Publications
-
Using Prosodic and Spectral Features in Detecting Depression in Elderly Males
In this study, we focus on speech features that can identify the speaker’s emotional health, i.e., whether the speaker is depressed or not.
-
Sensitivity to Secondhand Smoke Exposure Predicts Future Smoking Susceptibility
This study investigated whether sensitivity to secondhand smoke exposure (SHSe) contributes to smoking susceptibility.
-
Automatic detection of speaker attributes based on utterance text
We present models for detecting various attributes of a speaker based on uttered text alone.
-
Effective Arabic dialect classification using diverse phonotactic models
We study the effectiveness of recently developed language recognition techniques based on speech recognition models for the discrimination of Arabic dialects.
-
iVector fusion of prosodic and cepstral features for speaker verification
In this paper we apply the promising iVector extraction technique followed by PLDA modeling to simple prosodic contour features.
-
Identifying Agreement and Disagreement in Conversational Speech: A Cross-lingual Study
This paper presents models for detecting agreement/disagreement between speakers in English and Arabic broadcast conversation shows.
-
Nonprofit Pharma: Solutions to What Ails the Industry
To provide a perspective on NPO business models, a number of SRI case studies spanning a broad range of technical and business initiatives will be summarized.
-
Drug Targets for Cognitive Enhancement in Neuropsychiatric Disorders
The investigation of novel drug targets for treating cognitive impairments associated with neurological and psychiatric disorders remains a primary focus of study in central nervous system (CNS) research.
-
Atmospheric Ionization Module Osnabruck (AIMOS): 3. Comparison of Electron Density Simulations By AIMOS-HAMMONIA and Incoherent Scatter Radar Measurements
We evaluate numerical simulations of the 3-D spatial and temporal electron densities produced by these particle populations through a comparison with incoherent scatter radar observations.
-
Factor analysis back ends for MLLR transforms in speaker recognition
The purpose of this work is to show how recent developments in cepstral-based systems for speaker recognition can be leveraged for the use of Maximum Likelihood Linear Regression (MLLR) transforms.
-
Printed electronics
Recent developments have enabled the fabrication of electronic devices using additive printing techniques rather than subtractive photolithography.
-
Language matters in Twitter: a large scale study
We studied 62 million tweets collected over a four-week period and found that more than 100 languages were used.