This paper describes the CMU submission to shared task 1 of SIGMORPHON 2017. The system is based on the multi-space variational encoder-decoder (MSVED) method of Zhou and Neubig (2017), which employs both continuous and discrete latent variables for the variational encoder-decoder and is trained in a semi-supervised fashion. We discuss some language-specific errors and present result analysis.

A 4096×2160p multiview video encoder chip is implemented on a 3.95mm×2.90mm die with 90nm CMOS technology. A view-parallel macroblock-interleaved scheduling with 8stage macroblock pipelined architecture achieves 212Mpixels/s throughput, which is 3.4× to 7.7× better than the state-of-the-art encoder chips. In addition, 94% on-chip SRAM area and 79% external system memory bandwidth are saved.

| In this paper, we propose a combined source and channel coding system for multimedia information sources, which outputs di erent kinds of information on a frame by frame basis. We use a source encoder which has several probability tables for each medium and a channel encoder which has several convolutional codes for unequal error protection. Computer simulation shows the performance of our sy...

Despite the fast growing implementation of brushless DC motor, the older brushed DC motor is still relevant in many commercial, industrial and hobbyist applications due to low-cost and simplicity. Many brushed DC motor applications require precise speed and position control, thus requiring a sensor feedback. Commonly a separate rotary encoder is required to provide speed and positional feedback...

Latest developments in wearable devices permits un-damageable and cheapest way for gathering of medical data such as bio-signals like ECG, Respiration, Blood pressure etc. Gathering analysis various biomarkers are considered to provide anticipatory healthcare through customized applications purpose. Wearable will rely on size, resources battery capacity; we need a novel algorithm robustly contr...

We report the optical-coding operation of monolithic, ultra-compact optical-CDMA encoder and decoder pair, consisting of InP based integrated AWGs and phase modulators. The encoder and decoder successfully demonstrate eight-bit Walsh code based encoding and decoding. Introduction The Optical Code Division Multiple Access (O-CDMA) technology is a promising approach for future alloptical access n...

The output of a discrete Markov source is to be encoded instantaneously by a variable–rate encoder and decoded by a finite–state decoder. Our performance measure is a linear combination of the distortion and the instantaneous rate. Structure theorems, pertaining to the encoder and next–state functions are derived for every given finite–state decoder, which can have access to side information.