The result of the assessment is a comprehensive, across-subsystem performance profile for each participant. The profile, when compared to the same measures obtained from healthy controls, is used for diagnostic purposes. Currently, we are testing the sensitivity and specificity of these measures for diagnosis of ALS and for predicting the rate of disease progression. In the long term, the more refined endophenotype of bulbar ALS derived from this work is expected to strengthen future efforts to identify the genetic loci of ALS and improve diagnostic and treatment specificity of the disease as a whole. The objective assessment that is demonstrated in this video may be used to assess a broad range of speech motor impairments, including those related to stroke, traumatic brain injury, multiple sclerosis, and Parkinson disease.

show abstract

Accuracy Assessment for AG500, Electromagnetic Articulograph

Cited by 88 publications

References 9 publications

Articulatory Knowledge in the Recognition of Dysarthric Speech

Articulatory Knowledge in the Recognition of Dysarthric Speech

Vowel recognition from continuous articulatory movements for speaker-dependent applications

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis (ALS)

Contact Info

Product

Resources

About