In previous work, we proposed a new graph-based semisupervised learning (SSL) algorithm and showed that it outperforms other state-of-the-art SSL approaches for classifying documents and web-pages. Here we use a multi-threaded implementation in order to scale the algorithm to very large data sets. We treat the phonetically annotated portion of the Switchboard transcription project (STP) as labe...

In this paper we present our development work carried out in preparation for the March’96 speaker recognition test on the Switchboard corpus organized by NIST. The speaker verification system evaluated was a Gaussian mixture model. We provide experimental results on the development test and evaluation test data, and some experiments carried out since the evaluation comparing the GMM with a phon...

The NITE XML Toolkit (NXT) provides library support for working with multimodal language corpora. We describe our experiences in using it to study discourse effects on syntactic choice using the parsed Switchboard Corpus as a starting point, as a case study for others who may wish to adopt similar techniques using NXT or one of the other libraries that are beginning to emerge. We discuss conver...

The field of topic spotting in conversational speech deals with the problem of identifying “interesting” conversations or speech extracts amongst large volumes of speech data. In this research, two phoneme-based topic spotting systems were evaluated on the Switchboard Corpus. Experiments [1, 2] on the OGI Corpus suggested that the new Stochastic Method for the Automatic Recognition of Topics (S...

This paper analyzes the issues that arise when trying to add annotations to the dialogues in the Switchboard corpus according to ISO standard 24617-2, exploiting the existing SWBD-DAMSL annotations. These issues relate to differences between the two tag sets; to the highly multidimensional view that underlies the ISO standard; to differences in segmenting the dialogues into functional units; to...

How does the ventral striatum (VS) prioritize and process afferent input? In this issue, Calhoon and O'Donnell (2013) demonstrate that cortical projections to the VS can attenuate hippocampal and thalamic VS input, suggesting that the cortex can uniquely control VS circuit dynamics.

This paper adopts Latent Semantic Analysis (LSA) for longterm analysis of voice quality, in particular creakiness. Each automatically labeled creaky instance (word) is modeled as a document and different prosodic and syntactic cues as terms. This framework attempts to automatically identify the most salient correlates, or latent factors, of creakiness, and further assign each creaky instance (w...

The causes of pronunciation reduction in 8458 occurrences of ten frequent English function words in a four-hour sample from conversations from the Switchboard corpus were examined. Using ordinary linear and logistic regression models, we examined the length of the words, the form of their vowel (basic, full, or reduced), and final obstruent deletion. For all of these we found strong, independen...