Sciweavers

346 search results - page 59 / 70
» Speaker recognition
Sort
View
NIPS
1998
13 years 10 months ago
Controlling the Complexity of HMM Systems by Regularization
This paper introduces a method for regularization of HMM systems that avoids parameter overfitting caused by insufficient training data. Regularization is done by augmenting the E...
Christoph Neukirchen, Gerhard Rigoll
EMNLP
2010
13 years 6 months ago
Automatic Comma Insertion for Japanese Text Generation
This paper proposes a method for automatically inserting commas into Japanese texts. In Japanese sentences, commas play an important role in explicitly separating the constituents...
Masaki Murata, Tomohiro Ohno, Shigeki Matsubara
CLEF
2009
Springer
13 years 6 months ago
Exploiting Speech Recognition Transcripts for Narrative Peak Detection in Short-Form Documentaries
Narrative peaks are points at which the viewer perceives a spike in the level of dramatic tension within the narrative flow of a video. This paper reports on four approaches to na...
Martha Larson, Bart Jochems, Ewine Smits, Roeland ...
ECML
1993
Springer
14 years 21 days ago
Exploiting Context When Learning to Classify
This paper addresses the problem of classifying observations when features are context-sensitive, specifically when the testing set involves a context that is different from the t...
Peter D. Turney
TASLP
2010
133views more  TASLP 2010»
13 years 3 months ago
Unsupervised Equalization of Lombard Effect for Speech Recognition in Noisy Adverse Environments
In the presence of environmental noise, speakers tend to adjust their speech production in an effort to preserve intelligible communication. The noise-induced speech adjustments, c...
Hynek Boril, John H. L. Hansen