The QUT-NOISE-SRE protocol for the evaluation of noisy speaker recognition

The QUT-NOISE-SRE protocol is designed to mix the large QUT-NOISE database, consisting of over 10 hours of back- ground noise, collected across 10 unique locations covering 5 common noise scenarios, with commonly used speaker recognition datasets such as Switchboard, Mixer and the speaker recognition evaluation (SRE) datasets provided by NIST. By allowing common, clean, speech corpora to be mixed with a wide variety of noise conditions, environmental reverberant responses, and signal-to-noise ratios, this protocol provides a solid basis for the development, evaluation and benchmarking of robust speaker recognition algorithms, and is freely available to download alongside the QUT-NOISE database. In this work, we use the QUT-NOISE-SRE protocol to evaluate a state-of-the-art PLDA i-vector speaker recognition system, demonstrating the importance of designing voice-activity-detection front-ends specifically for speaker recognition, rather than aiming for perfect coherence with the true speech/non-speech boundaries.

Brain activity during the encoding, retention, and retrieval of stimulus representations

Studies of delayed nonmatching-to-sample (DNMS) performance following lesions of the monkey cortex have revealed a critical circuit of brain regions involved in forming memories and retaining and retrieving stimulus representations. Using event-related functional magnetic resonance imaging (fMRI), we measured brain activity in 10 healthy human participants during performance of a trial-unique visual DNMS task using novel barcode stimuli. The event-related design enabled the identification of activity during the different phases of the task (encoding, retention, and retrieval). Several brain regions identified by monkey studies as being important for successful DNMS performance showed selective activity during the different phases, including the mediodorsal thalamic nucleus (encoding), ventrolateral prefrontal cortex (retention), and perirhinal cortex (retrieval). Regions showing sustained activity within trials included the ventromedial and dorsal prefrontal cortices and occipital cortex. The present study shows the utility of investigating performance on tasks derived from animal models to assist in the identification of brain regions involved in human recognition memory.

fMRI evidence of word frequency and strength effects in recognition memory

We used event-related fMRI to investigate the neural correlates of encoding strength and word frequency effects in recognition memory. At test, participants made Old/New decisions to intermixed low (LF) and high frequency (HF) words that had been presented once or twice at study and to new, unstudied words. The Old/New effect for all hits vs. correctly rejected unstudied words was associated with differential activity in multiple cortical regions, including the anterior medial temporal lobe (MTL), hippocampus, left lateral parietal cortex and anterior left inferior prefrontal cortex (LIPC). Items repeated at study had superior hit rates (HR) compared to items presented once and were associated with reduced activity in the right anterior MTL. By contrast, other regions that had shown conventional Old/New effects did not demonstrate modulation according to memory strength. A mirror effect for word frequency was demonstrated, with the LF word HR advantage associated with increased activity in the left lateral temporal cortex. However, none of the regions that had demonstrated Old/New item retrieval effects showed modulation according to word frequency. These findings are interpreted as supporting single-process memory models proposing a unitary strength-like memory signal and models attributing the LF word HR advantage to the greater lexico-semantic context-noise associated with HF words due to their being experienced in many pre-experimental contexts.

Nanostructured hydroxyapatite surfaces-mediated adsorption alters recognition of BMP receptor IA and bioactivity of bone morphogenetic protein-2

Highly efficient loading of bone morphogenetic protein-2 (BMP-2) onto carriers with desirable performance is still a major challenge in the field of bone regeneration. Till now, the nanoscaled surface-induced changes of the structure and bioactivity of BMP-2 remains poorly understood. Here, the effect of nanoscaled surface on the adsorption and bioactivity of BMP-2 was investigated with a series of hydroxyapatite surfaces (HAPs): HAP crystal-coated surface (HAP), HAP crystal-coated polished surface (HAP-Pol), and sintered HAP crystal-coated surface (HAP-Sin). The adsorption dynamics of recombinant human BMP-2 (rhBMP-2) and the accessibility of the binding epitopes of adsorbed rhBMP-2 for BMP receptors (BMPRs) were examined by a quartz crystal microbalance with dissipation. Moreover, the bioactivity of adsorbed rhBMP-2 and the BMP-induced Smad signaling were investigated with C2C12 model cells. A noticeably high mass-uptake of rhBMP-2 and enhanced recognition of BMPR-IA to adsorbed rhBMP-2 were found on the HAP-Pol surface. For the rhBMP-2-adsorbed HAPs, both ALP activity and Smad signaling increased in the order of HAP-Sin < HAP < HAP-Pol. Furthermore, hybrid molecular dynamics and steered molecular dynamics simulations validated that BMP-2 tightly anchored on the HAP-Pol surface with a relative loosened conformation, but the HAP-Sin surface induced a compact conformation of BMP-2. In conclusion, the nanostructured HAPs can modulate the way of adsorption of rhBMP-2, and thus the recognition of BMPR-IA and the bioactivity of rhBMP-2. These findings can provide insightful suggestions for the future design and fabrication of rhBMP-2-based scaffolds/implants.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Decision trees for detection of activity intensity in youth with cerebral palsy

PURPOSE To develop and test decision tree (DT) models to classify physical activity (PA) intensity from accelerometer output and Gross Motor Function Classification System (GMFCS) classification level in ambulatory youth with cerebral palsy (CP); and 2) compare the classification accuracy of the new DT models to that achieved by previously published cut-points for youth with CP. METHODS Youth with CP (GMFCS Levels I - III) (N=51) completed seven activity trials with increasing PA intensity while wearing a portable metabolic system and ActiGraph GT3X accelerometers. DT models were used to identify vertical axis (VA) and vector magnitude (VM) count thresholds corresponding to sedentary (SED) (<1.5 METs), light PA (LPA) (>/=1.5 and <3 METs) and moderate-to-vigorous PA (MVPA) (>/=3 METs). Models were trained and cross-validated using the 'rpart' and 'caret' packages within R. RESULTS For the VA (VA_DT) and VM decision trees (VM_DT), a single threshold differentiated LPA from SED, while the threshold for differentiating MVPA from LPA decreased as the level of impairment increased. The average cross-validation accuracy for the VC_DT was 81.1%, 76.7%, and 82.9% for GMFCS levels I, II, and III, respectively. The corresponding cross-validation accuracy for the VM_DT was 80.5%, 75.6%, and 84.2%, respectively. Within each GMFCS level, the decision tree models achieved better PA intensity recognition than previously published cut-points. The accuracy differential was greatest among GMFCS level III participants, in whom the previously published cut-points misclassified 40% of the MVPA activity trials. CONCLUSION GMFCS-specific cut-points provide more accurate assessments of MVPA levels in youth with CP across the full spectrum of ambulatory ability.