SUMMARY: To expedite the review of semi-automated probability maps of organelles and other features from 3D electron microscopy data we have developed Probability Map Viewer, a Java-based web application that enables the computation and visualization of probability map generation results in near real-time as the data are being collected from the microscope. Probability Map Viewer allows the user to select one or more voxel classifiers, apply them on a sub-region of an active collection, and visualize the results as overlays on the raw data via any web browser using a personal computer or mobile device. Thus, Probability Map Viewer accelerates and informs the image analysis workflow by providing a tool for experimenting with and optimizing dataset-specific segmentation strategies during imaging. AVAILABILITY AND IMPLEMENTATION: https://github.com/crbs/probabilitymapviewer. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We present MPtracker, a new algorithm for tracking and separating the pitch frequencies of two speakers from their mixture. The pitch frequencies are detected by introducing a novel spectral distortion optimization which takes into account the sinusoidal modeling of the speech signal. The detected pitch frequencies are grouped, separated, and finally an interpolation method is applied to estimate missing pitch frequencies. We evaluated the performance of the proposed technique on 196 mixtures including 48 male-male, 48 female-female, and 96 male-female mixtures with target-to-interference ratios (TIR) ranging from 0 dB to +18 dB. The results show our simple but effective and fast technique significantly outperforms two widely-used approaches.

In model-based single channel speech separation, factorial hidden Markov models (FHMM) have been successfully applied to model the mixture signal Y(t) = X(t) + V(t) in terms of trained patterns of the speech signals X(t) and V(t). Nonetheless, when the test signals are scaled versions of the trained patterns (i.e. gxX(t) and gvV(t)), the performance of FHMM degrades significantly. In this paper, we introduce a modification to FHMM, called scaled FHMM, which compensates gain difference. In this technique, first, the scale factors are expressed in terms of the target-to-interference ratio (TIR). Then, an iteration quadratic optimization approach is coupled with FHMM to estimate TIR which with the decoded HMM sequences maximize the likelihood of the mixture signal. Experimental results, conducted on 180 mixtures with TIRs from 0 to 15 dB, show that the proposed technique significantly outperforms unscaled FHMM, and scaled/unscaled vector quantization speech separation techniques.

A major problem with speech recognition interfaces is the detection and correct rejection of words that lie outside of the command vocabulary. Given the limited resources provided to an interface, any method that is used to detect out-of-vocabulary (OOV) words should ideally require minimal computational resources. A new utterance verifier is proposed which detects OOV words efficiently using confidence measures calculated for additional words in the N-best list. This approach can be used with any existing confidence measure. We implement this utterance verifier with three different confidence measures and obtain a 3-16% improvement over their standard implementation.