The Rwth Speech Recognition System and Spoken Document Retrieval
نویسندگان
چکیده
In this paper, we present an overview of the RWTH Aachen large vocabulary continuous speech recognizer. The recognizer is based on continuous density hidden Markov models and a time-synchronous left-to-right beam search strategy. Experimental results on the ARPA Wall Street Journal (WSJ) corpus verify the effects of several system components, namely linear discriminant analysis, vocal tract normalization, pronunciation lexicon and cross-word triphones, on the recognition performance. Finally, the extension of the recognition system towards spoken document retrieval is discussed.
منابع مشابه
Spoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting
Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIBchr('39')s archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting...
متن کاملa Spoken Document Retrieval Application in the Oral History Domain
The application of automatic speech recognition in the broadcast news domain is well studied. Recognition performance is generally high and accordingly, spoken document retrieval can successfully be applied in this domain, as demonstrated by a number of commercial systems. In other domains, a similar recognition performance is hard to obtain, or even far out of reach, for example due to lack of...
متن کاملThe Cambridge University spoken document retrieval system
This paper describes the spoken document retrieval system that we have been developing and assesses its performance using automatic transcriptions of about 50 hours of broadcast news data. The recognition engine is based on the HTK broadcast news transcription system and the retrieval engine is based on the techniques developed at City University. The retrieval performance over a wide range of ...
متن کاملTowards an integrated approach for spoken document retrieval
This paper presents a novel approach to spoken document retrieval where the speech recognition and information retrieval components are more tightly integrated. This is done by developing new recognizer and retrieval models where the interface between the two components is better matched and the component goals are consistent with the overall goal of the combined system. Experiments on radio ne...
متن کاملLexicon optimization for dutch speech recognition in spoken document retrieval
In this paper, ongoing work concerning the language modelling and lexicon optimization of a Dutch speech recognition system for Spoken Document Retrieval is described: the collection and normalization of a training data set and the optimization of our recognition lexicon. Effects on lexical coverage of the amount of training data, of decompounding compound words and of different selection metho...
متن کامل