Sciweavers

1215 search results - page 8 / 243
» A theory of Error-Rate Testing
Sort
View
NAACL
1994
13 years 9 months ago
On Using Written Language Training Data for Spoken Language Modeling
We attemped to improve recognition accuracy by reducing the inadequacies of the lexicon and language model. Specifically we address the following three problems: (1) the best size...
Richard M. Schwartz, Long Nguyen, Francis Kubala, ...
IJDAR
2007
77views more  IJDAR 2007»
13 years 7 months ago
Genre as noise: noise in genre
Given a specific information need, documents of the wrong genre can be considered as noise. From this perspective, genre classification helps to separate relevant documents from...
Andrea Stubbe, Christoph Ringlstetter, Klaus U. Sc...
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
ICASSP
2011
IEEE
12 years 11 months ago
Fast speaker diarization based on binary keys
Splitting a speech signal into speakers is the main goal of a speaker diarization system, which has become an important building block in many speech processing algorithms. Curren...
Xavier Anguera Miró, Jean-François B...
CSDA
2008
102views more  CSDA 2008»
13 years 7 months ago
Step-up and step-down procedures controlling the number and proportion of false positives
In multiple hypotheses testing, it is important to control the probability of rejecting "true" null hypotheses. A standard procedure has been to control the family-wise ...
Paul N. Somerville, Claudia Hemmelmann