Sciweavers

44 search results - page 6 / 9
» Telephone Interview Transcripts
Sort
View
CLIN
2000
13 years 8 months ago
Proper Name Extraction from Non-Journalistic Texts
This paper discusses the influence of the corpus on the automatic identification of proper names in texts. Techniques developed for the newswire genre are generally not sufficient...
Thierry Poibeau, Leila Kosseim
CORR
2000
Springer
79views Education» more  CORR 2000»
13 years 7 months ago
Many uses, many annotations for large speech corpora: Switchboard and TDT as case studies
This paper discusses the challenges that arise when large speech corpora receive an ever-broadening range of diverse and distinct annotations. Two case studies of this process are...
David Graff, Steven Bird
ICASSP
2011
IEEE
12 years 11 months ago
A study of an irrelevant variability normalization based discriminative training approach for LVCSR
This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large v...
Yu Zhang, Jian Xu, Zhi-Jie Yan, Qiang Huo
TASLP
2008
148views more  TASLP 2008»
13 years 7 months ago
Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition
In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoust...
Giulia Garau, Steve Renals
LREC
2010
114views Education» more  LREC 2010»
13 years 8 months ago
The VeteranTapes: Research Corpus, Fragment Processing Tool, and Enhanced Publications for the e-Humanities
Enhanced Publications are a new way to publish scientific and other results in an electronic article. The advantage of EPs is that the relation between the article and the underly...
Henk van den Heuvel, René van Horik, Stef S...