31 search results - page 2 / 7 » Prosody-Based Automatic Segmentation of Speech into Sentence... |
COLING
1996
13 years 6 months ago
1996
Statistical language models play a major role in current speech recognition systems. Most of these models have focussed on relatively local interactions between words. Recently, h...
SEMCO
2007
IEEE
13 years 11 months ago
2007
IEEE
Automatic sentence segmentation of spoken language is an important precursor to downstream natural language processing. Previous studies combine lexical and prosodic features, but...
ACL
2008
13 years 6 months ago
2008
This paper explores the relationship between discourse structure and coverbal gesture. Using the idea of gestural cohesion, we show that coherent topic segments are characterized ...
CORR
2004
Springer
13 years 4 months ago
2004
Springer
We are developing a cross-media information retrieval system, in which users can view specific segments of lecture videos by submitting text queries. To produce a text index, the ...
LREC
2008
13 years 6 months ago
2008
Language models used in current automatic speech recognition systems are trained on general-purpose corpora and are therefore not relevant to transcribe spoken documents dealing w...