The Pulse Transit Time (PTT) is generally assumed to be a good surrogate measure to comfortably track blood pressure (BP) and blood pressure changes. This paper investigates PTT variations for healthy young subjects during a sequence of short-term physical exercises. PTT was measured by two different methodologies having different measurement accuracies as well as underlying assumptions: the total PTT from heart to fingertip and the difference of fingertip and earlobe PTTs. Small non consistent changes and very low correlation of both PTTs with systolic blood pressure (SBP) have been observed for the study population (-0.19 ± 0.45 and 0.22 ± 0.46). In conclusion, there might be a need for an improved measurement accuracy of the sensors and data processing techniques in use. The applicability of the Moens-Korteweg equation is also questionable for young people having flexible arteries. In this case, significant radius changes do occur in the large arteries during exercise, which might counteract a PTT decrease with the BP elevation. These radius effects are excluded from the Moens-Korteweg model.
To automatically evaluate the performance of children reading aloud or to follow a child's reading in reading tutor applications, different types of reading disfluencies and mispronunciations must be accounted for. In this work, we aim to detect most of these disfluencies in sentence and pseudoword reading. Detecting incorrectly pronounced words, and quantifying the quality of word pronunciations, is arguably the hardest task. We approach the challenge as a two-step process. First, a segmentation using task-specific lattices is performed, while detecting repetitions and false starts and providing candidate segments for words. Then, candidates are classified as mispronounced or not, using multiple features derived from likelihood ratios based on phone decoding and forced alignment, as well as additional meta-information about the word. Several classifiers were explored (linear fit, neural networks, support vector machines) and trained after a feature selection stage to avoid overfitting. Improved results are obtained using feature combination compared to using only the log likelihood ratio of the reference word (22% versus 27% miss rate at constant 5% false alarm rate).
This paper describes a low-resource approach to a Query-by-Example task, where spoken queries must be matched in a large dataset of spoken documents sometimes in complex or nonexact ways. Our approach tackles these complex match cases by using Dynamic Time Warping to obtain alternative paths that account for reordering of words, small extra content and small lexical variations. We also report certain advances on calibration and fusion of subsystems that improve overall results, such as manipulating the score distribution per query and using an average posteriorgram distance matrix as an extra subsystem. Results are evaluated on the MediaEval task of Query-by-Example Search on Speech (QUESST). For this task, the language of the audio being searched is almost irrelevant, approaching the use case scenario to a language of very low resources. For that, we use as features the posterior probabilities obtained from five phonetic recognizers trained with five different languages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.