This paper proposes a new method for automatically detecting disfluencies in spontaneous speech – specifically, selfcorrections – that explicitly models repetitions vs. other disfluencies. We show that, in a corpus of Supreme Court oral arguments, repetition disfluencies can be longer and more stutterlike than the short repetitions observed in the Switchboard corpus and suggest that they can be...

The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness of spontaneous speech transcripts. This paper presents a system that detects various types of disfluencies and other structural information with cues obtained from lexical and prosodic information sources. Specifically...

Speakers effectively use both visual and acoustic cues to convey information in speech. While earlier research has concentrated on the association of visual cues (provided by gestures) with fluent prosodic structure, this study looks at the relationship between visual cues, prosodic markers and spoken disfluencies. Preliminary results suggested that speakers preferentially perform gestures in t...

UNLABELLED Data on disfluencies in the speech of non-stuttering adults are relevant to several aspects of the assessment and treatment of adults who stutter. Currently, very few sources provide relevant data. In the existing literature on normally fluent speakers, there is no consistency in sample length or topic or in which types of disfluency are counted. Many studies report incomplete data, ...

Disfluencies in speech are instances of hesitation or correction that affect both the speaker and the listener. Typical surface forms of disfluencies are filled pauses (such as uh, uhm), silences at places in the utterance where syntax would not predict them, or repetitions of parts of the utterance (like (I mean + I mean) we should go). Disfluencies carry a folk notion of erroneousness or badn...

The thesis aimed explored disfluencies in stuttering through linguistic contrasts between English and German. Part one focused on the analysis o f speech samples of German speaking adults and children who stutter. Part two analysed bilingual German-English language development aiming to examine whether increased cognitive load o f two languages is related to language errors. Since people who st...

A large volume of literature now links language demand and fluency behaviors in children. Although it might be reasonable to assume that children with relatively weak language skills might demonstrate higher levels of disfluency, the sparse literature on this topic is characterized by conflicting findings on the relationship between language impairment and disfluency. However, in studies findin...

Speech transcripts often only capture semantic content, omitting disfluencies that can be useful for analyzing social dynamics of a discussion. This work describes steps in building a model that can recover a large fraction of locations where disfluencies were present, by transforming carefully annotated text to match the standard transcription style, introducing a two-stage model for handling ...