Tandem system adaptation using multiple linear feature transforms

Adaptation to speaker and environment changes is an essential part of current automatic speech recognition (ASR) systems. In recent years the use of multi-layer percpetrons (MLPs) has become increasingly common in ASR systems. A standard approach to handling speaker differences when using MLPs is to apply a global speaker-specific constrained MLLR (CMLLR) transform to the features prior to training or using the MLP. This paper considers the situation when there are both speaker and channel, communication link, differences in the data. A more powerful transform, front-end CMLLR (FE-CMLLR), is applied to the inputs to the MLP to represent the channel differences. Though global, these FE-CMLLR transforms vary from time-instance to time-instance. Experiments on a channel distorted dialect Arabic conversational speech recognition task indicates the usefulness of adapting MLP features using both CMLLR and FE-CMLLR transforms. © 2013 IEEE.

On chip plasmonic enhanced silicon schottky detector for telecom wavelengths

We demonstrate an integrated on-chip plasmonic enhanced Schottky detector for telecom wavelengths based on the internal photoemission process. This CMOS compatible device may serve as a promising alternative to the Si-Ge detectors. © 2011 Optical Society of America.

Silicon-metal waveguide as a high efficiency schottky detector for telecom wavelengths

We demonstrate an integrated on-chip compact and high efficiency Schottky detector for telecom wavelengths based on silicon metal waveguide. Detection is based on the internal photoemission process. Theory and experimental results are discussed. © 2012 Optical Society of America.

Locally-oxidized silicon surface-plasmon Schottky detector for telecom wavelengths

We demonstrate an integrated on-chip locally-oxidized silicon surface-plasmon Schottky detector for telecom wavelengths based on the internal photoemission process. Theoretical model and experimental results will be presented and discussed. © 2011 Optical Society of America.

An extension of slow feature analysis for nonlinear blind source separation

We present and test an extension of slow feature analysis as a novel approach to nonlinear blind source separation. The algorithm relies on temporal correlations and iteratively reconstructs a set of statistically independent sources from arbitrary nonlinear instantaneous mixtures. Simulations show that it is able to invert a complicated nonlinear mixture of two audio signals with a high reliability. The algorithm is based on a mathematical analysis of slow feature analysis for the case of input data that are generated from statistically independent sources. © 2014 Henning Sprekeler, Tiziano Zito and Laurenz Wiskott.