Abstract-Advances in formulating spoken document retrieval for a new National Gallery of the Spoken Word (NGSW) are addressed. NGSW is the first large-scale repository of its kind, consisting of speeches, news broadcasts, and recordings from the 20th century. After presenting an overview of the audio stream content of the NGSW, with sample audio files from U.S. Presidents from 1893 to the present, an overall system diagram is proposed with a discussion of critical tasks associated with effective audio information retrieval. These include advanced audio segmentation, speech recognition model adaptation for acoustic background noise and speaker variability, and information retrieval using natural language processing for text query requests that include document and query expansion. For segmentation, a new evaluation criterion entitled fused error score (FES) is proposed, followed by application of the CompSeg segmentation scheme on DARPA Hub4 Broadcast News (30.5% relative improvement in FES) and NGSW data. Transcript generation is demonstrated for a six-decade portion of the NGSW corpus. Novel model adaptation using structure maximum likelihood eigenspace mapping shows a relative 21.7% improvement. Issues regarding copyright assessment and metadata construction are also addressed for the purposes of a sustainable audio collection of this magnitude. Advanced parameter-embedded watermarking is proposed with evaluations showing robustness to correlated noise attacks. Our experimental online system entitled "SpeechFind" is presented, which allows for audio retrieval from a portion of the NGSW corpus. Finally, a number of research challenges such as language modeling and lexicon for changing time periods, speaker trait and identification tracking, as well as new directions, are discussed in Manuscript

In this paper, we propose a new framework for discriminating the initial maneuver of a lane-crossing event from a driver correction event, which is the primary reason for false warnings of lane departure prediction systems (LDPSs). The proposed algorithm validates the beginning episode of the trajectory of driving signals, i.e., whether it will cause a lane-crossing event, by employing driver behavior models of the directional sequence of piecewise lateral slopes (DSPLS) representing lane-crossing and driver correction events. The framework utilizes only common driving signals and allows the adaptation scheme of driver behavior models to better represent individual driving characteristics. The experimental evaluation shows that the proposed DSPLS framework has a detection error with as low as a 17% equal error rate. Furthermore, the proposed algorithm reduces the false-warning rate of the original lane departure prediction system with less tradeoff for the correct prediction.Index Terms-Driver adaptation, driver behavior model, lane departure, nuisance warning, time to line crossing (TLC).

No abstract

No abstract

No abstract