We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topic units. The approach combines hidden Markov models, statistical language models, and prosody-based decision trees. Lexical information is obtained from a speech recognizer, and prosodic features are extracted automatically from speech waveforms. We evaluate our approach o...

The Role of the Syllable in Speech Segmentation In previous papers we proposed that the syllable is a natural unit in speech processing (Mehler, Segui, and Frauenfelder 1981; Mehler 1981; Segui 1984). According to this position, syllabic units are constructed from the continuous speech signal and constitute the input for lexical access and eventually for more detailed phonemic analysis. This hy...

We present a domain-independent topic segmentation algorithm for multi-party speech. Our feature-based algorithm combines knowledge about content using a text-based algorithm as a feature and about form using linguistic and acoustic cues about topic shifts extracted from speech. This segmentation algorithm uses automatically induced decision rules to combine the different features. The embedded...

Brent, Lexical acquisition and lexical access 1 Abstract Much eeort has gone into constructing models of how children segment speech and thereby discover the words of their language. Much eeort has also gone into constructing models of how adults access their mental lexicons and thereby segment speech into words. In this paper, I explore the possibility of a model that could account for both wo...

This paper presents an unsupervised and incremental model of learning segmentation that combines multiple cues whose use by children and adults were attested by experimental studies. The cues we exploit in this study are predictability statistics , phonotactics , lexical stress and partial lexical information . The performance of the model presented in this paper is competitive with the state-o...

Segmentation research asks how listeners locate word boundaries in the ongoing speech stream. Previous work has identified multiple cues (lexical, segmental, prosodic) which affect perception of boundary placement, but such studies have almost exclusively used careful read speech, rather than speech elicited in a natural communicative context. We report development of a segmentation-oriented co...

The Role of the Syllable in Speech Segmentation In previous papers we proposed that the syllable is a natural unit in speech processing (Mehler, Segui, and Frauenfelder 1981; Mehler 1981; Segui 1984). According to this position, syllabic units are constructed from the continuous speech signal and constitute the input for lexical access and eventually for more detailed phonemic analysis. This hy...

Human listeners use lexical stress for word segmentation and disambiguation. We look into using lexical stress for largevocabulary speech recognition for the Dutch language. It appears that beside vowels, consonants should be taken into account. By introducing stressed phonemes, and features for spectral bands and the fundamental frequency, we reduce the word error rate by 2.6 %.