Author: SRI International
-
Significance of Joint Features Derived from the Modified Group Delay Function in Speech Processing
This paper investigates the significance of combining cepstral features derived from the modified group delay function and from the short-time spectral magnitude like the MFCC.
-
The ICSI-SRI Spring 2006 Meeting Recognition System
We describe the development of the ICSI-SRI speech recognition system for the NIST Spring 2006 Meeting Rich Transcription (RT-06S) evaluation, highlighting improvements, including the delay-and-sum algorithm, the nearfield segmenter, language models, posterior-based features, HMM adaptation methods, and adapting to a small amount of new lecture data.
-
A Web Based Authoring Tool for Intelligent Tutors: Blending Assessment And Instructional Assistance
To help teachers make better use of their time, we are integrating assistance and assessment by utilizing a web-based system (“Assistment”) that will offer instruction to students while providing a more detailed evaluation of their abilities to the teacher than is possible under current approaches.
-
Scan Rate: A new metric for the analysis of reading behaviours in asynchronous computer conferencing environments
This article introduces a new computer conferencing metric called Scan Rate, which is a measure of students’ and instructors’ online reading speed.
-
National Early Intervention Longitudinal Study (NEILS) Final Report
This National Early Intervention Longitudinal Study (NEILS) report presents the key findings from a national longitudinal study. This report summarizes some of the key findings from this 10-year study and notes their implications for policy, practice, and additional research.
-
A Categorization of Explanation Questions for Task Processing Systems
In this paper we propose a categorization of question types relevant to explaining task processing. For each question type, we also propose alternative explanation strategies for answering them.
-
Model Adaptation for Dialog Act Tagging
In this study we used the ICSI meeting corpus with high-level meeting recognition dialog act (MRDA) tags, that is, question, statement, backchannel, disruptions, and floor grabbers/holders. We performed controlled adaptation experiments using the Switchboard (SWBD) corpus with SWBD-DAMSL tags as the out-of-domain corpus.
-
Teaching and California’s Future: California’s Teaching Force 2006: Key Issues and Trends
This annual report discusses trends in the supply, demand, and distribution of California teachers; details the impact of state policy changes on the teacher development system; and highlights themes that emerge from these new policies and programs and assesses the adequacy of the state’s efforts.
-
Model Adaptation for Sentence Segmentation from Speech
This paper analyzes various methods to adapt sentence segmentation models trained on conversational telephone speech (CTS) to meeting style conversations. The sentence segmentation model trained using a large amount of CTS data is used to improve the performance when various amounts of meeting data are available.
-
A Study in Machine Learning from Imbalanced Data for Sentence Boundary Detection in Speech
We have constructed a hidden Markov model (HMM) system to detect sentence boundaries that uses both prosodic and textual information. Since there are more non-sentence boundaries than sentence boundaries in the data, the prosody model, which is implemented as a decision tree classifier, must be constructed to effectively learn from the imbalanced data distribution.
-
Localization in Horizontal-Only Ambisonic Systems
We test the localization of horizontal-only Ambisonic reproduction systems using various test signals to separately evaluate low-frequency and mid-frequency localization.
-
Presentation of Information for Link Analysis
SRI’s LAW (Link Analysis Workbench) is a system that helps intelligence analysts detect occurrences of situations of interest by finding pattern instances in vast amounts of data using graph edit distance matching techniques.