We present an investigation of the relevance of simple conversational features as indicators of topic shifts in small-group meetings. Three proposals for representation of dialogu...
It has been shown that large gains in speech intelligibility can be obtained by using the binary mask approach which retains the time-frequency (T-F) units of the mixture signal t...
This paper describes the AuToBI tool for automatic generation of hypothesized ToBI labels. While research on automatic prosodic annotation has been conducted for many years, AuToB...
Two speech feature sets, RMS rhythmicity and formant frequencies F1-F4, are analyzed for their ability to distinguish alcoholized from sober speech. We describe the statistical fr...
Florian Schiel, Christian Heinrich, Veronika Neume...
This paper presents a Bayesian approach for Gaussian mixture model (GMM)-based speaker identification. Some approaches evaluate the speaker score of a test speech utterance using ...