Our aim is to annotate some of (or excerpts of some of) the Switchboard dialogues for (co-)reference and information structure. Information structure at this stage does not include pitch accents and nothing about them is included in this document as of now. Information status at the moment is defined via three categories: old, mediated, new (see Section 5). We will annotate information status o...

Speaker variability strongly impacts human perception and technology performance, yet large-scale, systematic study of the acoustic characteristics involved is rarely undertaken. This study provides statistics on selected segmental and suprasegmental acoustic parameters from measures made on spontaneous conversational telephone speech from 160 speakers in the Switchboard Corpus. Since spontaneo...

We are applying a memory based learning (MBL) algorithm to the task of automatic dialog act (DA) tagging. This work is along the lines of a recent trend that considers MBL as being more appropriate for natural language processing. We did the experiments on the Switchboard corpus, overcome the problem of feature selection and yield results that seem to be better that previous reported results on...

In many residential buildings the electrical wires of individual houses are laid in same conduit pipe and some mistakes could be made identifying similar coloured when they pipe. Most faults caused by neutral interconnection wiring system. Usually connected to bus within panel board or switchboard, "bonded" earth ground. our secondary distribution, tree system supply is mostly utilized. The vol...

This paper summarizes the work of the “Rapid Speech Recognizer Adaptation” team in the workshop held at Johns Hopkins University in the summer of 1998. The project addressed the modeling of dependencies between units of speech with the goal of making more effective use of small amounts of data for speaker adaptation. A variety of methods were investigated and their effectiveness in a rapid adap...

Dialogue acts play an important role in modelling discourse phenomena in several components of modern dialogue systems. Many different features have been so far proposed for dialogue act recognition. In this report, we take a cue-based model approach, and use N grams in utterances in dialogue as cue phrases. In our experiment with the switchboard corpus, we obtained 57.1% classification accurac...

We present a system for summarizing transcripts of conversational dialogues based on lexical chaining. The experiments were carried out with twenty Switchboard dialogues (LDC, 1993). We designed and implemented four summarization methods employing lexical chains as their source representation. The summarization task is defined as extracting the most relevant utterances conveying the meaning of ...

In this paper, we apply a bidirectional Long Short-Term Memory with a Conditional Random Field to the task of disfluency detection. Long-range dependencies is one of the core problems for disfluency detection. Our model handles long-range dependencies by both using the Long Short-Term Memory and hand-crafted discrete features. Experiments show that utilizing the hand-crafted discrete features s...

In this paper we discuss the use of multilayered tagsets for dialogue acts, in the context of dialogue understanding for multiparty meeting recording and retrieval applications. We discuss some desiderata for such tagsets and critically examine some previous proposals. We then define MALTUS, a new tagset based on the ICSI-MR and Switchboard tagsets, which satisfies these requirements. We presen...

We show how the factor analysis model for speaker verification can be successfully implemented using some fast approximations which result in minor degradations in accuracy and open up the possibility of training the model on very large databases such as the union of all of the Switchboard corpora. We tested our algorithms on the NIST 1999 evaluation set (carbon data as well as electret). Using...