As interactive voice response systems become more prevalent and provide increasingly more complex functionality, it becomes clear that the challenges facing such systems are not solely in their synthesis and recognition capabilities. Issues such as the coordination of turn exchanges between system and user also play an important role in system usability. In particular, both systems and users ha...

This paper describes a transformation-based learning approach to disfluency detection in speech transcripts using primarily lexical features. Our method produces comparable results to two other systems that make heavy use of prosodic features, thus demonstrating that reasonable performance can be achieved without extensive prosodic cues. In addition, we show that it is possible to facilitate th...

We propose that, in Mandarin speech, an automatic prosodic break detector can be trained without any prosodically labeled training data. We use only lexical and acoustic cues to create a small labeled training set, then use semi-supervised learning to train a prosodic break detector. A generative mixture model is proposed as the learning algorithm that can learn with both labeled and unlabeled ...

Variations in the acoustic manifestations of the rounding and height contrasts in French vowels are investigated in different prosodic positions. Four speakers produced sentences containing the vowels /i, e, a, y, ø/ at the beginning of different prosodic constituents: Intonational Phrase, Accentual Phrase and Word. Acoustic cues for the rounding contrast (F2, F3, F3-F2) and for the vowel heigh...

As the basic prosodic unit, the prosodic word influences the naturalness and the intelligibility greatly. Although the research shows that the lexicon word are greatly different from the prosodic word, the lexicon word still provides the important cues for the prosodic word forming. The rhythm constraint is another important factor for the prosodic word prediction. Some lexicon word length patt...

In this paper we show how prosody can be used in spoken dialog systems. First, we describe the phenomena that prosodic analysis is concerned with and give examples why prosody is relevant in the context of spoken dialog processing. Then we examine prosody in the light of pattern classification. We show how prosodic events can be categorized. We detail how those prosodic events manifest themselv...

This study presents an approach for prosody-driven segmentation of speech data. The model is based solely on F0 contours and RMS envelopes. Phoneme or word information from a speech recognizer is unneccesary. Using data from German broadcast news, we show how this prosodic information can be exploited to retrieve structural information of the spoken text. The suitability of the CART-like algori...

In most of the cases spontaneaously uttered units of speech (e.g. in face-to-face dialogues) contain performance phenomena like repairs, breaking offs, omissions and others that motivate a restructuring procedure which allows storage or further processing of the input. In our view, this restructuring procedure is based on the segmentation of the input into a set of functional (i.e. meaningful) ...

Discovering and quantifying the prosodic signals that help manage turn-taking is difficult, in part because of the limitations of commonly used methods. This paper presents an integrated method that uses both perceptually-based analysis and quantitative analysis. The eight activities involved in the method — clarification of aims, problem formulation, corpus preparation, feature discovery, feat...