Abstract: Large area, high current, lateral GaN power transistors are implemented using an on-chip interconnect topology wherein the transistor is arranged as an array of sections, each section comprising a set of transistor islands; gate and source buses that form each gate drive loop have substantially the same track widths; the source bus runs over or under the gate bus, and the tracks are inductively coupled to provide flux cancellation in the gate drive loop, thereby reducing parasitic inductances. The gate delay in each gate drive loop is reduced, minimizing the gate drive phase difference across the transistor. An overlying current redistribution layer preferably has a track width no greater than that of the underlying source and drain buses, for efficient coupling. This topology provides improved scalability, enabling fabrication of multi-section, large scale, high current lateral GaN transistors with reduced gate drive loop inductance, for improved operational stability.

Abstract: Large area, high current, lateral GaN power transistors are implemented using an on-chip interconnect topology wherein the transistor is arranged as an array of sections, each section comprising a set of transistor islands; gate and source buses that form each gate drive loop have substantially the same track widths; the source bus runs over or under the gate bus, and the tracks are inductively coupled to provide flux cancellation in the gate drive loop, thereby reducing parasitic inductances. The gate delay in each gate drive loop is reduced, minimizing the gate drive phase difference across the transistor. An overlying current redistribution layer preferably has a track width no greater than that of the underlying source and drain buses, for efficient coupling. This topology provides improved scalability, enabling fabrication of multi-section, large scale, high current lateral GaN transistors with reduced gate drive loop inductance, for improved operational stability.

Abstract: A computer-implemented method according to one embodiment includes estimating a speaker dependent acoustic model utilizing test speech data and maximum likelihood linear regression (MLLR), transforming labeled speech data to create transformed speech data, utilizing the speaker dependent acoustic model and a linear transformation, and adjusting a deep neural network (DNN) acoustic model, utilizing the transformed speech data.

Abstract: A computer-implemented method according to one embodiment includes estimating a speaker dependent acoustic model utilizing test speech data and a hybrid estimation technique, transforming labeled speech data to create transformed speech data, utilizing the speaker dependent acoustic model and a nonlinear transformation, and adjusting a deep neural network (DNN) acoustic model, utilizing the transformed speech data.

Abstract: A computer-implemented method according to one embodiment includes estimating a speaker dependent acoustic model utilizing test speech data and maximum likelihood linear regression (MLLR), transforming labeled speech data to create transformed speech data, utilizing the speaker dependent acoustic model and a linear transformation, and adjusting a deep neural network (DNN) acoustic model, utilizing the transformed speech data.

Abstract: A computer-implemented method according to one embodiment includes estimating a speaker dependent acoustic model utilizing test speech data and a hybrid estimation technique, transforming labeled speech data to create transformed speech data, utilizing the speaker dependent acoustic model and a nonlinear transformation, and adjusting a deep neural network (DNN) acoustic model, utilizing the transformed speech data.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: A method for adapting acoustic models used for automatic speech recognition is provided. The method includes estimating noise in a portion of a speech signal, determining a first estimated variance scaling vector using an estimated 2-order polynomial and the noise estimation. The estimated 2-order polynomial represents a prior knowledge of a dependency of a variance scaling vector on noise, determining a second estimated variance scaling vector using statistics from prior portions of the speech signal, determining a variance scaling factor using the first estimated variance scaling vector and the second estimated variance scaling vector, and using the variance scaling factor to adapt an acoustic model.

Abstract: A method for adapting acoustic models used for automatic speech recognition is provided. The method includes estimating noise in a portion of a speech signal, determining a first estimated variance scaling vector using an estimated 2-order polynomial and the noise estimation, wherein the estimated 2-order polynomial represents a priori knowledge of a dependency of a variance scaling vector on noise, determining a second estimated variance scaling vector using statistics from prior portions of the speech signal, determining a variance scaling factor using the first estimated variance scaling vector and the second estimated variance scaling vector, and using the variance scaling factor to adapt an acoustic model.

Abstract: The mismatch between the distributions of acoustic models and features in speech recognition may cause performance degradation. A sequential variance adaptation (SVA) adapts the covariances dynamically based on a sequential EM algorithm. The original covariances in acoustic models are adjusted by scaling factors which are sequentially updated once new collection data is available.

Abstract: The mismatch between the distributions of acoustic models and features in speech recognition may cause performance degradation. A sequential bias adaptation (SBA) applies state or class dependent biases to the original mean vectors in acoustic models to take into account the mismatch between features and the acoustic models.

Abstract: To make speech recognition robust in a noisy environment, variable parameter Gaussian Mixture HMM is described which extends existing HMMs by allowing HMM parameters to change as a function of a continuous variable that depends on the environment. Specifically, in one embodiment the function is a polynomial, the environment is described by signal-to-noise ratio. The use of the parameters functions improves the HMM discriminability during multi-condition training. In the recognition process, a set of HMM parameters is instantiated according to parameter functions, based on current environment. The model parameters are estimated using Expectation-Maximization algorithm for variable parameter GMHMM.

Abstract: Molecular electronic devices and method of making molecular electronic devices having a self-assembled ordered insulating molecular electronic film having insulating molecules attached at one end to a first electrode, and conducting device molecules inserted into the insulating molecular electronic film such that the device molecules are attached at the bottom end to a first electrode and the top end to a second electrode are provided.