Publications
-
Coping with Unseen Data Conditions: Investigating Neural Net Architectures, Robust Features, and Information Fusion for Robust Speech Recognition
This work investigates the performance of traditional deep neural networks under varying acoustic conditions and evaluates their performance with speech recorded under realistic background conditions that are mismatched with respect…
-
On the Issue of Calibration in DNN-Based Speaker Recognition Systems
This article is concerned with the issue of calibration in the context of Deep Neural Network (DNN) based approaches to speaker recognition. We propose a hybrid alignment framework, which stems…
-
The 2016 Speakers in the Wild Speaker Recognition Evaluation
This article provides details of the SITW speaker recognition challenge and analysis of evaluation results. We provide an analysis of some of the top performing systems submitted during the evaluation and…
-
The SRI CLEO Speaker-State Corpus
We introduce the SRI CLEO (Conversational Language about Everyday Objects) Speaker-State Corpus of speech, video, and biosignals.
-
Unsupervised Learning of Acoustic Units Using Autoencoders and Kohonen Nets
This work investigates learning acoustic units in an unsupervised manner from real-world speech data by using a cascade of an autoencoder and a Kohonen net.
-
Fusion Strategies for Robust Speech Recognition and Keyword Spotting for Channel- and Noise-Degraded Speech
Current state-of-the-art automatic speech recognition systems are sensitive to changing acoustic conditions, which can cause significant performance degradation.
-
Intelligent Coaching Systems in Higher-Order Applications: Lessons from Automated Content Creation Bottlenecks
This presentation describes two projects for interactive training that developed prototypes for automated content creation plus a third project that illustrates a suite of learning object libraries to support engineering…
-
Minimizing Annotation Effort for Adaptation of Speech-Activity Detection Systems
This paper focuses on the problem of selecting the best-possible subset of available audio data given a budgeted time for annotation.
-
The SRI speech-based collaborative learning corpus
We introduce the SRI speech-based collaborative learning corpus, a novel collection designed for the investigation and measurement of how students collaborate together in small groups.
-
The SRI System for the NIST OpenSAD 2015 Speech Activity Detection Evaluation
In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation. We present results on three different development databases that we created…
-
Course-Taking Effect on Postsecondary Enrollment of Deaf and Hard of Hearing Students
Data from the National Longitudinal Transition Study-2 were used to examine the effect of academic and career or technical education course-taking in high school on deaf or hard of hearing…
-
Integrated Digital Printing of Flexible Circuits for Wireless Sensing
At PARC, we combine high functionality c-Si CMOS and digitally printed components and interconnects to create an integrated platform that can read and process multiple discrete sensors.