Automatic speech recognition systems generally produce unpunctuated text which is difficult
to read for humans and degrades the performance of many downstream machine …

The expression and experience of human behavior are complex and multimodal and
characterized by individual and contextual heterogeneity and variability. Speech and …

Unlike read or laboratory speech, spontaneous speech contains high rates of disfluencies
(eg repetitions, repairs, filled pauses, false starts). This paper aims to promote 'disfluency …

A crucial step in processing speech audio data for information extraction, topic detection, or
browsing/playback is to segment the input into sentence and topic units. Speech …

Effective human and automatic processing of speech requires recovery of more than just the
words. It also involves recovering phenomena such as sentence boundaries, filler words …

This article contains a literature review of evidence of large prosodic domains that
correspond to syntactic units such as a clause or a sentence. In particular, different phonetic …

The output of automatic speech recognition systems is generally an unpunctuated stream of
words which is hard to process for both humans and machines. We present a two-stage …

Unlike read or laboratory speech, spontaneous speech contains high rates of disfluencies
(eg, repetitions, repairs, filled pauses). Such events reflect production problems frequently …

This paper focuses on the task of inserting punctuation symbols into transcribed
conversational speech texts, without relying on prosodic cues. We investigate limitations …

Ensuring proper punctuation and letter casing is a key pre-processing step towards applying
complex natural language processing algorithms. This is especially significant for textual …