Jason Davenport

Learn More
In this paper, we describe our recent work in fast automatic transcription of broadcast news programming from radio and television. Given our state-of-the-art BBN BYBLOS primary system [1] running at 230 times real time (230xRT) we show that eliminating and approximating many computationally expensive components speeds up the system by a factor of more than(More)
High-throughput screening of a library of diverse molecules has identified the 1,4-naphthoquinone scaffold as a new class of Hsp90 inhibitors. The synthesis and evaluation of a rationally-designed series of analogues containing the naphthoquinone core scaffold has provided key structure-activity relationships for these compounds. The most active inhibitors(More)
In this paper, we describe our recent signi cant progress in automatic transcription of broadcast news programming from radio and television, compared to that described in [1] at EuroSpeech97. Overall, we achieve a 42% relative word error rate reduction during the latest DARPA November 1998 Hub-4 Evaluation, in contrast to the 1996 evaluation result(More)
In this paper, we describe the BBN BYBLOS system used for the 1999 Hub-4E 10xRT evaluation benchmark, and discuss the improvements made to the system in 1999. We focus on the techniques that were new in this year’s system to achieve an optimal tradeoff between accuracy and speed for the evaluation benchmark test. Overall, we improved the recognition(More)
A high-throughput screening of natural product libraries identified (-)-gambogic acid (1), a component of the exudate of Garcinia harburyi, as a potential Hsp90 inhibitor, in addition to the known Hsp90 inhibitor celastrol (2). Subsequent testing established that 1 inhibited cell proliferation, brought about the degradation of Hsp90 client proteins in(More)
In this paper, we describe the BBN Byblos system used for the 1997 DARPA Hub-4 Broadcast News evaluation and discuss numerous improvements made to the system in 1997. We focused our e ort entirely upon the two conditions containing studio-quality uncorrupted speech from native speakers, the so-called F0 (prepared speech) and F1 (spontaneous speech)(More)
In this paper we describe the BBN Byblos 10x real time system used for the 1998 Hub-4 English tests. Given our state of the art primary system [1] running at 230 times real time (230 xRT) we show that eliminating and approximating many computationally expensive components speeds up the system by a factor of 23 with a relative loss in WER of 18%. This is(More)
In this paper, we describe the BBN BYBLOS system used for the 1998 Hub-4E primary and Hub-4Sp evaluation benchmarks, and discuss the improvements made to the system in 1998. We focus on the techniques that were new in this year’s system, including processing of the acoustic training data, test segmentation, revised cepstral normalization and Vocal Tract(More)