As new approaches toward clean-slate network transport continue to emerge in the wireless domain and beyond, so grows the difficulty of conducting reproducible, head-to-head evalu...
Remote execution can transform the puniest mobile device into a computing giant able to run resource-intensive applications such as natural language translation, speech recognitio...
Maximum-Likelihod Linear Regression (MLLR) transform coefficients have shown to be useful features for text-independent speaker recognition systems. These use MLLR coefficients ...
In prior work, we have proposed techniques to extend the ease of shared-memory parallel programming to distributed-memory platforms by automatic translation of OpenMP programs to ...
A sound source separation technique based on a bio-inspired neural network, capable of functioning in more than two-source mixtures, is proposed. Separation results are compared wi...