Author: SRI International
-
Within-Class Covariance Normalization for SVM-based Speaker Recognition
This paper extends the within-class covariance normalization (WCCN) technique described for training generalized linear kernels.
-
Assessing Local Item Dependence In Building Explanation Tasks (Padi Technical Report 14)
A common practice in the assessment of science education is to have a shared stimulus followed by a number of questions. In these cases, one might doubt the usual assumption of standard Item Response Theory of local item independence among items that are supposed to measure the same latent proficiency. As an anticipated violation of…
-
QASR: Question Answering Using Semantic Roles for Speech Interface
In this paper, we evaluate a semantic role labeling approach to the extraction of answers in the open domain question answering task. We show that this technique especially improves the system performance when answers are communicated to the user by voice.
-
Investigation on Mandarin Broadcast News Speech Recognition
This paper describes our efforts in building a competitive Mandarin broadcast news speech recognizer. We present two novel algorithms in smoothing pitch features and segmenting Chinese characters into word units.
-
Globe Year 10 Evaluation: Into The Next Generation
This is the 10th in a series of annual evaluation reports that SRI has submitted to the GLOBE Program since the Program’s inception in 1995.
-
Speaker Clustered Regression-Class Trees for MLLR Adaptation
A speaker clustering algorithm is presented that is based on an eigenspace representation of Maximum Likelihood Linear Regression (MLLR) transformations and is used for training cluster-dependent regression-class trees for MLLR adaptation.
-
Improved Speech Activity Detection Using Cross-Channel Features for Recognition of Multiparty Meetings
We describe the development of a speech activity detection system using an HMM-based segmenter for automatic speech recognition on individual headset microphones in multispeaker meetings. We look at cross-channel features (energy and correlation based) to incorporate into the segmenter for the purpose of addressing errors related to cross-channel phenomena such as crosstalk.
-
Enriching Speech Recognition with Automatic Detection of Sentence Boundaries and Disfluencies
This paper describes a metadata detection system that combines information from different types of textual knowledge sources with information from a prosodic classifier. We investigate maximum entropy and conditional random field models, in addition to the predominant HMM approach, and find that discriminative models generally provide benefit over generative models.
-
A Heritage of Innovation: SRI’s First Half Century
From its beginnings at Stanford University, where it was intended to serve industry in the Western United States, SRI has grown to a worldwide research organization.
-
Proving Authentication Properties in the Protocol Derivation Assistant
In the present paper, we introduce an axiomatic theory of authentication suitable for the automatic proof of authentication properties. We describe a proof of the authentication property of a simple protocol, as derived in Pda, for which the the proof obligations have been automatically generated and discharged.
-
Fighting the Wrong Battle in the Teacher Preparation Wars
SRI conducted a comprehensive study of alternative teacher certification programs to determine the characteristics of those that were effective.
-
Build IT: Girls Developing Information Technology Fluency Through Design. Annual Report Year 1
The goals for the first year of the Build IT project were to develop and implement the three units of the curriculum at four school sites reaching a total of 60 girls in sixth and seventh grade in order to begin to achieve the above three programmatic goals.