Publications
-
Adaptive and Discriminative Modeling for Improved Mispronunciation Detection
In the context of computer-aided language learning, automatic detection of specific phone mispronunciations by nonnative speakers can be used to provide detailed feedback about specific pronunciation problems.
-
Simplified VTS-Based I-Vector Extraction in Noise-Robust Speaker Recognition
In this work, we propose an efficient simplification scheme, named sVTS, in order to show that the VTS approach gives improvements in large scale applications compared to state-of-the-art systems.
-
Uncovering Cryptic Glycan Markers in Multiple Sclerosis (MS) and Experimental Autoimmune Encephalomyelitis (Eae)
We observed epitope-spreading of autoantibody responses to a variety of antigenic structures in the cerebrospinal fluid (CSF) of patients with multiple sclerosis (MS) and in the serum of mice with…
-
Clock Synchronization on the RAX Spacecraft
The Radio Aurora Explorer (RAX) is a CubeSat that was developed to study space weather in Earth׳s ionosphere. Accuracy of the onboard clock is critical for processing the radar measurements.
-
Highly Accurate Phonetic Segmentation Using Correction Models and System Fusion
We investigate techniques for boosting the accuracy of automatic phonetic segmentation based on HMM acoustic-phonetic models.
-
Medium-Duration Modulation Cepstral Feature for Robust Speech Recognition
In this paper, we present the Modulation of Medium Duration Speech Amplitude feature, which is a composite feature capturing subband speech modulations and a summary modulation.
-
NV-CMOS HD Camera for Day/Night Imaging
SRI International (SRI) has developed a new multi-purpose day/night video camera with low-light imaging performance comparable to an image intensifier, while offering the size, weight, ruggedness, and cost advantages enabled…
-
Articulatory features from neural networks and their role in speech recognition
This paper presents a deep neural network (DNN) to extract articulatory information from the speech signal and explores different ways to use such information in a continuous speech recognition task.
-
Feature Fusion for High-Accuracy Keyword Spotting
This paper assesses the role of robust acoustic features in spoken term detection (a.k.a keyword spotting—KWS) under heavily degraded channel and noise corrupted conditions.
-
Submodular Subset Selection for Large-Scale Speech Training Data
We address the problem of subselecting a large set of acoustic data to train automatic speech recognition (ASR) systems. To this end, we apply a novel data selection technique based…
-
Design, Development, Implementation, and on-Orbit Performance of the Dynamic Ionosphere Cubesat Experiment Mission
The Dynamic Ionosphere CubeSat Experiment (DICE) mission consists of two 1.5U CubeSats which were launched into an eccentric low Earth orbit on October 28, 2011.
-
Emotion Detection in Speech Using Deep Networks
We propose a novel staged hybrid model for emotion detection in speech. Hybrid models exploit the strength of discriminative classifiers along with the representational power of generative models.