The focus of this thesis proposal is to improve the ability of a computational system to understand spoken utterances in a dialogue with a human. Available computational methods for word recognition do not perform as well on spontaneous speech as we would hope. Even a state of the art recognizer achieves slightly worse than 70% word accuracy on (nearly) spontaneous speech in a conversation about a specific problem. To address this problem, I will explore novel methods for post-processing the output of a speech recognizer in order to correct errors. I adopt statistical techniques for modeling the noisy channel from the speaker to the listener in order to correct some of the errors introduced there. The statistical model accounts for frequent errors such as simple word/word confusions and short phrasal problems (one-to-many word substitutionsand many-to-one word concatenations). To use the model, a search algorithm is required to find the most likely correction of a given word sequence ...

Abstract. In this paper we describe a screening approach forspeech/ language analysis using learned, at connectionist representations. For investigating this approach we built a hybrid connectionist system using a large number of connectionist and symbolic modules. Our system SCREEN 1 learns a at syntactic and semantic analysis of incremental streams of word hypothesis sequences. In this paper we focus on techniques for improving the quality of pruned hypotheses from a speech recognizer using acoustic, syntactic, and semantic knowledge. We show that the developed architecture is able to cope with real-world spontaneously spoken language in an incremental and parallel manner. 1

. In this paper we describe a screening approach for speech/ language analysis using learned, flat connectionist representations. For investigating this approach we built a hybrid connectionist system using a large number of connectionist and symbolic modules. Our system SCREEN 1 learns a flat syntactic and semantic analysis of incremental streams of word hypothesis sequences. In this paper we focus on techniques for improving the quality of pruned hypotheses from a speech recognizer using acoustic, syntactic, and semantic knowledge. We show that the developed architecture is able to cope with real-world spontaneously spoken language in an incremental and parallel manner. 1 Introduction Processing real-world spontaneously spoken language in computational models causes more problems than the analysis of written texts since spontaneous language is often irregular, faulty and heterogeneous. Besides the "noise" produced by a human speaker (interjections, pauses, repetitions, repairs, re...

Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language models, many current spoken-language systems still use a relatively brittle, hand-coded symbolic grammar or symbolic semantic component. In contrast, we describe a so-called screening approach for learning robust processing of spontaneously spoken language. A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels. Rather than using a deeply structured symbolic analysis, we use a flat connectionist analysis. This screening approach aims at supporting speech and language processing by using (1) data-driven learning and (2) robustness of connectionist networks. In order to test this approach, we have developed the screen system which is ba...