So-called ill-formed utterances abound in natural discourse. This paper describes how listeners can understand such utterances in a discourse, including speech hesitations and slips-of-the-tongue. Through analysis of durations of utterances and their succeeding pauses, and of intonation patterns, and also through listener understanding experiments using ill-formed utterances, the following resu...

As a step toward simulating dynamic dialogue between agents and humans in virtual environments, we describe learning a model of social behavior composed of interleaved utterances and physical actions. In our model, utterances are abstracted as {speech act, propositional content, referent} triples. After training a classifier on 100 gameplay logs from The Restaurant Game annotated with dialogue ...

This paper presents a method for reducing the effort of transcribing user utterances to develop language models for conversational speech recognition when a small number of transcribed and a large number of untranscribed utterances are available. The recognition hypotheses for untranscribed utterances are classified according to their confidence scores such that hypotheses with high confidence ...

This paper provides a description of the structure and goals of the database of Russian Language Affective (emotional) utterances. It also reports some preliminary results of an experimental phonetic analysis of the acoustic characteristics of emotional utterances (surprise, happiness, anger, sadness and fear) vs. neutral ones in Russian. The study utilizes 600 database utterances by 10 speaker...

This work explores the timing of very short utterances in conversations, as well as the effects of excluding intervals adjacent to such utterances from distributions of betweenspeaker interval durations. The results show that very short utterances are more precisely timed to the preceding utterance than longer utterances in terms of a smaller variance and a larger proportion of no-gap-no-overla...

This paper presents a method for reducing the effort of transcribing user utterances to develop language models for conversational speech recognition when a small number of transcribed and a large number of untranscribed utterances are available. The recognition hypotheses for untranscribed utterances are classified according to their confidence scores such that hypotheses with high confidence ...

This paper presents an effective technique for clustering speech utterances based on their associated speaker. In attempts to determine which utterances are from the same speakers, a prerequisite is to measure the similarity of voice characteristics between utterances. Since the vast majority of existing methods evaluate the inter-utterance similarity by taking only the information from the spe...

This paper discusses how to build a system that can engage in a mixed-initiative human-machine spoken dialogue in which system utterances sometimes overlap with user utterances and vice versa. In the method, a module that incrementally understands user utterances and another module that incrementally generates system utterances work in parallel, and the timing of taking and releasing the dialog...