Switchboard in orbit

Disfluencies in Switchboard

Disfluencies (“um,” repeats, self-repairs) are prevalent in spontaneous speech, and are relevant to both human speech communication and speech processing by machine. Although disfluencies have commonly been viewed as ‘noisy’ events, results from a large descriptive study indicate that disfluencies show regularities in a number of dimensions [9]. This paper reports selected results on Switchboar...

Resegmentation of SWITCHBOARD

The SWITCHBOARD (SWB) corpus is one of the most important benchmarks for recognition tasks involving large vocabulary conversational speech (LVCSR). The high error rates on SWB are largely attributable to an acoustic model mismatch, the high frequency of poorly articulated monosyllabic words, and large variations in pronunciations. It is imperative to improve the quality of segmentations and tr...

An endosomal switchboard

oad the heat-shock protein Hsp70 with a peptide from a tumor-specific antigen, then inject it into a mouse bearing a tumor with the same antigen, and the mouse will mount a vigorous immune response that can significantly reduce tumor progression. The result is promising, but how does it work? Studying human Hsp70, Becker et al. (page 1277) now show that the cell surface protein CD40 binds speci...

Switchboard Workshop 1998

Towards Interpretation of Creakiness in Switchboard

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...