Titlebook: Information Retrieval Techniques for Speech Applications; Anni R. Coden,Eric W. Brown,Savitha Srinivasan Conference proceedings 2002 Sprin

STRI

書目名稱Information Retrieval Techniques for Speech Applications影響因子(影響力)




書目名稱Information Retrieval Techniques for Speech Applications影響因子(影響力)學(xué)科排名




書目名稱Information Retrieval Techniques for Speech Applications網(wǎng)絡(luò)公開度




書目名稱Information Retrieval Techniques for Speech Applications網(wǎng)絡(luò)公開度學(xué)科排名




書目名稱Information Retrieval Techniques for Speech Applications被引頻次




書目名稱Information Retrieval Techniques for Speech Applications被引頻次學(xué)科排名




書目名稱Information Retrieval Techniques for Speech Applications年度引用




書目名稱Information Retrieval Techniques for Speech Applications年度引用學(xué)科排名




書目名稱Information Retrieval Techniques for Speech Applications讀者反饋




書目名稱Information Retrieval Techniques for Speech Applications讀者反饋學(xué)科排名

發(fā)出眩目光芒

0302-9743 eon ResearchandDevelopmentinInformationRetrieval.Thetitleoftheworkshop was: “Information Retrieval Techniques for Speech Applications.” Interestinspeechapplicationsdatesbackanumberofdecades.However, it is only in the last few years that automatic speech recognition has left the con?nes of the basic

Pepsin

Capitalization Recovery for Texton output and closed caption text. The value of these text sources can be greatly enhanced with proper capitalization. We describe and evaluate a series of techniques that can recover proper capitalization. Our final system is able to recover more than 88% of the capitalized words with better than 90% accuracy.

取回

Speech and Hand Transcribed Retrievalinary documents are generally retrieved in preference to recognised ones. Means of correcting or eliminating the observed bias is the subject of this paper. Initial ideas and some preliminary results are presented.

NOTCH

Speech-Driven Text Retrieval: Using Target IR Collections for Statistical Language Model Adaptation d to a target collection, we adapt statistical language models used for speech recognition based on the target collection, so as to improve both the recognition and retrieval accuracy. Experiments using existing test collections combined with dictated queries showed the effectiveness of our method.

indemnify

大炮

neutral-posture

Segmenting Conversations by Topic, Initiative, and Stylesegmentations and should be easy to obtain from the audio. Speech style variation at the beginning, middle and end of topics may also be exploited for topical segmentation and would not require the detection of rare keywords.

壓倒性勝利

Extracting Caller Information from Voicemailthis work, we present two information extraction methods, one based on hand-crafted rules, one based on statistically trained maximum entropy model.We evaluate their performance on both manually transcribed messages and on the output of a speech recognition system.

窗簾等