1 |
DoD Enterprise Architecting: Joint Issues Derived From SOF Air Analysis
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
2 |
Using Prosody for Automatic Sentence Segmentation of Multi-Party Meetings
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
3 |
Tactical Digital Information Link-Technical Advice and Lexicon for Enabling Simulation (TADIL-TALES) II: Link 11/11B
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
7 |
Learning to Recognize Features of Valid Textual Entailments
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
8 |
A Methodology to Predict Specific Communication Themes from Overall Communication Volume for Individuals and Teams
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
9 |
Integrating Ontologies into Multiagent Systems Engineering
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
10 |
Toward an Interagency Language Roundtable Based Assessment of Speech-to-Speech Translation Capabilities
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
11 |
Dealing with Out of Domain Questions in Virtual Characters
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
12 |
Experimental Facility for Measuring the Impact of Environmental Noise and Speaker Variation on Speech-to-Speech Translation Devices
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
13 |
Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
14 |
Edge-Splitting in a Cumulative Multimodal System, for a No-Wait Temporal Threshold on Information Fusion, Combined with an Under-Specified Display
|
|
|
|
In: DTIC (2006)
|
|
Abstract:
Predicting the end of user input turns in a multimodal system can be complex. User interactions vary across a spectrum from single, unimodal inputs to multimodal combinations delivered either simultaneously or sequentially. Early multimodal systems used a fixed duration temporal threshold to determine how long to wait for the next input before processing and integration. Several recent studies have proposed using dynamic or adaptive temporal thresholds to predict turn segmentation and thus achieve faster system response times. We introduce an approach that requires no temporal threshold. First we contrast current multimodal command interfaces to a new class of cumulative-observant multimodal systems that we introduce. Within that new system class we show how our technique of edge-splitting combined with our strategy for under-specified, no-wait, visual feedback resolves parsing problems that underlie turn segmentation errors. Test results show a 46.2% significant reduction in multimodal recognition errors, compared to not using these techniques. ; Presented at the International Conference on Spoken Language Processing (9th), Interspeech2006-ICSLP, held in Pittsburg, PA, on 17-21 Sep 2006 and to be published in proceedings. The original document contains color images.
|
|
Keyword:
*PARSERS; *SPEECH; COMPUTATIONAL LINGUISTICS; CUMULATIVE-OBSERVANT MULTIMODAL INTERFACE; Cybernetics; EDGE-SPLITTING; FEEDBACK; HANDWRITING; Linguistics; MAN COMPUTER INTERFACE; SYMPOSIA; TURN SEGMENTATION; UNDER SPECIFIED DISPLAY
|
|
URL: http://www.dtic.mil/docs/citations/ADA454818 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA454818
|
|
BASE
|
|
Hide details
|
|
15 |
On Speaker-Specific Prosodic Models for Automatic Dialog Act Segmentation of Multi-Party Meetings
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
16 |
Using Linguistic Analysis to Identify High Performing Teams
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
19 |
Text Analysis Using Automated Language Translators
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
20 |
The 2005 AFRL/HEC One-Speaker Detection Systems
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
|
|